No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Real-time line detection through an improved Hough transform voting scheme
Abstract
The Hough transform (HT) is a popular tool for line detection due to its robustness to noise and missing data. However, the computational cost associated to its voting scheme has prevented software implementations to achieve real-time performance, except for very small images. Many dedicated hardware designs have been proposed, but such architectures restrict the image sizes they can handle. We present an improved voting scheme for the HT that allows a software implementation to achieve real-time performance even on relatively large images. Our approach operates on clusters of approximately collinear pixels. For each cluster, votes are cast using an oriented elliptical-Gaussian kernel that models the uncertainty associated with the best-fitting line with respect to the corresponding cluster. The proposed approach not only significantly improves the performance of the voting scheme, but also produces a much cleaner voting map and makes the transform more robust to the detection of spurious lines.
... In response to the aforementioned challenges, this paper takes advantage of the consistent and stable information that line features provide in low-textured environments and their consistency across different viewpoints. This paper proposes a CSM pose estimation Remote Sens. 2024, 16,114 3 of 26 method that integrates visual and radar line features. The main contributions of this paper are as follows: ...
... Commonly used line detection algorithms include Hough [16], LSWMS [17], Edline [18], and LSD [19]. Most of these methods rely on image gradients or edge information, and different methods have varying sensitivities to lines. ...
... The updated mean is shown in Equation (16). ...
Millimeter-wave radar and optical cameras are one of the primary sensing combinations for autonomous platforms such as self-driving vehicles and disaster monitoring robots. The millimeter-wave radar odometry can perform self-pose estimation and environmental mapping. However, cumulative errors can arise during extended measurement periods. In particular scenes where loop closure conditions are absent and visual geometric features are discontinuous, existing loop detection methods based on back-end optimization face challenges. To address this issue, this study introduces a correlative scan matching (CSM) pose estimation method that integrates visual and radar line features (VRL-SLAM). By making use of the pose output and the occupied grid map generated by the front end of the millimeter-wave radar’s simultaneous localization and mapping (SLAM), it compensates for accumulated errors by matching discontinuous visual line features and radar line features. Firstly, a pose estimation framework that integrates visual and radar line features was proposed to reduce the accumulated errors generated by the odometer. Secondly, an adaptive Hough transform line detection method (A-Hough) based on the projection of the prior radar grid map was introduced, eliminating interference from non-matching lines, enhancing the accuracy of line feature matching, and establishing a collection of visual line features. Furthermore, a Gaussian mixture model clustering method based on radar cross-section (RCS) was proposed, reducing the impact of radar clutter points online feature matching. Lastly, actual data from two scenes were collected to compare the algorithm proposed in this study with the CSM algorithm and RI-SLAM.. The results demonstrated a reduction in long-term accumulated errors, verifying the effectiveness of the method.
... Collinear points in the image space are represented by a single point (r , θ ) at which sinusoidal curves in the polar coordinate space intersect. Straight lines can be detected by evaluating the accumulation value at that point (r , θ ) in the polar coordinate space, as illustrated in Figure 3. HT can also be applied to detect geometric shapes such as circles, ellipses, and other specific shapes in addition to line detection [25,26]. objects, it is used to remove stars, filter out sporadic noise and cosmic rays to reduce the influence of background moving objects. ...
... The moving objects appear as straight lines, which can be recognized using HT. Hough transform [24] is based on the concept of map- in the polar coordinate space, as illustrated in Figure 3. HT can also be applied to detect geometric shapes such as circles, ellipses, and other specific shapes in addition to line detection [25,26]. HT exhibits high computational complexity, particularly when handling large-sized images. ...
Compared with the international meteor surveillance systems, the ground wide angle camera (GWAC) system exhibits characteristics such as images with the resolution of 4K × 4K and single-site observation. These characteristics present challenges for meteor detection in the GWAC system. Consequently, this paper proposes a new meteor detection algorithm for the GWAC system on the base of the solely mini-GWAC system data algorithm. The new algorithm consists of the following key steps: (1) to compare differences between adjacent frames, applying block-based image binarization thresholds, and incorporating median filtering to reduce noise; (2) to adopt the probabilistic Hough transform (PHT) to identify moving objects and cluster them based on the origin moment of the line segments, while assessing the credibility of clustering; (3) to introduce the so-called maximum disappearance frame for moving objects in the tracking algorithm, enhancing the ability to track multi-frame moving objects. The utilization of the line segment inclination angle of the moving object as the direction of movement facilitates the tracking of multiple moving objects, thereby reducing the probability of mistakenly selecting single-frame moving objects; (4) to leverage the light curves of single-frame moving objects to select meteors to enhance the accuracy of meteor detection. Comparative experiments demonstrate that our proposed algorithm processes each frame image in just 0.39 s, achieving an accuracy of 89.8% in the dataset of 5856 adjacent frames. The experimental results indicate that the algorithm achieved an accuracy of 90.27% when applied in the meteor detection of the image data captured by the GWAC system from Dec. 10th to 19th in 2019 and 2021, obtaining excellent detection results.
... This is associated with the widespread development and application of unmanned aerial vehicles (UAVs) in many fields, including the military sphere. Known works explore the influence of geometric distortions on the formation of the DF [8], as well as the possible appearance of false objects [9]. In this regard, the task is typically solved using a single informational feature -signal intensity. ...
The purpose of the article is to substantiate the feasibility of using object contrast as an informative feature for the formation of images used in technical vision systems. This goal is achieved by studying the dependence of the contrast of objects in images on the viewing geometry and determining the conditions under which the greatest similarity of the compared images is ensured. The solution to the first problem is based on the presentation of reference information about sighted objects, taking into account the navigation parameters of mobile robots. By modeling in the MATLAB software environment for typical viewing conditions, selective images were obtained using randomly selected fragments from Google Earth Pro, the distribution of contrast values and the cross-correlation function of the original and selective images. The influence of viewing angles on the distribution of contrasts and the formation of the decisive function was determined. The studies were performed for viewing angles of -60˚, -80˚ and -90˚ for altitudes in the range from 500 to 600 meters. The most significant result is a model of a set of reference images, taking into account the influence of navigation parameters on the contrast of objects, as well as experimentally established dependences of the distribution of contrasts for typical viewing conditions. The novelty of the work lies in the fact that the procedure for generating images and the decision function using the contrast of objects has been further developed. This will significantly increase the efficiency of selection of objects with insignificant brightness characteristics.
... This stage becomes significantly important when locating the UAV on the navigation route with the presence of small-sized objects, especially under the influence of interference leading to a reduction in the signalto-noise ratio in the image, which, in turn, deteriorates the accuracy characteristics of the CVS. Various applications of multipath processing for the purpose of selecting an object of interest on the current image (CI) have been explored in numerous works [6][7][8][9][10][11]. Multipath processing is based on the properties of the intensity histogram of the original image. ...
The purpose of the article is to develop a three-stage procedure for identifying an anchor object in a noisy current image. This goal is achieved by determining the sampling threshold levels at which the greatest similarity of the compared images is ensured; development of a procedure for refining the maximum of the decision function by quantizing the current image. The solution to the first problem is based on the formation of a correlation field of radio brightness temperatures and the choice of a sampling threshold. It is proposed to use the cross-correlation coefficient as a criterion for the degree of image matching. The effectiveness of the procedure for selecting a fragment of a reference image is assessed based on the criterion of the probability of selecting a fragment of a reference image. It is shown that image noise can lead to a decrease in the probability of selecting a fragment of a reference image, down to 0.4. It is proposed to refine the maximum of the decision function based on the iteration method. The most significant results are the obtained dependences of the probability of choosing a fragment of the reference image on the threshold value and the signal-to-noise ratio, as well as the analytical relation for the asymptote of this dependence. The novelty of the work lies in the fact that the procedure for forming the decisive function has been further developed. This will significantly improve the operating efficiency of unmanned aerial vehicles, especially in conditions of interference.
