Radim Sara

Czech Technical University in Prague | ČVUT · Department of Cybernetics and Robotics

Cameras are the prevalent sensors used for perception in autonomous robotic systems, but initial calibration may degrade over time due to dynamic factors. This may lead to the failure of the downstream tasks, such as simultaneous localization and mapping (SLAM) or object recognition. Hence, a computationally light process that detects the decalibra...

Matched filter is an exceedingly popular method in many fields. In optical astronomy, the common application includes matching streak templates of various lengths and orientations (shape hypothesis). We present a matched filter modification suitable for shorter streaks (less than ca. 100 px) that is faster than current state-of-the-art approaches....

Matched filter is an exceedingly popular method in many fields. In optical astronomy, the common application includes matching streak templates of various lengths and orientations (shape hypothesis). We present a matched filter modification suitable for shorter streaks (less than ca. 100 px) that is faster than current state-of-the-art approaches....

Abstract. Fast-moving celestial objects, like near-Earth objects (NEOs), orbiting space debris, or meteors, appear as streaks superimposed over the star background in images taken by an optical telescope at long exposures. As the apparent magnitude of the object increases (the object becomes fainter), its detection becomes progressively harder. We...

In this paper, we present a novel method for online LiDAR-Camera system calibration tracking and refinement. The method is correspondence-free, formulated as a maximum-likelihood learning task. It is based on a consistency of projected LiDAR point cloud corners and optical image edges. The likelihood function is robustified using a model in which t...

It is known that detecting straight streaks from fast moving celestial objects in optical images is an easy problem as long as the streaks are sufficiently long and/or their signal-to-background (SBR) is sufficiently high. At low SBR the situation is different. Since the SBR can be arbitrarily small in practice, a good detection procedure has to pr...

This paper describes statistical models and an efficient Monte-Carlo algorithm for detecting tracks of slowly moving objects in optical telescope imagery sequences. The algorithm is based on accurate robust image pre-registration with respect to the star background, hot/warm pixel suppression, extracting dense normalized local image features, pixel...

We propose a method for semantic parsing of images with regular structure. The structured objects are modeled in a densely connected CRF. The paper describes how to embody specific spatial relations in a representation called Spatial Pattern Templates (SPT), which allows us to capture regularity constraints of alignment and equal spacing in pairwis...

Certain classification tasks in computer vision require the classifier response to be computed in every pixel of an image. When combined with large, complex features, it becomes challenging to build such a classifier on a standard PC architecture and achieve real-time performance. We present an FPGA implementation of a car wheel classifier response...

Current collision mitigation systems focus on rear end collisions. To address the full spectrum of real world accidents, these systems will have to be enhanced to cover more traffic situations. Vehicle to vehicle accidents in crossing traffic situations make up around 25% of accidents in Germany. This paper discusses the requirements and difference...

We present a method for recognition of structured images and demonstrate it on the detection of windows in facade images. Given an ability to obtain local low-level data evidence on primitive elements of a structure (like window in a facade image), we determine their most probable number, attribute values (location, size) and neighborhood relation....

We present a method for calculation of disparity maps from stereo sequences. Disparity map from previous frame is first transferred to the new frame using estimated motion of the calibrated stereo rig. The predicted disparities are validated for the new frame and areas where prediction failed are matched with a traditional stereo matching algorithm...

We propose a method for stochastic parsing of images with regular structures exhibiting symmetries, such as facades of buildings. The translational symmetry is represented by an array of elements (windows) that is generated with a stochastic grammar which allows structural exceptions and spatial deviations for individual elements. The reflection sy...

We propose a novel method for recognition of structured images and demonstrate it on detection of windows in facade images. Given an ability to obtain local low-level data evidence on primitive elements of a structure (like window in a facade image), we determine their most probable number, attribute values (location, size) and neighborhood relatio...

In this paper we propose a pipeline for accurate 3D reconstruction from multiple images that deals with some of the possible sources of inaccuracy present in the input data. Namely, we address the problem of inaccurate camera calibration by including a method adjusting the camera parameters in a global structure-and-motion problem, which is solved...

