Visual SLAM with an Omnidirectional Camera

Rituerto, Alejandro; Puig, Luis; Guerrero, J. J.

doi:10.1109/icpr.2010.94

Cited by 52 publications

(26 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While there exists a large body of literature on omnidirectional camera calibration [15], [16], [17], [18], localization [19], [20] and sparse structure-from-motion / SLAM [21], [22], [23], surprisingly little research has been carried out towards dense 3D reconstruction with catadioptric cameras.…”

Section: Related Workmentioning

confidence: 99%

Omnidirectional 3D reconstruction in augmented Manhattan worlds

Schoenbein

Geiger

2014

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-This paper proposes a method for high-quality omnidirectional 3D reconstruction of augmented Manhattan worlds from catadioptric stereo video sequences. In contrast to existing works we do not rely on constructing virtual perspective views, but instead propose to optimize depth jointly in a unified omnidirectional space. Furthermore, we show that plane-based prior models can be applied even though planes in 3D do not project to planes in the omnidirectional domain. Towards this goal, we propose an omnidirectional slanted-plane Markov random field model which relies on plane hypotheses extracted using a novel voting scheme for 3D planes in omnidirectional space. To quantitatively evaluate our method we introduce a dataset which we have captured using our autonomous driving platform AnnieWAY which we equipped with two horizontally aligned catadioptric cameras and a Velodyne HDL-64E laser scanner for precise ground truth depth measurements. As evidenced by our experiments, the proposed method clearly benefits from the unified view and significantly outperforms existing stereo matching techniques both quantitatively and qualitatively. Furthermore, our method is able to reduce noise and the obtained depth maps can be represented very compactly by a small number of image segments and plane parameters.

show abstract

Section: Related Workmentioning

confidence: 99%

Omnidirectional 3D reconstruction in augmented Manhattan worlds

Schoenbein

Geiger

2014

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

show abstract

“…In [17] a SLAM with an omnidirectional sensor has been proposed; in contrast with our approach they do not estimate the depth. In [18] the previous approach is extended by considering a patch formulation for data association which is invariant to rotation and scale.…”

Section: Related Workmentioning

confidence: 99%

Method for SLAM Based on Omnidirectional Vision: A Delayed-EKF Approach

et al. 2017

View full text Add to dashboard Cite

This work presents a method for implementing a visual-based simultaneous localization and mapping (SLAM) system using omnidirectional vision data, with application to autonomous mobile robots. In SLAM, a mobile robot operates in an unknown environment using only on-board sensors to simultaneously build a map of its surroundings, which it uses to track its position. The SLAM is perhaps one of the most fundamental problems to solve in robotics to build mobile robots truly autonomous. The visual sensor used in this work is an omnidirectional vision sensor; this sensor provides a wide field of view which is advantageous in a mobile robot in an autonomous navigation task. Since the visual sensor used in this work is monocular, a method to recover the depth of the features is required. To estimate the unknown depth we propose a novel stochastic triangulation technique. The system proposed in this work can be applied to indoor or cluttered environments for performing visual-based navigation when GPS signal is not available. Experiments with synthetic and real data are presented in order to validate the proposal.

show abstract

“…Most VO algorithms for omnidirectional cameras [7], [8], [9], [10] rely on robust feature descriptors (e.g., SIFT [11]) to establish feature correspondence. To cope with the significant distortion of large FoV images, special descriptors were developed that model the distortion effects to improve feature matching [12], [13], [14], [15].…”

Section: A Related Workmentioning

confidence: 99%

Benefit of large field-of-view cameras for visual odometry

Zhang

Rebecq

Förster

et al. 2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

The transition of visual-odometry technology from research demonstrators to commercial applications naturally raises the question: "what is the optimal camera for vision-based motion estimation?" This question is crucial as the choice of camera has a tremendous impact on the robustness and accuracy of the employed visual odometry algorithm. While many properties of a camera (e.g. resolution, frame-rate, global-shutter/rolling-shutter) could be considered, in this work we focus on evaluating the impact of the camera field-of-view (FoV) and optics (i.e., fisheye or catadioptric) on the quality of the motion estimate. Since the motion-estimation performance depends highly on the geometry of the scene and the motion of the camera, we analyze two common operational environments in mobile robotics: an urban environment and an indoor scene. To confirm the theoretical observations, we implement a state-of-the-art VO pipeline that works with large FoV fisheye and catadioptric cameras. We evaluate the proposed VO pipeline in both synthetic and real experiments. The experiments point out that it is advantageous to use a large FoV camera (e.g., fisheye or catadioptric) for indoor scenes and a smaller FoV for urban canyon environments. Benefit of Large Field-of-View Cameras for Visual OdometryZichao Zhang, Henri Rebecq, Christian Forster, Davide Scaramuzza Abstract-The transition of visual-odometry technology from research demonstrators to commercial applications naturally raises the question: "what is the optimal camera for visionbased motion estimation?" This question is crucial as the choice of camera has a tremendous impact on the robustness and accuracy of the employed visual odometry algorithm. While many properties of a camera (e.g. resolution, frame-rate, globalshutter/rolling-shutter) could be considered, in this work we focus on evaluating the impact of the camera field-of-view (FoV) and optics (i.e., fisheye or catadioptric) on the quality of the motion estimate. Since the motion-estimation performance depends highly on the geometry of the scene and the motion of the camera, we analyze two common operational environments in mobile robotics: an urban environment and an indoor scene. To confirm the theoretical observations, we implement a stateof-the-art VO pipeline that works with large FoV fisheye and catadioptric cameras. We evaluate the proposed VO pipeline in both synthetic and real experiments. The experiments point out that it is advantageous to use a large FoV camera (e.g., fisheye or catadioptric) for indoor scenes and a smaller FoV for urban canyon environments. SUPPLEMENTARY MATERIALA video showing our omnidirectional visual odometry pipeline performing on real and synthetic data is available at the website: http://rpg.ifi.uzh.ch/fov.html.

show abstract

Visual SLAM with an Omnidirectional Camera

Cited by 52 publications

References 11 publications

Omnidirectional 3D reconstruction in augmented Manhattan worlds

Omnidirectional 3D reconstruction in augmented Manhattan worlds

Method for SLAM Based on Omnidirectional Vision: A Delayed-EKF Approach

Benefit of large field-of-view cameras for visual odometry

Contact Info

Product

Resources

About