... Hence, CFH was also designed to detect the weld lines to register cracks. Hough transform (HT) is one classical method for line detection (Fang & Leung, 2006;Fernandes & Oliveira, 2008), whose core concept is to parameterize objects, and then identify shapes in the parametric domain. As shown in Figure 3a, in a 2D image I∈ℝ H×W , a line l can be characterized by two parameters: the slope θ l ∈[0, π) and the bias ∈ [− √ 2 + 2 ∕2, √ 2 + 2 ∕2]. ...
Digital twin requires establishing a self‐updated model to simulate the structural damage perceived onsite. Despite the great success in damage identification and quantification, the difficulty in registration still limits the efficiency of model updating. This study presented a framework that enables a finite element (FE) model of welded joints to remesh itself for updating the geometric changes caused by the fatigue crack. Leveraging the linear geometry of the weld, a crack registration algorithm was proposed for the automation of crack perception. First, a dual‐task network was established to identify the crack and weld on the 2D image, where the deep Hough transform was introduced to detect the positioning weld among the irregular structural geometry. With the time‐of‐flight technique, the crack was then reconstructed and quantified in the 3D camera coordinate system. Meanwhile, the 3D structure coordinate system was established from positioning welds. Through simple coordinate transformation, the fatigue crack was automatically registered to the welded joint. Finally, the perception algorithms were integrated with the FE model, taking about 1 min to map the crack into the model. Under laboratory tests, the perception performance was not sensitive to the camera pose. The perceived errors were mainly reflected in the crack local morphology, not leading to improper reconstruction of the structural stiffness matrix.
... Line segment detection is a classical problem in computer vision that can be traced back to the Hough Transform [24] and its improvements [41,19,84]. Local line segment detectors [21,2,63,62,46] are efficient alternatives that fit segments to local regions with a prominent gradient. ...
... Galamhos et al. [7] proposed the progressive probabilistic Hough transform, which makes the line segment detection faster by randomly selecting the edge pixels. Fernandes et al. [8] improved the voting method by using a directional elliptical Gaussian kernel to vote, achieving more robust detection. However, these methods still cannot solve the problem of false positive well. ...
Aiming at the problem that the existing line segment detectors will detect overdense meaningless textures, this paper proposes a fusing contour features optimization method for line segment detector, called CF-Lines. We define a new line segment attribute, called "line segment associate contour(LAC)" attribute, which includes the contour features, the length and the angle of line segment. After using existing algorithms to detect contours and line segments, CF-Lines calculates the LAC of all line segments. When the LAC is greater than the threshold and passes the quantitative verification, the line segment is removed as overdense meaningless texture. Using the YorkUrban and Wireframe datasets, the CF-Lines is tested and compared with original detectors. Experimental results show that CF-Lines performs better than the original detectors in average precision, F-score, average length of line segments and average number of line segments.
... Feature-voting (Boiangiu and Radu, 2003;Leonardo and Manuel, 2008) is a process to estimate model parameters using input values, while reversing the roles of input data and estimated parameters. For a specific model, for each parameter, numerous values are spread; for each selected value-set each input is tested: if the input is compatible with the value-set, a vote is listed for that specific value-set. ...
... There exists several classical line feature extraction algorithms, such as LSD [23], EDLines [24], Hough [25], CannyLines [26]. CubeSLAM uses LSD [23] to extract line features and use it for the construction of 3D BBox. ...
Object-level landmarks enable the SLAM system to construct robust object-keyframe constraints of bundle adjustment and improve the pose estimation performance. In this paper, we present a real-time online object-level SLAM. The dual Bundle Adjustment (BA) optimization method, including high and low frequencies, is proposed to optimize the estimated pose. The High-frequency BA (HBA) module is used to quickly estimate the camera pose by matching landmarks of keyframes and feature points of the current frame. Then, the estimated camera pose is used in the Low-frequency BA (LBA) module to improve the trajectory accuracy. The LBA module integrates the object-level landmarks into the pose graph to optimize the camera pose of local mapping. Moreover, we build an additional object detection thread to extract object 2D bounding boxes online. While this paper improves the data association through the depth projection of point-line features and the Euclidean distance of object centroid. Experimental results show that our proposed algorithm effectively reduce the drift error of camera pose estimation and improve the accuracy by a large margin on different datasets.
... The third stage involves determining the minimum permissible correlation between adjacent reference images forming the required minimum set for the chosen range of viewing parameters, satisfying condition (6) and the unimodality of the function ( , ) t Rr . In the final stage, the minimum number of reference images forming the desired set is determined based on the minimum permissible degree of correlation between individual images. ...
The aim of this work is to reduce the amount of computational cost when monitoring the state of critical infrastructure objects using flying mobile robots equipped with correlation-extreme navigation system, based on minimizing the number of fragments of reference images. The goal is achieved by establishing a minimum permissible degree of correlation between the individual images, which form a set of reference images. The most essential result is substantiation of the approach to formation of a set of selective images based on scene correlation analysis and sufficiency of conservation of correlation connection of images in limits 0.6 ... 0.7. This reduces the amount of computation and extends the operating time of mobile robots while maintaining accuracy. The significance of the obtained results consists in the possibility of solving a complex task of forming a set of reference images, depending on the information content and stochastic conditions of sighting of critical infrastructure objects. The solution of this task will increase efficiency of critical infrastructure objects state control due to optimization of reference images number used in the monitoring process, increase operability, and provide high control reliability in stochastic sighting conditions. The novelty of the work lies in the fact that the method of process formalized description of forming a reference images set to ensure reliable monitoring of critical infrastructure facilities using flying mobile robots for various sectors of the economy, the practical application of which will ensure reliable control and their condition assessment.
... Borrmann et al. summarize these methods [23] and their experiments indicate RHT is the best one. Inspired by the kernel-based HT (KHT) [24] which is designed for 2D images, Limberger et al. [25] present a deterministic technique that combines with octree and principal component analysis (PCA). The method achieves state-of-art real-time extraction with cost O(nlogn). ...
Bundle adjustment (BA) on LiDAR point clouds has been extensively investigated in recent years due to its ability to optimize multiple poses together, resulting in high accuracy and global consistency for point cloud. However, the accuracy and speed of LiDAR bundle adjustment depend on the quality of plane extraction, which provides point association for LiDAR BA. In this study, we propose a novel and efficient voxel-based approach for plane extraction that is specially designed to provide point association for LiDAR bundle adjustment. To begin, we partition the space into multiple voxels of a fixed size and then split these root voxels based on whether the points are on the same plane, using an octree structure. We also design a novel plane determination method based on principle component analysis (PCA), which segments the points into four even quarters and compare their minimum eigenvalues with that of the initial point cloud. Finally, we adopt a plane merging method to prevent too many small planes from being in a single voxel, which can increase the optimization time required for BA. Our experimental results on HILTI demonstrate that our approach achieves the best precision and least time cost compared to other plane extraction methods.
... The Hough transform [43] consists of the transition from the image space to the parameter space and the subsequent search for extreme values corresponding to lines using the voting procedure. Along with the classical Hough transform [44], there are a large number of optimizations that include probabilistic algorithms [45]- [47], as well as algorithms that analyze neighborhoods of peak values in the parametric space [48]. ...
Lines are interesting geometrical features commonly seen in indoor and urban environments. There is missing a complete benchmark where one can evaluate lines from a sequential stream of images in all its stages: Line detection, Line Association and Pose error. To do so, we present a complete and exhaustive benchmark for visual lines in a SLAM front-end, both for RGB and RGBD, by providing a plethora of complementary metrics. We have also labelled data from well-known SLAM datasets in order to have all in one poses and accurately annotated lines. In particular, we have evaluated 17 line detection algorithms, 5 line associations methods and the resultant pose error for aligning a pair of frames with several combinations of detector-association. We have packaged all methods and evaluations metrics and made them publicly available on web-page.
... Line segment detection is a classical problem in computer vision that can be traced back to the Hough Transform [23] and its improvements [39,18,80]. Local line segment detectors [20,2,59,58] are efficient alternatives that fit segments to local regions with a prominent gradient. ...