This paper describes a simple but non-trivial semidense stereoscopic matching algorithm that could be taught in Computer Vision courses. The description is meant to be instructive and accessible to the student. The level of detail is sufficient for a student to understand all aspects of the algorithm design and to make his/her own modifications. Th...

We propose a novel method for recognition of structured images and demonstrate it on detection of windows in facade images. Given an ability to obtain local low-level data evidence on primitive elements of a structure (like window in a facade image), we determine their most probable number, attribute values (location, size) and neighborhood relatio...

We use a MRF with asymmetric pairwise compatibility constraints between direct pixel neighbors to solve a constrained binary image segmentation task. The model is constraining shape and alignment of individual contiguous binary segments by introducing auxiliary labels and their pairwise interactions. Such representation is not necessarily unique. W...

This paper presents the initial results of the algorithm performance contest that was organized as part of the 5th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS 2008). The focus of the 2008 contest was automatic building detection and digital surface model (DSM) extraction. A QuickBird data set with manual ground truth was used for b...

We present a novel algorithm for image-based surface reconstruction from a set of calibrated images. The problem is formulated in Bayesian framework, where esti-mates of depth and visibility in a set of selected cameras are iteratively improved. The core of the algorithm is the min-imisation of overall geometric L 2 error between measured 3D points...

Ultrasonography is a cheap and quick non-invasive medical imaging technique, used as a diagnostic method for autoimmune thyroiditis. Another important diagnostic method for this chronic inflammation is measuring the increased level of thyroid antibodies (anti-thyroid peroxidase (TPOAb) and/or anti-thyroglobulin (TgAb)) in blood samples. This paper...

In this paper, we propose a new algorithm for fairing discrete surfaces resulting from stereo-based D reconstruction task. Such results are typically too dense, uneven and noisy, which is inconvenient for further processing. Our approach jointly optimises mesh smoothness and regularity. The definition is given on a discrete surface and the solution...

Segmentation of windowpanes in images of building façades is formulated as a task of maximum aposteriori probability labeling. As-suming orthographic rectification of the image, the windowpanes are al-ways axis-parallel rectangles of relatively low variability in appearance. Every image pixel has one of 10 possible labels, and the labels in adjacen...

Helmholtz stereopsis is a relatively recent reconstruction technique which is able to reconstruct scenes with arbitrary and unknown surface reflectance properties. Conventional implementations of the method estimate surface normal direction at each surface point via an eigenanalysis, thereby optimising an algebraic distance. We develop a more physi...

We pose robust matching with parametric and non-parametric constraints as the problem of finding a stable independent set (SIS) in an oriented graph whose vertices are all possible correspondences, whose edges capture the structure of the constraints and whose edge orientation represents pairwise comparison 'is better' based on correspondence quali...

Computer Vision is a discipline whose ultimate goal is to interpret optical images of real scenes. It is well understood that such a problem is cursed by ambiguity of interpretation and uncertainty of evidence. Despite imperfectness of results due to the scenes never following our prior models exactly, Computer Vision has achieved a significant pro...

We propose a coarse registration method of range images using both geometric and photometric features. The framework of existing methods using multiple features first defines a single similarity distance summing up each feature based evaluations, and then minimizes the distance between range images for registration. In contrast, we formulate regist...

In stereo literature, there is no standard method for evaluating algorithms for semi-dense stereo matching. Moreover, existing evaluations for dense methods require a fixed parameter setting for the tested algorithms. In this paper, we propose a method that overcomes these drawbacks and still is able to compare algorithms based on a simple numerica...

Abstract A simple stereo matching,algorithm is proposed,that visits only a small fraction of disparity space in order to find a semi-dense disparity map. It works by growing from a small set of correspondence,seeds. Unlike in known,seedgrowing algorithms, it guarantees matching accuracy and correctness, even in the presence of repetitive patterns....

