Fig 3 - uploaded by Aaron Mavrinac
Content may be subject to copyright.
Source publication
An economical self-localization system which uses a monocular camera and a set of artificial landmarks is presented herein. The system represents the surrounding environment as a topological graph where each node corresponds to an artificial landmark and each edge corresponds to a relative pose between two landmarks. The edges are weighted based on...
Contexts in source publication
Context 1
... shown in Fig. 3, the localization graph is connected assuming that the direct pose estimates in Fig. 2 are all available. Thus, the camera c can be localized with respect to the common reference frame R using any of the markers in the ...
Context 2
... aside from additional effort positioning and obtaining pose estimates, to increasing the size of M. In this example, direct pose estimates P W c , P W X , P Y X , P ZX , P Y Z , P Y R , and P ZR are obtained, along with their respective pose uncertainties. The availability of direct pose estimates is encapsulated in the localization graph of Fig. 3. The solution is obtained through composition of the estimated poses, accord- ing to (3), where the shortest paths are computed using Dijkstra's algorithm or similar. As an example, suppose the shortest path from c to R in G L is c, W, X, Y, Z, R. ...
Similar publications
The development of image sensor and optics enables the application of vision-based techniques to the non-contact dynamic vibration analysis of large-scale structures. As an emerging technology, a vision-based approach allows for remote measuring and does not bring any additional mass to the measuring object compared with traditional contact measure...
Citations
... As a solution to these issues, several authors have suggested the use of fiducial markers to enhance the pose estimation process (Davison et al. 2007;Yamada et al. 2009;Klopschitz and Schmalstieg 2007;Shaya et al. 2012;Neunert et al. 2015). The SPM-SLAM method (Rafael et al. 2019) addresses some of the aforementioned limitations by utilizing squared fiducial markers instead of natural features. ...
Fiducial markers are a cost-effective solution for solving labeling and monocular localization problems, making them valuable tools for augmented reality (AR), robot navigation, and 3D modeling applications. However, with the development of many marker detection systems in the last decade, it has become challenging for new users to determine which is best suited for their needs. This paper presents a qualitative and quantitative evaluation of the most relevant marker systems. We analyze the available alternatives in the literature, describe their differences and limitations, and conduct detailed experiments to compare them in terms of sensitivity, specificity, accuracy, computational cost, and performance under occlusion. To our knowledge, this study provides the most comprehensive and updated comparison of fiducial markers. In the Conclusion section, we offer recommendations on which method to use based on the application requirements.
... For instance, a tag-based precision landing on a recharging station for automated energy replenishment of micro UAVs was proposed in [56]. However, few studies have focused on using tags as a significant part of their localization solution [57,58]. ...
Automated visual data collection using autonomous unmanned aerial vehicles (UAVs) can improve the accessibility and accuracy of the frequent data required for indoor construction inspections and tracking. However, robust localization, as a critical enabler for autonomy, is challenging in ever-changing, cluttered, GPS-denied indoor construction environments. Rapid alterations and repetitive low-texture areas on indoor construction sites jeopardize the reliability of typical vision-based solutions. This research proposes a tag-based visual-inertial localization method for off-the-shelf UAVs with only a camera and an inertial measurement unit (IMU). Given that tag locations are known in the BIM, the proposed method estimates the UAV's global pose by fusing inertial data and tag measurements using an on-manifold extended Kalman filter (EKF). The root-mean-square error (RMSE) achieved in our experiments in laboratory and simulation, being as low as 2 − 5 cm, indicates the potential of deploying the proposed method for autonomous navigation of low-cost UAVs in indoor construction environments.
... An alternative to tracking natural keypoints in images is detecting fiducial markers. Klopschitz and other authors [59][60][61] introduced methods for solving visual SLAM based on markers. However, they do not consider optimizing the estimated marker poses for the ambiguity problem. ...
Artificial marker mapping is a useful tool for fast camera localization estimation with a certain degree of accuracy in large indoor and outdoor environments. Nonetheless, the level of accuracy can still be enhanced to allow the creation of applications such as the new Visual Odometry and SLAM datasets, low-cost systems for robot detection and tracking, and pose estimation. In this work, we propose to improve the accuracy of map construction using artificial markers (mapping method) and camera localization within this map (localization method) by introducing a new type of artificial marker that we call the smart marker. A smart marker consists of a square fiducial planar marker and a pose measurement system (PMS) unit. With a set of smart markers distributed throughout the environment, the proposed mapping method estimates the markers’ poses from a set of calibrated images and orientation/distance measurements gathered from the PMS unit. After this, the proposed localization method can localize a monocular camera with the correct scale, directly benefiting from the improved accuracy of the mapping method. We conducted several experiments to evaluate the accuracy of the proposed methods. The results show that our approach decreases the Relative Positioning Error (RPE) by 85% in the mapping stage and Absolute Trajectory Error (ATE) by 50% for the camera localization stage in comparison with the state-of-the-art methods present in the literature.