Line segments are powerful features complementary to points. They offer structural cues, robust to drastic viewpoint and illumination changes, and can be present even in texture-less areas. However, describing and matching them is more challenging compared to points due to partial occlusions, lack of texture, or repetitiveness. This paper introduces a new matching paradigm, where points, lines, and their descriptors are unified into a single wireframe structure. We propose GlueStick, a deep matching Graph Neural Network (GNN) that takes two wireframes from different images and leverages the connectivity information between nodes to better glue them together. In addition to the increased efficiency brought by the joint matching, we also demonstrate a large boost of performance when leveraging the complementary nature of these two features in a single architecture. We show that our matching strategy outperforms the state-of-the-art approaches independently matching line segments and points for a wide variety of datasets and tasks. The code is available at https://github.com/cvg/GlueStick.
... In contrast, the works of refs. [17,18] use a kernel-based Hough transform to improve the original HT by performing Hough voting on collinear pixels with an elliptical Gaussian kernel. Additionally, John et al. [19,20] input image into hierarchical image patches and then independently apply HT to each patch. ...
Transmission line detection is the basic task of using UAVs for transmission line inspection and other related tasks. However, the detection results based on traditional methods are vulnerable to noise, and the results may not meet the requirements. The deep learning method based on segmentation may cause a lack of vector information and cannot be applied to subsequent high-level tasks, such as distance estimation, location, and so on. In this paper, the characteristics of transmission lines in UAV images are summarized and utilized, and a lightweight powerline detection network is proposed. In addition, due to the reason that powerlines often run through the whole image and are sparse compared to the background, the FPN structure with Hough transform and the neck structure with multi-scale output are introduced. The former can make better use of edge information in a deep neural network as well as reduce the training time. The latter can reduce the error caused by the imbalance between positive and negative samples, make it easier to detect the lines running through the whole image, and finally improve the network performance. This paper also constructs a powerline detection dataset. While the net this paper proposes can achieve real-time detection, the f-score of the detection dataset reaches 85.6%. This method improves the effect of the powerline extraction task and lays the groundwork for subsequent possible high-level tasks.
... For a curve with n parameters, it improves efficiency by randomly selecting n pixels and mapping them to a point in the parameter space. Fernandes et al. [23] proposed a kernel-based Hough transform (KHT) method, which improves the robustness of HT using an effective voting scheme. Du et al. [24] proposed a method that could accurately extract the endpoints of line segments, which uses the geometric analysis method to extract inherent features of line segments from the voting distribution near the HT peak. ...
The relative pose estimation of the space target is indispensable for on-orbit autonomous service missions. Line segment detection is an important step in pose estimation. The traditional line segment detectors show impressive performance under sufficient illumination, while it is easy to fail under complex illumination conditions where the illumination is too bright or too dark. We propose a robust line segment detector for space applications considering the complex illumination in space environments. An improved two-dimensional histogram construction strategy is used to optimize the Otsu method to improve the accuracy of anchor map extraction. To further improve line segment detection’s effect, we introduce an aggregation method that uses the angle difference between segments, the distance between endpoints, and the overlap degree of segments to filter the aggregation candidate segments and connect disjoint line segments that probably came from the same segment. We demonstrate the performance of the proposed line segment detector using a variety of images collected on a semiphysical simulation platform. The results show that our method has better performance than traditional line segment detectors including LSD, Linelet, etc., in terms of line detection precision.
... Then, an open operation is adopted in Fig. 3 (c) to suppress the small dynamic noise points while merging each adjacent independent black region to highlight the distinguishing features. After that, the boundary extraction algorithm is used to obtain edge information of the black regions due to LiDAR just can observe the contours of black areas, and the straight line extraction is performed using Hough Transform Line Detection (HTLD) [35] , shown in Fig. 3 (d) and (e). However, when dealing with imprecise original maps, discontinuous, blurry and short features are present in the feature extraction results. ...
Automatic Guided Vehicles (AGVs) are crucial for improving the operational efficiency of industrial scenes, however the self-localization of AGVs faces severe challenges in a dynamic environment due to a large number of observation noises. To address the above issue, this paper presents a trusted area information based self-localization method to achieve efficient and accurate localization in a highly dynamic scene, where the proportion of dynamic obstacles is close to 50%. First of all, the "coarse-noise filter-fine" self-localization framework is proposed to establish the foundation of accurate and efficient localization. Then, the morphology-based trusted area selection is adopted to efficaciously extract the trusted area, in which the probability of appearing dynamic objects is low. After that, based on dynamic angular resolution filtering considering the trusted area, a robust point cloud generation is designed to generate trusted area information. Trusted area information contains dense reliable point cloud in the statice area and spares observation noise in the dynamic area, thus improving the performance of observation models and scan matching. Finally, the self-developed AGV is adopted to verify the effectiveness of the proposed self-localization system in real and simulated dynamic scenes.
... Then, an open operation is adopted in Fig. 3 (c) to suppress the small dynamic noise points while merging each adjacent independent black region to highlight the distinguishing features. After that, the boundary extraction algorithm is used to obtain edge information of the black regions due to LiDAR just can observe the contours of black areas, and the straight line extraction is performed using Hough Transform Line Detection (HTLD) [35] , shown in Fig. 3 (d) and (e). However, when dealing with imprecise original maps, discontinuous, blurry and short features are present in the feature extraction results. ...
Automatic Guided Vehicles (AGVs) are crucial for improving the operational efficiency of industrial scenes, however the self-localization of AGVs faces severe challenges in a dynamic environment due to a large number of observation noises. To address the above issue, this paper presents a trusted area information based self-localization method to achieve efficient and accurate localization in a highly dynamic scene, where the proportion of dynamic obstacles is close to 50%. First of all, the “coarse-noise filter-fine” self-localization framework is proposed to establish the foundation of accurate and efficient localization. Then, the morphology-based trusted area selection is adopted to efficaciously extract the trusted area, in which the probability of appearing dynamic objects is low. After that, based on dynamic angular resolution filtering considering the trusted area, a robust point cloud generation is designed to generate trusted area information. Trusted area information contains dense reliable point cloud in the statice area and spares observation noise in the dynamic area, thus improving the performance of observation models and scan matching. Finally, the self-developed AGV is adopted to verify the effectiveness of the proposed self-localization system in real and simulated dynamic scenes.
... Various segmentation methodologies have been proposed to extract these quality parameters and keep visual differences based on textural heterogeneity [15,[35][36][37] and the morphological structure [10,20,27] of each cytological component (nuclei, cytoplasm, extracellular component, RBC, and background). These morphological and textural parameters are extracted with various segmentation approaches, e.g., thresholding technique [16], Otsu thresholding [10,28], Otsu thresholding followed by LDA [27], thresholding followed by k-means [17,20,24,25], k-means with graph cut method [30], textural parameter followed by PCA and k-means [18], L2E along with canny edge and Hough transformation [19,[38][39][40][41], gaussian mixer model and expectation maximization [9], mean shift elimination [21], contour models [21,23,[42][43][44][45][46][47][48][49], color-coded map based [29], watershed [37,50], piecewise [51] entropy-based histogram [31], level-set [52], and transfer learning approaches for feature extraction [32][33][34] have been introduced to segment histopathological images. Many works have been performed in image segmentation, available in survey resources. ...
This paper proposes a noble image segment technique to differentiate between large malignant cells called centroblasts vs. centrocytes. A new approach is introduced, which will provide additional input to an oncologist to ease the prognosis. Firstly, a H&E-stained image is projected onto L*a*b* color space to quantify the visual differences. Secondly, this transformed image is segmented with the help of k-means clustering into its three cytological components (i.e., nuclei, cytoplasm, and extracellular), followed by pre-processing techniques in the third step, where adaptive thresholding and the area filling function are applied to give them proper shape for further analysis. Finally, the demarcation process is applied to pre-processed nuclei based on the local fitting criterion function for image intensity in the neighborhood of each point. Integration of these local neighborhood centers leads us to define the global criterion of image segmentation. Unlike active contour models, this technique is independent of initialization. This paper achieved 92% sensitivity and 88.9% specificity in comparing manual vs. automated segmentation.