We present an automatic pipeline for recovering the geometry of a 3D scene from a set of unordered, uncalibrated images. The contributions in the paper are the presentation of the system as a whole, from images to geometry, the estimation of the local scale for various scene components in the orientation-topology module, the procedure for orienting...

In this paper we introduce constraint satisfaction framework suitable for the task of finding correspondences in computer vision. This task lies in the heart of many problems like stereovision, 3D model reconstruction, image stitching, camera autocalibration, recognition and image retrieval and a host of others. If the problem domain is general eno...

In this paper we propose the first version of FAIR, a low-dimensional image neighborhood descriptor that shows performance comparable to SIFT introduced by Lowe. The dimension of FAIR we tested is 30, compared to the dimension of 128 in SIFT. Sensitivity of the FAIR descriptor to skew, rotation, image blur and noise is similar to SIFT. FAIR shows b...

Automatic range image registration without any knowledge of the viewpoint requires identification of common regions across different range images and then establishing point correspondences in these regions. We formulate this as a graph-based optimization problem. More specifically, we define a graph in which each vertex represents a putative match...

A traditional solution of area-based stereo uses some kind of windowed pixel intensity correlation. This approach suffers from discretization artifacts which corrupt the correlation value. We introduce a new correlation statistic, which is completely invariant to image sampling, moreover it naturally provides a position of the correlation maximum b...

A traditional solution of area-based stereo uses some kind of windowed pixel intensity correlation. This approach suffers from discretization artifacts which corrupt the correlation value. We introduce a new correlation statistic, which is completely invariant to image sampling, moreover it naturally provides a position of the correlation maximum b...

Ultrasound B-mode images of thyroid gland were previously analyzed to distinguish normal tissue from inflamed tissue due to Hashimoto’s Lymphocytic Thyroiditis. This is a two-class recognition problem. Sensitivity and specificity of 100% was reported using Bayesian classifier with selected texture features. These results were obtained on 99 subject...

In this paper we propose rectification procedure for binocular stereoscopic vision that minimizes the loss of local image neighbourhood discriminability in rectified images. The optimality of the rectification is thus influenced by image contents. Such rectification helps seek for precise dense correspondences.

A traditional solution of area-based stereo uses some kind of windowed pixel intensity correlation. This approach suffers from discretization artifacts which corrupt the correlation value. We introduce a new correlation statistic, which is completely invariant to image sampling, moreover it naturally provides a position of the correlation maximum b...

Usually object segmentation and motion estimation are con- sidered (and modelled) as dierent tasks. For motion estimation this leads to problems arising especially at the boundary of an object mov- ing in front of another if e.g. prior assumptions about continuity of the motion field are made. Thus we expect that a good segmentation will improve th...

This paper describes a method for accurate dense reconstruction of a complex scene from a small set of high-resolution unorganized still images taken by a hand-held digital camera. A fully automatic data processing pipeline is proposed. Highly discriminative features are first detected in all images. Correspondences are then found in all image pair...

The main contributions are two-fold: Firstly, some theoretical analyses are carried out on trinocular rectification, including the relationship among the three rectified images and their three fundamental matrices, and an geometric interpretation of the 6 free parameters involved in the rectification process. Such results could be used as a theoret...

Ultrasonography is a generally accepted method for diagnosing both the diffuse and focal (nodal) lesions of the thyroid gland. The main limit of this method is the restricted ability of the human eye to analyse all information included. Moreover, the proportion of subjectivity when evaluating the picture is greater than with other imaging methods....

Helmholtz Stereopsis (HS) has recently been explored as a promising technique for capturing shape of objects with un- known reectance . So far, it has been widely applied to objects of smooth geometry and piecewise uniform Bidi- rectional Reectance Distribution Function (BRDF). More- over, for non-convex surfaces the inter-reection effects have bee...

In this paper we propose rectification procedure for binocular stereoscopic vision that minimizes the loss of local image neighbourhood discriminability in rectified images. The optimality of the rectification is thus influenced by image contents. Such rectification helps seek for precise dense correspondences.