... In particular, planar markers [1]- [6], which are designed to be easily detected and associated across images, find extensive use in laboratory and commercial settings (factories, warehouses, mines, etc.). In applications that perform planar marker-based SfM or SLAM [7]- [10], there is a basic need to estimate the 6DOF pose of an observed marker relative to the camera coordinate frame. This is often solved as a special case of planar pose estimation (PPE), which functions by determining the relative pose between a plane of known dimensions and its projection onto the image [11]- [13]. ...
... Marker-based SfM/SLAM is an active research area [7]- [10], [20]. Marker ambiguity is not dealt with explicitly in [7], [9], [20], though [9] combined feature-based SfM with marker-based SfM. ...
... Marker-based SfM/SLAM is an active research area [7]- [10], [20]. Marker ambiguity is not dealt with explicitly in [7], [9], [20], though [9] combined feature-based SfM with marker-based SfM. Munoz-Salinas et al. applied the ratio test of [13] in their marker-based SfM [8] and SLAM pipeline [10]. ...
Planar markers are useful in robotics and computer vision for mapping and localisation. Given a detected marker in an image, a frequent task is to estimate the 6DOF pose of the marker relative to the camera, which is an instance of planar pose estimation (PPE). Although there are mature techniques, PPE suffers from a fundamental ambiguity problem, in that there can be more than one plausible pose solutions for a PPE instance. Especially when localisation of the marker corners is noisy, it is often difficult to disambiguate the pose solutions based on reprojection error alone. Previous methods choose between the possible solutions using a heuristic criteria, or simply ignore ambiguous markers. We propose to resolve the ambiguities by examining the consistencies of a set of markers across multiple views. Our specific contributions include a novel rotation averaging formulation that incorporates long-range dependencies between possible marker orientation solutions that arise from PPE ambiguities. We analyse the combinatorial complexity of the problem, and develop a novel lifted algorithm to effectively resolve marker pose ambiguities, without discarding any marker observations. Results on real and synthetic data show that our method is able to handle highly ambiguous inputs, and provides more accurate and/or complete marker-based mapping and localisation.
... Later, Klopschitz et al. [31] proposed a method where Structure from Motion was first employed to reconstruct the scene, and then the markers were located from the recovered camera poses. Karam et al. [32] presented a method to create a map of markers as a pose graph where nodes represent markers and edge the relative pose between them. Finally, Neunert et al. [33] proposed to fuse inertial information with fiducial markers using an EKF. ...
This paper proposes a novel approach for Simultaneous Localization and Mapping by fusing natural and artificial landmarks. Most of the SLAM approaches use natural landmarks (such as keypoints). However, they are unstable over time, repetitive in many cases or insufficient for a robust tracking (e.g. in indoor buildings). On the other hand, other approaches have employed artificial landmarks (such as squared fiducial markers) placed in the environment to help tracking and relocalization. We propose a method that integrates both approaches in order to achieve long-term robust tracking in many scenarios. Our method has been compared to the start-of-the-art methods ORB-SLAM2 [1] and LDSO [2] in the public dataset Kitti [3], Euroc-MAV [4], TUM [5] and SPM [6], obtaining better precision, robustness and speed. Our tests also show that the combination of markers and keypoints achieves better accuracy than each one of them independently.
... Later, Klopschitz et al. [31] proposed a method where Structure from Motion was first employed to reconstruct the scene, and then the markers were located from the recovered camera poses. Karam et al. [32] presented a method to create a map of markers as a pose graph where nodes represent markers and edge the relative pose between them. Finally, Neunert et al. [33] proposed to fuse inertial information with fiducial markers using an EKF. ...