... However, the hardware resources applicable to the aerospace level are very limited, and at the same time, the requirements for target positioning accuracy and positioning real-time are very high, which increases the demand for designing a fast and accurate space cooperative target recognition and pose measurement algorithm at the software level [7]. In addition, in the field of spatial vision, many unfavorable factors, such as complex image background, poor lighting environment, target motion blur, and image occlusion, affect the scope of application, positioning accuracy, and rapidity of target recognition algorithms [8][9]. Therefore, designing a space-cooperative target recognition and pose 2 measurement algorithm with fast recognition speed and high pose measurement accuracy is a key research direction of spatial vision systems. ...
Visual guidance based on cooperative target is one of the most commonly used approaches in the field of space in-orbit service, such as spacecraft rendezvous and docking and satellite maintenance. Considering the limited space hardware resources, it is necessary to design an embedded image processing algorithm to meet the special needs of space recognition, such as small memory consumption and fast recognition speed. Therefore, aiming at the classic three-point cooperative target, recognition, and pose estimation algorithm is designed in this paper based on mono-vision. In this method, a fast inflection point detection method is designed, and the contour is divided into several edges with a single feature, which improves the accuracy of circle recognition. Finally, the relative pose of the target coordinate system can be obtained quickly and accurately by P3P. The algorithm has low complexity and can realize fast recognition with small memory, even with limited space-grade hardware resources. The effectiveness of the proposed method is verified by experiments.
... It reduced noises (i.e., small particles out of areas of interest), found intensity gradient of images (i.e., outer edges of shanks), and removed unnecessary pixels (i.e., litter pixels and skin pixels) on the neighborhood of gradient directions. The Hough transform is a popular tool for line detection due to its robustness to noise and missing data and was selected to detect shank edge orientation (Fernandes and Oliveira, 2008). The shank edge orientation represented the shank orientation with respect to the gripper or camera position. ...
Highlights
A broiler mortality removal robot was successfully developed.
The broiler shank was the target anatomical part for detection and mortality pickup.
Higher light intensities improved the performance of detection and pickup performance.
The final success rate for picking up dead birds was 90.0% at the 1000-lux light intensity.
Abstract. Manual collection of broiler mortality is time-consuming, unpleasant, and laborious. The objectives of this research were: (1) to design and fabricate a broiler mortality removal robot from commercially available components to automatically collect dead birds; (2) to compare and evaluate deep learning models and image processing algorithms for detecting and locating dead birds; and (3) to examine detection and mortality pickup performance of the robot under different light intensities. The robot consisted of a two-finger gripper, a robot arm, a camera mounted on the robot’s arm, and a computer controller. The robot arm was mounted on a table, and 64 Ross 708 broilers between 7 and 14 days of age were used for the robot development and evaluation. The broiler shank was the target anatomical part for detection and mortality pickup. Deep learning models and image processing algorithms were embedded into the vision system and provided location and orientation of the shank of interest, so that the gripper could approach and position itself for precise pickup. Light intensities of 10, 20, 30, 40, 50, 60, 70, and 1000 lux were evaluated. Results indicated that the deep learning model “You Only Look Once (YOLO)” V4 was able to detect and locate shanks more accurately and efficiently than YOLO V3. Higher light intensities improved the performance of the deep learning model detection, image processing orientation identification, and final pickup performance. The final success rate for picking up dead birds was 90.0% at the 1000-lux light intensity. In conclusion, the developed system is a helpful tool towards automating broiler mortality removal from commercial housing, and contributes to further development of an integrated autonomous set of solutions to improve production and resource use efficiency in commercial broiler production, as well as to improve well-being of workers. Keywords: Automation, Broiler, Deep learning, Image processing, Mortality, Robot arm.
... intersection of lines could lie in in the coordinate. Since the emergence of HT, many scholars (Sklansky 1978, Brown 1983 proposed improved algorithms to detect lines and circular arcs in a binary image and there is still a wealth of literatures about the Hough transform in recent years (Chandan et al. 2008, Fernandes et al. 2008. However, all these HTs have the limitation that they can only detect parametric curves. ...
Curve extraction is an important and basic technique in image processing and computer vision. Due to the complexity of the images and the limitation of segmentation algorithms, there are always a large number of noisy pixels in the segmented binary images. In this paper, we present an approach based on ant colony system (ACS) to detect nonparametric curves from a binary image containing discontinuous curves and noisy points. Compared with the well-known Hough transform (HT) method, the ACS-based curve extraction approach can deal with both regular and irregular curves without knowing their shapes in advance. The proposed approach has many characteristics such as faster convergence, implicit parallelism and strong ability to deal with highly-noised images. Moreover, our approach can extract multiple curves from an image, which is impossible for the previous genetic algorithm based approach. Experimental results show that the proposed ACS-based approach is effective and efficient.
... Namun, pendeteksian berbasis LiDAR tergolong mahal dan tidak aplikatif pada kapal tak berawak berukuran kecil akibat ukuran sensor yang besar. Sehingga dalam rangka mengatasi keterbatasan performa komputasi sistem tertanam Raspberry Pi 4 yang digunakan pada kapal, maka dirancang sebuah sistem pendeteksian rintangan berbasis pengolahan citra yang mengkombinasikan deteksi tepi Canny [11], transformasi Hough [12], dan deteksi saliensi [13]. Gambar ...
Kapal tanpa awak yang digunakan untuk berpatroli di perairan pesisir membutuhkan sistem deteksi dan penghindar rintangan yang andal. Hal ini dikarenakan banyak terdapat objek-objek yang dapat menghalangi lajunya kapal di permukaan air. Tantangan dalam pengembangan sistem pendeteksian rintangan berbasis citra bagi kapal tak berawak ukuran kecil adalah performa komputasi yang terbatas. Penelitian dilakukan untuk membuat sebuah sistem pendeteksian rintangan bagi kapal tanpa awak yang akurat dengan proses komputasi yang minimum agar dapat diimplementasikan ke dalam sistem tertanam. Sistem yang dibuat mengkombinasikan deteksi tepi, transformasi Hough dan deteksi saliensi untuk mendeteksi adanya rintangan di atas permukaan air. Dari hasil pengujian didapatkan bahwa performa sistem dapat mendekati kemampuan sistem lain yang lebih kompleks namun belum dapat mengunggulinya. Sistem ini juga diimplementasikan pada sistem tertanam dan menghasilkan kecepatan yang memungkinkan untuk dilakukan pengimplementasian secara real-time.
... Among the applications of geometrical feature extraction, the classical method for the extraction of boundaries in a 2D matrix is canny edge detection [31]. Another popular approach is estimating the boundaries based on Hough transformation for the line geometry detection [32][33][34]. The popular approach for corner detection is the Harris Corner detector [35]. ...
Robot-aided cleaning auditing is pioneering research that uses autonomous robots to assess a region’s cleanliness level by analyzing the dirt samples collected from various locations. Since the dirt sample gathering process is more challenging, adapting a coverage planning strategy from a similar domain for cleaning is non-viable. Alternatively, a path planning approach to gathering dirt samples selectively at locations with a high likelihood of dirt accumulation is more feasible. This work presents a first-of-its-kind dirt sample gathering strategy for the cleaning auditing robots by combining the geometrical feature extraction and swarm algorithms. This combined approach generates an efficient optimal path covering all the identified dirt locations for efficient cleaning auditing. Besides being the foundational effort for cleaning audit, a path planning approach considering the geometric signatures that contribute to the dirt accumulation of a region has not been device so far. The proposed approach is validated systematically through experiment trials. The geometrical feature extraction-based dirt location identification method successfully identified dirt accumulated locations in our post-cleaning analysis as part of the experiment trials. The path generation strategies are validated in a real-world environment using an in-house developed cleaning auditing robot BELUGA. From the experiments conducted, the ant colony optimization algorithm generated the best cleaning auditing path with less travel distance, exploration time, and energy usage.
... As one of the most important features for human perception, 3D line segment structures are widely used and play an important role in many areas, such as building outline extraction [1], building model reconstruction [2,3], road extraction [4], registration [5], localization [6], calibration [7], and more. Over the past few decades, detecting line segments from 2D images has been well-studied [8][9][10][11][12], while the works on 3D line segment extraction are still insufficient. Moreover, unlike 2D images whose pixels are closely related to their neighboring pixels, unorganized point clouds lack connectivity information. ...