Helmholtz stereopsis guarantees unbiasedness by BRDF of the search for inter-image correspondences. In a practical setup, calibrated pixel sensitivity and corrected light anisotropy are required for the method to work well. In this paper a simple method for joint light-camera radiometric calibration is proposed. Such calibration is shown to be an i...

The current practice in assessing sonographic findings of chronic inflamed thyroid tissue is mainly qualitative, based just on a physician's experience. This study shows that inflamed and healthy tissues can be differentiated by automatic texture analysis of B-mode sonographic images. Feature selection is the most important part of this procedure....

Local joint image modeling in stereo matching brings more discriminable and stable matching features. Such features reduce the need for strong prior models (continuity) and thus algorithms that are less prone to false positive artefacts in general complex scenes can be applied. One of the principal qual-ity factors in area-based dense stereo is the...

In this paper we study the behaviour of the Stratified Dense Matching algorithm~(SDM). We focus on its properties and performance and compare the results with the Confidently Stable Matching, the algorithm used in the SDM. The experiments are performed on a rigorous ground-truth experiment, as well as on real outdoor scenes.

Relations between measurable properties of B-mode ultrasound images of thyroid gland and clinical and laboratory findings in patients with chronic inflammation of thyroid gland were studied. Data from 65 patients with lymphocytic thyroiditis (LT) and 38 control subjects were analysed. Raw values of individual B-mode image pixels and standard co-occ...

Chronic autoimmune thyroiditis is a common disease of thyroid gland. The paper describes a novel method of modeling texture features and reports results of sonographic image analysis and distinguishing between normal tissue and the chronic inflammation process in thyroid gland by means of texture analysis. Reconstruction analysis is used to find ap...

The knowledge of stereo matching algorithm properties and behaviour under varying conditions is crucial for the selection of a proper method for the desired application. In this paper we study the behaviour of four representative matching algorithms under varying signal-to-noise ratio in six types of error statistics. The errors are focused on basi...

Ultrasound is very important imaging modality in diagnosing and monitoring diseases of thyroid gland. We propose using quantifiable indices for texture characterization and classification. Spatial features, co-occurrence texture features, and non-heuristic texture features are compared in this study. The spatial texture features acted as the best d...

The knowledge of stereo matching algorithm properties and behaviour under varying conditions is crucial for the selection of a proper method for the desired application. In this paper we study the behaviour of four representative matching algorithms under varying signal-to-noise ratio in six types of error statistics. The errors are focused on basi...

A photogrammetric method for measuring general motions is used to show that it is possible to measure quantitative parameters related to breathing movements of a human body. In a feasibility test we succeeded to relate the observed measurements with a biomechanical breathing model. The proposed setup allows for a non-contact, instantaneous measurem...

Stereo matching is an ill-posed problem for at least two principal reasons: (1) because of the random nature of match similarity measure and (2) because of structural ambiguity due to repetitive patterns. Both ambiguities require the problem to be posed in the regularization framework. Continuity is a natural choice for a prior model. But this mode...

Lambertian photometric stereo with uncalibrated light directions and intensities determines the surface normals only up to an invertible linear transformation. We show that if object reflectance is a sum of Lambertian and specular terms, the ambiguity reduces into a 2dof group of transformations (compositions of isotropic scaling, rotation around t...

Facial expressions of emotion are increasingly being used in neuroscience as probes for functional imaging and as stimuli for studying hemispheric specialization for face and emotion processing. Available facial stimuli are 2-dimensional and therefore, their orientation is fixed and poorly suited for examining asymmetries, they are often obtained u...

Sonography is a widely used non-invasive diagnostic tool and its main advantage is low cost in comparison with other diagnostic methods such as immunological analyses. In this work it is presented the relation between a sonographic image of thyroid gland and an immunological status of the patients with Hashimoto's lymphocytic thyroiditis (chronic i...

The success of discrimination between normal and inflamed parenchyma of thyroid gland by means of automatic texture analysis is largely determined by selecting descriptive yet simple and independent sonographic image features.We replace the standard non-systematic process of feature selection by systematic feature construction based on the search f...