This paper proposes a novel approach for Simultaneous Localization and Mapping by fusing natural and artificial landmarks. Most of the SLAM approaches use natural landmarks (such as keypoints). However, they are unstable over time, repetitive in many cases or insufficient for a robust tracking (e.g. in indoor buildings). On the other hand, other approaches have employed artificial landmarks (such as squared fiducial markers) placed in the environment to help tracking and relocalization. We propose a method that integrates both approaches in order to achieve long-term robust tracking in many scenarios. Our method has been compared to the start-of-the-art methods ORB-SLAM2 and LDSO in the public dataset Kitti, Euroc-MAV, TUM and SPM, obtaining better precision, robustness and speed. Our tests also show that the combination of markers and keypoints achieves better accuracy than each one of them independently.
... Karam et al. [24] propose the creation of a pose graph where nodes represent markers and edges the relative pose 107 between them. The map is created in an on-line process, and edges are updated dynamically. ...
SLAM is generally addressed using natural landmarks such as keypoints or texture, but it poses some limitations, such as the need for enough textured environments and high computational demands. In some cases, it is preferable sacrificing the flexibility of such methods for an increase in speed and robustness by using artificial landmarks. The recent work [1] proposes an off-line method to obtain a map of squared planar markers in large indoor environments. By freely distributing a set of markers printed on a piece of paper, the method estimates the marker poses from a set of images, given that at least two markers are visible in each image. Afterwards, camera localization can be done, in the correct scale. However, an off-line process has several limitations. First, errors can not be detected until the whole process is finished, e.g., an insufficient number of markers in the scene or markers not properly spotted in the capture stage. Second, the method is not incremental, so, in case of requiring the expansion of the map, it is necessary to repeat the whole process from start. Finally, the method can not be employed in real-time systems with limited computational resources such as mobile robots or UAVs. To solve these limitations, this work proposes a real-time solution to the problems of simultaneously localizing the camera and building a map of planar markers. This paper contributes with a number of solutions to the problems arising when solving SLAM from squared planar markers, coining the term SPM-SLAM. The experiments carried out show that our method can be more robust, precise and fast, than visual SLAM methods based on keypoints or texture.
... Once the camera trajectory is accurately obtained, marker locations are obtained by triangulation. In literature [16] a graph is used to describe the geometric relationship of each marker, which is updated dynamically. Whenever a pair of markers are seen in a frame, their relative position is updated and if it is better than the previous one, it is replaced. ...
A novel multi-sensor fusion indoor localization algorithm based on ArUco marker is designed in this paper. The proposed ArUco mapping algorithm can build and correct the map of markers online with Grubbs criterion and K-mean clustering, which avoids the map distortion due to lack of correction. Based on the conception of multi-sensor information fusion, the federated Kalman filter is utilized to synthesize the multi-source information from markers, optical flow, ultrasonic and the inertial sensor, which can obtain a continuous localization result and effectively reduce the position drift due to the long-term loss of markers in pure marker localization. The proposed algorithm can be easily implemented in a hardware of one Raspberry Pi Zero and two STM32 micro controllers produced by STMicroelectronics (Geneva, Switzerland). Thus, a small-size and low-cost marker-based localization system is presented. The experimental results show that the speed estimation result of the proposed system is better than Px4flow, and it has the centimeter accuracy of mapping and positioning. The presented system not only gives satisfying localization precision, but also has the potential to expand other sensors (such as visual odometry, ultra wideband (UWB) beacon and lidar) to further improve the localization performance. The proposed system can be reliably employed in Micro Aerial Vehicle (MAV) visual localization and robotics control.
... The work of Karam et al. [40] proposes the creation of a pose graph where nodes represents markers and edges the relative pose between them. The map is created in an online process, and edges updated dynamically. ...
Squared planar markers are a popular tool for fast, accurate and robust camera localization, but its use is frequently limited to a single marker, or at most, to a small set of them for which their relative pose is known beforehand. Mapping and localization from a large set of planar markers is yet a scarcely treated problem in favour of keypoint-based approaches. However, while keypoint detectors are not robust to rapid motion, large changes in viewpoint, or significant changes in appearance, fiducial markers can be robustly detected under a wider range of conditions. This paper proposes a novel method to simultaneously solve the problems of mapping and localization from a set of squared planar markers. First, a quiver of pairwise relative marker poses is created, from which an initial pose graph is obtained. The pose graph may contain small pairwise pose errors, that when propagated, leads to large errors. Thus, we distribute the rotational and translational error along the basis cycles of the graph so as to obtain a corrected pose graph. Finally, we perform a global pose optimization by minimizing the reprojection errors of the planar markers in all observed frames. The experiments conducted show that our method performs better than Structure from Motion and visual SLAM techniques.