As one of the most common features, 3D line segments provide visual information in scene surfaces and play an important role in many applications. However, due to the huge, unstructured, and non-uniform characteristics of building point clouds, 3D line segment extraction is a complicated task. This paper presents a novel method for extraction of 3D line segment features from an unorganized building point cloud. Given the input point cloud, three steps were performed to extract 3D line segment features. Firstly, we performed data pre-processing, including subsampling, filtering and projection. Secondly, a projection-based method was proposed to divide the input point cloud into vertical and horizontal planes. Finally, for each 3D plane, all points belonging to it were projected onto the fitting plane, and the α-shape algorithm was exploited to extract the boundary points of each plane. The 3D line segment structures were extracted from the boundary points, followed by a 3D line segment merging procedure. Corresponding experiments demonstrate that the proposed method works well in both high-quality TLS and low-quality RGB-D point clouds. Moreover, the robustness in the presence of a high degree of noise is also demonstrated. A comparison with state-of-the-art techniques demonstrates that our method is considerably faster and scales significantly better than previous ones. To further verify the effectiveness of the line segments extracted by the proposed method, we also present a line-based registration framework, which employs the extracted 2D-projected line segments for coarse registration of building point clouds.
The composition of an image is a critical element chosen by the author to construct an image that conveys a narrative and related emotions. Other key elements include framing, lighting, and colors. Assessing classical and simple composition rules in an image, such as the well-known “rule of thirds”, has proven effective in evaluating the aesthetic quality of an image. It is widely acknowledged that composition is emphasized by the presence of leading lines. While these leading lines may not be explicitly visible in the image, they connect key points within the image and can also serve as boundaries between different areas of the image. For instance, the boundary between the sky and the ground can be considered a leading line in the image. Making the image’s composition explicit through a set of leading lines is valuable when analyzing an image or assisting in photography. To the best of our knowledge, no computational method has been proposed to trace image leading lines. We conducted user studies to assess the agreement among image experts when requesting them to draw leading lines on images. According to these studies, which demonstrate that experts concur in identifying leading lines, this paper introduces a fully automatic computational method for recovering the leading lines that underlie the image’s composition. Our method consists of two steps: firstly, based on feature detection, potential weighted leading lines are established; secondly, these weighted leading lines are grouped to generate the leading lines of the image. We evaluate our method through both subjective and objective studies, and we propose an objective metric to compare two sets of leading lines.
Semantic lines are some particular dominant lines in an image, which divide the image into several semantic regions and outline its conceptual structure. They play a vital role in image analysis, scene understanding, and other downstream tasks due to their semantic representation ability for the image layout. However, the accuracy and efficiency of existing semantic line detection methods still couldn’t meet the need of real applications. So, a new semantic line detection method based on the deep Hough transform network with attention mechanism and strip convolution is proposed. Firstly, the detection performance is improved by combining the channel attention mechanism with the feature pyramid network to alleviate the influence of redundant information. Then, the strip convolution and mixed pooling layer are introduced to effectively collect the remote information and capture the long-range dependencies between pixel backgrounds. Finally, the strategy of GhostNet is adopted to reduce the computational cost. Results of experiments on open datasets validate the proposed method, which is comparable to and even outperforms the state-of-the-art methods in accuracy and efficiency. Our code and pretrained models are available at: https://github.com/zhizhz/sml.
NOvA utilizes multiple algorithms and techniques to make sense of the blips of light seen in the detectors. First, low-level reconstruction is performed where nearby hits in time and space are grouped together as they are likely to have come from the same source. Next, we begin to resolve individual particles, and apply machine learning techniques to determine their specific types. Finally, in order to perform our physics analyses, we must estimate the energies associated with each particle and interaction.
The neutral line, a crucial feature found in sky light polarization pattern images, plays a crucial role in bio-inspired polarization navigation. However, current methods for detecting the neutral line typically assume clear and unobstructed conditions. Unfortunately, the sky polarization pattern (SPP) is susceptible to various weather conditions and geographic environments, leading to distorted patterns caused by random occlusions. Consequently, accurately determining the orientation information of the neutral line becomes challenging. To address this issue, we conduct an in-depth analysis of the distribution characteristics of the neutral line in the SPP using both simulation and real measurement experiments. In addition, we curate a comprehensive dataset known as the SPP dataset. Leveraging an adversarial learning-based approach, we propose a novel method for reconstructing SPP images. Subsequently, we perform neutral line detection on the reconstructed SPPs. Notably, our method showcases exceptional performance in detecting neutral lines, even in the presence of up to 80% occlusions within the area of interest. Experimental evaluations, conducted on both simulated and measured SPPs, validate the effectiveness and robustness of our proposed method. Furthermore, quantitative analyses of the experimental results confirm the stability and reliability of our approach. Our work makes a valuable contribution to the field of SPP reconstruction and neutral line detection under complex conditions. Moreover, it holds significant potential for advancing the measurement and application of polarization techniques. Data and models are available at:
https://github.com/WNCI
.
The chapter describes a brief history of the emergence of the theory of cellular automata, their main properties, and methods for constructing. The image skeletonization methods based on the Euler zero differential are described. The advantages of using hexagonal coverage for detecting moving objects in the image are shown. The software and hardware implementation of the developed methods are presented. Based on the obtained results, a hexagonal-coated cellular automata was developed to identify images of objects based on the Radon transform. The method and mathematical model of the selection of characteristic features for the selection of the skeleton and implementation on cellular automata with a hexagonal coating are described. The Radon transform allowed to effectively extract the characteristic features of images with a large percentage of noise. An experiment for different images with different noises was conducted. Experimental analysis showed the advantages of the proposed methods of image processing and extraction of characteristic features.
The purpose of this work is to improve the accuracy of critical infrastructure condition assessment using mobile robots by considering the geometric distortions of the current images during the formation of a set of reference images. The goal is achieved by determining the sampling step values by angles and sighting height without loss of accuracy. The most important result is the determination of acceptable discretization values in the range of angles and heights of a correlation-extreme navigation system. The significance of the obtained results is in solving the problem of forming a set of reference images, which will reduce the impact of changes in the geometry of sighting on the accuracy of the evaluation of objects. A special feature of the results obtained is the establishment of maximum permissible sampling steps in angles and heights of sight to ensure the required accuracy of object state estimation. When forming a set of reference images, the sampling step by height should be (0.06....0.11)% and (0.12....0.2)% relative to the initial flight altitude for the sighting surface with normal and high object saturation, respectively. The angular sampling step is 10...17 degrees and 6...10 degrees, respectively, for the same surface types. The difference from known works is that the perspective and scale distortions are considered at the stage of formation of a set of reference images, which ensures high accuracy of the system functioning in conditions of orientation and sighting geometry changes.
Line features are of great importance for the registration of the Vehicle-Borne Mobile Mapping System that contains both lidar and multiple-lens panoramic cameras. In this work, a spherical straight- line model is proposed to detect the unified line features in the panoramic imaging surface based on the Spherical Hough Transform. The local topological constraints and gradient image voting are also combined to register the line features between panoramic images and lidar point clouds within the Hough parameter space. Experimental results show that the proposed method can accurately extract the long strip targets on the panoramic images and avoid spurious or broken line-segments. Meanwhile, the line matching precision between point clouds and panoramic images are also improved.
A method for welding line detection using point cloud data is proposed to automate welding operations combined with a contact sensor. The proposed system targets a fillet weld, in which the joint line between two metal plates attached vertically is welded. In the proposed method, after detecting the position and orientation of two flat plates regarding a single viewpoint as a rough measurement, the flat plates are measured from the optimal shooting position in each plane in detail to detect a precise weld line. When measuring a flat plate from an angle, the 3D point cloud obtained by a depth camera contains measurement errors. For example, a point cloud measuring a plane has a wavy shape or void owing to light reflection. However, by shooting the plane vertically, the point cloud has fewer errors. Using these characteristics, a two-step measurement algorithm for determining weld lines was proposed. The weld line detection results show an improvement of 5 mm compared with the rough and precise measurements. Furthermore, the average measurement error was less than 2.5 mm, and it is possible to narrow the range of the search object contact sensor for welding automation.