This paper deals with stable monotonic matching (SMM), which is a generalization of stable matching that includes ordering constraint. The matching algorithm is fast, does not optimize any explicit cost functional, processes one epipolar line at a time, and requires only two parameters for disparity search range. A designed experiment demonstrates...

Photometric stereo with uncalibrated lights determines surface orientations ambiguously up to any regular transformation. If the surface reflectance model is separable with respect to the illumination and viewing directions, its inherent symmetries enable to design two previously unrecognized constraints on normals that reduce this ambiguity. The t...

: This work deals with verification of local 3D geometric model recovered from noisy data. Verification is understood as making decision about consistency of the model with a set of images. To evaluate the consistency, a statistical measure is chosen and a novel procedure for testing statistical dependence among a set of random variables is propose...

In this paper,we have investigated the fusion of surface data obtained by two different surface recovery methods. In particular, we have fused the depth data obtainable by shape from contours and local surface orientation data obtainable by photometric stereo. It has been found that the surface obtained by fusing orientation and depth data is able...

Sonography is a widely used non-invasive diag-nostic tool. Analyzing changes in sonograms provides a means of diagnosing and monitoring chronic thyroid gland diseases. Nonetheless, conventional sonography is still qual-itative. To improve the diagnosis reliability, quantitative im-age analysis is highly desirable for the assessment of various thyro...

We show in this chapter that the bottom-up approach to 3D surface model reconstruction is feasible and may be used in applications requiring precision and accuracy. We focus on acquiring 3D models of natural objects for medical applications, augmented reality, and telepresence. The reconstruction consists of several successive steps in which more c...

Among properties computer vision attempts to extract from images are: local shape, intrinsic reflection parameters, and roughness because they are all crucial to the success of image interpretation in general and to realistic surface modeling in particular. We seek light reflection phenomena and reflectance models that could better capture the rela...

In the advent of the ubiquity of distributed computing with multimedia capabilities, it is very natural to contemplate collaborations that were not previously possible. In the past scientists, doctors, educators, engineers always had need to share, exchange, debate their work, designs, methodology, knowledge and experience. This was commonly done b...

In this paper we address an application of computer vision which can in the future change completely our way of communicating over the network. We present our version of a testbed for telecollaboration. It is based on a highly accurate and precise stereo algorithm. The results demonstrate the live (on-line) recovery of 3D models of a dynamically ch...

In this paper we summarize the results we have obtained in building a testbed for tele-collaboration. It is based on a highly accurate and precise stereo algorithm. The results demonstrate the live (on-line) recovery of 3-D models of a dynamically changing environment and the simultaneous display and manipulation of the models. Virtual tele-collabo...

We address the problem of automatically reconstructing m-manifolds of unknown topology from unorganized points in metric p-spaces obtained from a noisy measurement process . The point set is first approximated by a collection of oriented primitive fuzzy sets over a range of resolutions. Hierarchical multiresolution representation is then computed b...

We present our long-term effort focused on building a 3-D model acquisition system for teleimmersion applications. In our project we stress fast processing and high fidelity of the result: it is not just geometric accuracy of the recovered geometric model but also radiometric correctness of the recovered surface texture. We suggest that single-type...

We address the problem of automatically reconstructing m-manifolds of unknown topology from unorganized points in metric p-spaces obtained from a noisy measurement process. The point set is first approximated by a collection of oriented primitive fuzzy sets over a range of resolutions. Hierarchical multiresolution representation is then computed ba...

We study occluding contour artifacts in area-based stereo matching: they are false responses of the matching operator to the occlusion boundary and cause the objects extend beyond their true boundaries in disparity maps. Most of the matching methods suffer from these artifacts; the effect is so strong that it cannot be ignored. We show what gives r...

We study occluding contour artifacts in area-based stereo matching: they are false responses of the matching operator to the occlusion boundary and cause the objects to extend beyond their true boundaries in disparity maps. Most of the matching methods suffer from these artifacts; the effect is so strong that it cannot be ignored. We show what give...

We address the problem of automatically reconstructing m-manifolds of