In recent days, automated demarcation of biased nuclei of follicular lymphoma has become a standard framework in the pipeline of quantitative histopathology. It has received substantial consideration due to subjective variability between different oncologists. This difference can occasionally result in erroneous conclusions, distinct prognostic reports, and inconsistent treatment. This paper provides additional input to an oncologist to ease the prognosis process. This approach defines a local criterion fitting function in neighbourhood of each point based on image intensity. An assumption is pixel intensity will remain constant next to the point. Integration of these local neighbourhood centres leads us to define the global criterion of image segmentation. Segmentation accuracy is evaluated using region-based measures and the optimal segmentation accuracy of 98.6% is achieved using the DICE coefficient. By using locally formulated energy, execution time is also reduced in comparison to the contour algorithm. This technique is independent of the initialization.
In this study, we propose a novel CLAHE-based nighttime image contrast enhancement approach for vehicle detection under nighttime conditions, which improves the contrast of low-quality nighttime images while preventing over-enhancement by employing the image dehazing technique. To implement and evaluate our proposed contrast enhancement method on nighttime images, we consider a scenario of using a camera-based Internet of Things (IoT)-edge computing device for traffic and road surveillance. Edge-computing and IoT technology enable significant amounts of novel studies to advance traffic system monitoring, sensing, control, and management. Considering multiple metrics of image enhancement quality, the proposed nighttime image contrast enhancement method outperforms some existing well-performing CLAHE-based methods. To provide accurate vehicle detection under nighttime conditions and different challenges, including vehicle overlapping, low-light conditions, camera vibrations, and image distortion, must be addressed. For this purpose, a deep neural network based on YOLOv5 architecture has been designed and trained using our custom-labeled dataset. The developed neural network is proven to be effective in the detection of different vehicles under low-light ambient conditions using video captured from a stationary camera. Experiments on our dataset show that the proposed contrast enhancement method greatly improves the detection performance of the trained YOLOv5 model under low-environment-light conditions compared with the model trained using unenhanced images. The model trained with enhanced images can provide an improvement of 5.7% on F1 score, 6.3% on mAP
$_{0.5,}$
and 3.4% on mAP
$_{0.5:0.95} $
under specific conditions.
In this paper, we propose a fast Line Segment Detection algorithm for Polarimetric synthetic aperture radar (PolSAR) data (PLSD). We introduce the Constant False Alarm Rate (CFAR) edge detector to obtain the gradient map of the PolSAR image, which tests the equality of the covariance matrix using the test statistic in the complex Wishart distribution. A new filter configuration is applied here to save time. Then, the Statistical Region Merging (SRM) framework is utilized for the generation of line-support regions. As one of our main contributions, we propose a new Statistical Region Merging algorithm based on gradient Strength and Direction (SRMSD). It determines the merging predicate with consideration of both gradient strength and gradient direction. For the merging order, we set it by bucket sort based on the gradient strength. Furthermore, the pixels are restricted to belong to a unique region, making the algorithm linear in time cost. Finally, based on Markov chains and a contrario approach, the false alarm control of line segments is implemented. Moreover, a large scene airport detection method is designed based on the proposed line segment detection algorithm and scattering characteristics. The effectiveness and applicability of the two methods are demonstrated with PolSAR data provided by UAVSAR.
Semantic line detection plays a specific guiding role in aesthetic composition, photography, and so on. This paper introduces the method of semantic line detection and summarizes its present situation. The existing semantic line detection techniques are summarized from the traditional and deep learning-based methods, and the corresponding advantages and disadvantages are pointed out. Based on some difficulties existing in the semantic line detection method, this paper puts forward its own prospects for the future development direction of semantic line detection.KeywordsSemantic line detectionDeep learningComputer vision
The Global Meteor Network (GMN) utilizes highly sensitive low-cost CMOS video cameras which run open-source meteor detection software on Raspberry Pi computers. Currently, over 450 GMN cameras in 30 countries are deployed. The main goal of the network is to provide long-term characterization of the radiants, flux, and size distribution of annual meteor showers and outbursts in the optical meteor mass range. The rapid 24-h publication cycle the orbital data will enhance the public situational awareness of the near-Earth meteoroid environment. The GMN also aims to increase the number of instrumentally observed meteorite falls and the transparency of data reduction methods. A novel astrometry calibration method is presented which allows decoupling of the camera pointing from the distortion, and is used for frequent pointing calibrations through the night. Using wide-field cameras (88° × 48°) with a limiting stellar magnitude of +6.0 ± 0.5 at 25 frames per second, over 220 000 precise meteoroid orbits were collected since 2018 December until 2021 June. The median radiant precision of all computed trajectories is 0.47°, 0.32° for $\sim 20{{\ \rm per\ cent}}$ of meteors which were observed from 4 + stations, a precision sufficient to measure physical dispersions of meteor showers. All non-daytime annual established meteor showers were observed during that time, including five outbursts. An analysis of a meteorite-dropping fireball is presented which showed visible wake, fragmentation details, and several discernible fragments. It had spatial trajectory fit errors of only ∼40 m, which translated into the estimated radiant and velocity errors of 3 arcmin and tens of meters per second.
Aiming to improve the spatial resolution of a neutron imaging system (NIS) for 14 MeV fusion neutrons, an ideal micron resolution capillary detector filled with a high optical index liquid scintillator was simulated. A threshold for each capillary pixel and a threshold for each cluster were applied to suppress the gamma-induced background. In addition, by using a pattern recognition algorithm and an optimized Hough Transformation, the accuracy of determining the neutron positions and the dynamic range of this detector were enhanced. For an ideal capillary array detector, the spatial resolution is expected as one capillary size of 20μm. The dynamic range of ∼1000 is reachable while the accuracy of neutron impinging position determination keeps better than 85%. The ionization quenching, light sharing and energy resolution of the detector were applied to the simulated data to understand the capillary array detector.
The research studied Probability Density Function (pdf), Cumulative Distribution Function (CDF) and graphical analysis of the bivariate central normal distribution. The CDF of this distribution is then used to compute power of the test Pre-Test-Test (PTT) in the testing intercept. The tables and graphs of the pdf (and CDF) of the bivariate central normal distribution (BCND) and power of the test in testing intercept are produced using R-code. The results showed that the mean and coefficient correlation have a significant affect on the curve, but the variance is not. The curves tend to be leptokurtic for small coefficient correlation, and they will be mesocurtic for large coefficient correlation. The power of the PTT increases as the CDF of the BCND increases.
The Hough transform is an established tool for discovering linear features in images. The present investigation presents a new and specific algorithm for detecting geological lineaments in satellite images and scanned aerial photographs which incorporates the Hough transform, a new kind of a "directional detector," and a special counting mechanism for detecting peaks in the Hough plane. Three test sites representing different geological environments and remote sensing altitudes were selected. The first site represents sedimentary conditions of chalk beds on cherry picker photography; the second represents plutonic conditions of granite rocks on an aerial photograph; and the third represents tectonic fractures of carbonates, chalks, and cherts on digital satellite data. In all cases, automatic extraction and mapping of lineaments conformed well to interpretation of lineaments by human performance.
Current approaches to content-based retrieval of multimedia data usually rely either on query by example or on sketches of the desired image, but not on both. In this paper, we propose a new query specification scheme, where digital images are combined with sketches, after vectorization, taking advantage of both methods. We selected a set of algorithms to perform image vectorization, taking into account the trade-off between vector image quality and processing time. This method of specifying queries is part of a system to retrieve vector drawings, which we briefly describe in this paper.
This paper describes a computational approach to edge detection. The success of the approach depends on the definition of a comprehensive set of goals for the computation of edge points. These goals must be precise enough to delimit the desired behavior of the detector while making minimal assumptions about the form of the solution. We define detection and localization criteria for a class of edges, and present mathematical forms for these criteria as functionals on the operator impulse response. A third criterion is then added to ensure that the detector has only one response to a single edge. We use the criteria in numerical optimization to derive detectors for several common image features, including step edges. On specializing the analysis to step edges, we find that there is a natural uncertainty principle between detection and localization performance, which are the two main goals. With this principle we derive a single operator shape which is optimal at any scale. The optimal detector has a simple approximate implementation in which edges are marked at maxima in gradient magnitude of a Gaussian-smoothed image. We extend this simple detector using operators of several widths to cope with different signal-to-noise ratios in the image. We present a general method, called feature synthesis, for the fine-to-coarse integration of information from operators at different scales. Finally we show that step edge detector performance improves considerably as the operator point spread function is extended along the edge.
The Hough transform is a useful technique in the detection of straight lines and curves in an image. Due to the mathematical similarity of the Hough transform and the forward Radon transform, the Hough transform can be computed using the Radon transform which, in turn, can be evaluated using the central slice theorem. This involves a two-dimensional Fourier transform, an x-y to r-θ mapping and a 1D Fourier transform. This can be implemented in specialized hardware to take advantage of the computational savings of the fast Fourier transform. In this paper, we outline a fast and efficient method for the computation of the Hough transform using Fourier methods. The maxima points generated in the Radon space, corresponding to the parametrisation of straight lines, can be enhanced with a post transform convolutional filter. This can be applied as a 1D filtering operation on the resampled data whilst in the Fourier space, so further speeding the computation. Additionally, any edge enhancement or smoothing operations on the input function can be combined into the filter and applied as a net filter function.
The generalized Hough transform constitutes a wellknown approach to object recognition and pose detection. To attain reliable detection results, however, a very large number of candidate object poses and scale factors need to be considered. We employ an inexpensive, consumer-market graphics-card as the "poor man's" parallel processing system. We describe the implementation of a fast and enhanced version of the generalized Hough transform on graphics hardware. Thanks to the high bandwidth of on-board texture memory, a single pose can be evaluated in less than 3 ms, independent of the number of edge pixels in the image. From known object geometry, our hardware-accelerated generalized Hough transform algorithm is capable of detecting an object's 3D pose, scale, and position in the image within less than one minute. A good pose estimation is even delivered in less than 10 seconds.
The Hough transform is recognized as being a powerful tool in shape analysis which gives good results even in the presence of noise and occlusion. Major shortcomings of the technique are excessive storage requirements and computational complexity. Solutions to these problems form the bulk of contributions to the literature concerning the Hough transform. An excellent comprehensive review of available methods up to and partially including 1988 is given by Illingworth and Kittler (Comput. Vision Graphics Image Process. 44, 1988, 87-116). In the years following this survey much new literature has been published. The present work offers an update on state of the art Hough techniques. This includes comparative studies of existing techniques, new perspectives on the theory, very many novel algorithms, parallel implementations, and additions to the task-specific hardware. Care is taken to distinguish between research that aims to further basic understanding of the technique without necessarily being computationally realistic and research that may be applicable in an industrial context. A new trend in Hough transform work, that of the probabilistic Houghs, is identified and reviewed in some detail. Attempts to link the low level perceptive processing offered by the Hough transform to high level knowledge driven processing are also included, together with the many recent successful applications appearing in the literature.
This paper presents a modified Hough transform (HT) by formulating the conjugate pair for line detection. By considering conjugate pair of the HT, a fast computing algorithm can be derived. The concept of conjugation is applied to the Radon transform, a generalized HT, and the Gabor transforms. Formulation of the conjugate pairs of 3D Hough transform is also presented.
This patent relates to a method and means for recognizing a complex
pattern in a picture. The picture is divided into framelets, each framelet being
sized so that any segment of the complex pattern therewithin is essentially a
straight line. Each framelet is scanned to produce an electrical pulse for each
point scanned on the segment therewithin. Each of the electrical pulses of each
segment is then transformed into a separate strnight line to form a plane
transform in a pictorial display. Each line in the plane transform of a segment
is positioned laterally so that a point on the line midway between the top and
the bottom of the pictorial display occurs at a distance from the left edge of
the pictorial display equal to the distance of the generating point in the
segment from the left edge of the framelet. Each line in the plane transform of
a segment is inclined in the pictorial display at an angle to the vertical whose
tangent is proportional to the vertical displacement of the generating point in
the segment from the center of the framelet. The coordinate position of the
point of intersection of the lines in the pictorial display for each segment is
determined and recorded. The sum total of said recorded coordinate positions
being representative of the complex pattern. (AEC)
In this article a new method for the calibration of a vision system which consists of two (or more) cameras is presented. The proposed method, which uses simple properties of vanishing points, is divided into two steps. In the first step, the intrinsic parameters of each camera, that is, the focal length and the location of the intersection between the optical axis and the image plane, are recovered from a single image of a cube. In the second step, the extrinsic parameters of a pair of cameras, that is, the rotation matrix and the translation vector which describe the rigid motion between the coordinate systems fixed in the two cameras are estimated from an image stereo pair of a suitable planar pattern. Firstly, by matching the corresponding vanishing points in the two images the rotation matrix can be computed, then the translation vector is estimated by means of a simple triangulation. The robustness of the method against noise is discussed, and the conditions for optimal estimation of the rotation matrix are derived. Extensive experimentation shows that the precision that can be achieved with the proposed method is sufficient to efficiently perform machine vision tasks that require camera calibration, like depth from stereo and motion from image sequence.
We present a comprehensive review of the Hough transform, HT, in image processing and computer vision. It has long been recognized as a technique of almost unique promise for shape and motion analysis in images containing noisy, missing, and extraneous data but its adoption has been slow due to its computational and storage complexity and the lack of a detailed understanding of its properties. However, in recent years much progress has been made in these areas. In this review we discuss ideas for the efficient implementation of the HT and present results on the analytic and empirical performance of various methods. We also report the relationship of Hough methods and other transforms and consider applications in which the HT has been used. It seems likely that the HT will be an increasingly used technique and we hope that this survey will provide a useful guide to quickly acquaint researchers with the main literature in this research area.
This paper reviews the Hough transform hardware implementations, with a specific analysis of the architectures that explicitly address the “real-time” issue. The work presents an introduction for a critical assessment of the notion of “real-time”, especially for what concerns modern multimedia applications. The main contribution of this work is the proposal of a new metric for measuring the performance of Hough transform architectures against a given definition of “real-time”. The basic idea is that there is no single set of constraints that define “real-time” for every application domain, and that even the simplest case of Hough transform for line detection, must be properly characterized within a specific application domain. The architectures are classified and evaluated, after a proper characterization of the Hough transform complexity, in terms of dimensions of parameter space and time complexity.
This letter presents a binary Hough transform (BHT) derived from the conventional Hough transform with slope/ intercept parameterization and a systolic architecture for its efficient implementation using only adders and delay-elements.
An efficient method for finding straight lines in edge maps is described. The algorithm is based on a pyramid structure with each layer in the pyramid splitting the complete image into a number of subimages. At the bottom level of the pyramid short line segments are detected by applying a Hough transform to small subimages. The algorithm proceeds, bottom up, from this low level description by grouping line segments within local neighborhoods into longer lines. Line segments which have local support propagate up the hierarchy and take part in grouping at higher levels. The length of a line determines approximately the level in the pyramid to which it propagates. Hence we obtain a hierarchical description of the line segments in a scene which can be useful in matching. The algorithm has a number of advantages over previously proposed hierarchical methods for the detection of straight lines. It is quite efficient and has a particularly attractive architecture which is suitable for parallel implementation.
The slope-intercept Hough transform (SIHT) is one of the two types of line-detection methods. However, the disadvantage of the SIHT is its low memory utilization, say 50%. Based on the affine transformation, this paper presents a new method to improve the memory utilization of the SIHT from 50% to 100%. According to the proposed affine transformation, we first present a basic SIHT-based algorithm for detecting lines. Instead of concerning floating-point operations in the basic SIHT-based algorithm, an improved SIHT-based algorithm, which mainly concerns integer operations, is presented. Besides the memory utilization advantage, experimental results reveal that the improved SIHT-based algorithm has more than 60% execution time improvement ratio when compared to the basic SIHT-based algorithm and has more than 33% execution time improvement ratio when compared to another type of line-detection methods, such as the (r,θ)-based HT algorithm and its variant. The detailed complexity analyses for all the related algorithms are also investigated and we show that the time complexity required in the improved SIHT-based algorithm is the least.
A computer vision system has been implemented that can recognize three-dimensional objects from unknown viewpoints in single gray-scale images. Unlike most other approaches, the recognition is accomplished without any attempt to reconstruct depth information bottom-up from the visual input. Instead, three other mechanisms are used that can bridge the gap between the two-dimensional image and knowledge of three-dimensional objects. First, a process of perceptual organization is used to form groupings and structures in the image that are likely to be invariant over a wide range of viewpoints. Second, a probabilistic ranking method is used to reduce the size of the search space during model-based matching. Finally, a process of spatial correspondence brings the projections of three-dimensional models into direct correspondence with the image by solving for unknown viewpoint and model parameters. A high level of robustness in the presence of occlusion and missing data can be achieved through full application of a viewpoint consistency constraint. It is argued that similar mechanisms and constraints form the basis for recognition in human vision.
The Hough transform is a method for detecting curves by exploiting the duality between points on a curve and parameters of that curve. The initial work showed how to detect both analytic curves(1,2) and non-analytic curves,(3) but these methods were restricted to binary edge images. This work was generalized to the detection of some analytic curves in grey level images, specifically lines,(4) circles(5) and parabolas.(6) The line detection case is the best known of these and has been ingeniously exploited in several applications.(7,8,9)We show how the boundaries of an arbitrary non-analytic shape can be used to construct a mapping between image space and Hough transform space. Such a mapping can be exploited to detect instances of that particular shape in an image. Furthermore, variations in the shape such as rotations, scale changes or figure ground reversals correspond to straightforward transformations of this mapping. However, the most remarkable property is that such mappings can be composed to build mappings for complex shapes from the mappings of simpler component shapes. This makes the generalized Hough transform a kind of universal transform which can be used to find arbitrarily complex shapes.
In this paper a new method for extracting vanishing points from real images is proposed. This method exhibits a linear computational complexity and has good precision. The linear computational complexity is due to the introduction of polar space, which permits the selection of segments converging on the same vanishing point before the computation of the vanishing point itself. Extensive experimentation on real images shows that vanishing points can be identified and located even in cluttered images, and that the proposed algorithm is suitable for recovering the heading direction of a robot moving in corridors and offices.
A new algorithm is presented whereby the Radon transform may be computed in a time commensurate with real-time computer vision applications. The computation and storage requirments are optimized using the four-fold symmetry of the image plane and the properties of the transform. A hybrid technique of multi-tasking and asynchronous parallel processing is proposed and a suitable architecture is suggested.
Hough has proposed an interesting and computationally efficient procedure for detecting lines in pictures. This paper points out that the use of angle-radius rather than slope-intercept parameters simplifies the computation further. It also shows how the method can be used for more general curve fitting, and gives alternative interpretations that explain the source of its efficiency.
An artificial retina camera (ARC) is employed for real-time preprocessing of images. And the algorithm of Hough transform is advanced for detecting the biology-images with approximate circle edge-information in the two-dimension space. This method also works in parallel for processing multiple input and partial input patterns.
This paper discusses high-speed array implementations of two image
processing algorithms, namely the `Hough transform for detection of line
segments', and `backprojection in CT image reconstruction'. A
multi-chip-module (MCM) construction is proposed consisting of three
types of chips, a high speed multi-function nonlinear chip, a flexible
multiply-accumulate chip, and an image kernel chip. Called V-array, it
can be configured to have eight Hough modules, so as to produce the
Hough transform of a 1024×1024 image in an estimated 13 ms in 2.0
micron CMOS technology (6.6 ms in 1.0 micron CMOS technology).
Similarly, a V-array MCM can accommodate eight CT modules, which can
produce the backprojected image in 209 ms in 2.0 micron CMOS technology
(105 ms in 1.0 micron CMOS technology). To gain a significant speed
advantage, we have developed an advanced multi-function cell for
performing any one of four nonlinear operations: square-root,
reciprocal, sine/cosine, and arctangent-all realized in a single chip,
accessible on a selectable basis. A 16 bit four-function “one
cycle” VLSI chip, fabricated in 2.0 micron CMOS technology, is
presently available which outputs a new result every clock cycle. Using
this nonlinear cell and two other cells, an application level Hough
transform module and a CT module are presented
Real-time segmentation and tracking of biopsy needles is a very important part of image-guided surgery. Since the needle appears as a straight line in medical images, the Hough transform for straight-line detection is a natural and powerful choice for needle segmentation. However, the transform is computationally expensive and in the standard form is ineffective for real-time segmentation applications. This paper proposes a dedicated hardware architecture for the Hough transform based on distributed arithmetic (DA) principles that results in a real-time implementation. The architecture exploits the inherent parallelism of the Hough transform and reduces the overall computation time. The DA Hough transform architecture has been implemented using the Xilinx field-programmable gate array (FPGA). For a 256x256-bit image, the proposed design takes between 0.1 ms and 1.2 ms to process the Hough transform when the feature points in the image are varied from 2% to 50% of the total image; these values are well within the bounds of real-time operation and thus can facilitate needle segmentation in real time.
A hierarchical line and segment extraction algorithm, based on a
pyramid, is described. Initially, lines are detected in small windows
using the Hough transform. The detected lines are then merged using a
distance criteria thus avoiding a reaccumulation process at each level
of the pyramid. The hierarchical merging process is efficiently
performed on lines rather than on segments (since there are many more
segments than lines). The detected lines are broken into segments, at
the top of the pyramid. The proposed approach is compared to similar
approaches based on hierarchical feature extraction. The authors show
that their approach combines the advantages of other works and avoids
their drawbacks such as quantisation effect and lack of robustness
Vista is a software environment supporting the modular implementation and execution of computer vision algorithms. Because it is extensible, portable, and freely available, Vista is an appropriate medium for the exchange of standard implementations of algorithms. This paper, an overview of Vista, describes its file format, its data abstraction, its conventions for UNIX filter programs and library routines, and its user interface toolkit. Unlike systems that are designed principally to support image processing, Vista provides for the easy creation and use of arbitrary data types, such as are needed for many areas of computer vision research. 1 Introduction As a science concerned with creating artificial systems, computer vision ought to emphasize the evaluation and comparison of alternative methods [1] [2]. It should be simple to compose large systems from components created by other researchers. That this is seldom done is partly due to the lack of a suitable, common software environ...
We present a new approach for modeling and rendering existing architectural scenes from a sparse set of still photographs. Our modeling approach, which combines both geometry-based and imagebased techniques, has two components. The first component is a photogrammetricmodeling methodwhich facilitates the recovery of the basic geometry of the photographed scene. Our photogrammetric modeling approach is effective, convenient, and robust because it exploits the constraints that are characteristic of architectural scenes. The second component is a model-based stereo algorithm, which recovers how the real scene deviates from the basic model. By making use of the model, our stereo technique robustly recovers accurate depth from widely-spaced image pairs. Consequently, our approach can model large architectural environments with far fewer photographs than current image-based modeling approaches. For producing renderings, we present view-dependent texture mapping, a method of compositing multiple views of a scene that better simulates geometric detail on basic models. Our approach can be used to recover models for use in either geometry-based or image-based rendering systems. We present results that demonstrate our approach 's ability to create realistic renderings of architectural scenes from viewpoints far from the original photographs. CR Descriptors: I.2.10 [Artificial Intelligence]: Vision and Scene Understanding - Modeling and recovery of physical attributes; I.3.7 [Computer Graphics]: Three-Dimensional Graphics and Realism - Color, shading, shadowing, and texture I.4.8 [Im- age Processing]: Scene Analysis - Stereo; J.6 [Computer-Aided Engineering]: Computer-aided design (CAD). 1