The Experts below are selected from a list of 5976 Experts worldwide ranked by ideXlab platform
Simon Lacroix - One of the best experts on this subject based on the ideXlab platform.
-
ISRR - Simultaneous Localization and Mapping with Stereovision.
2020Co-Authors: Ilkyun Jung, Simon LacroixAbstract:This paper presents as imultaneous localization and mapping approach based on an extended kalman filter ,u sing only as et of non-registered Stereovision image pairs. Invariant image point features are used to detect 3D landmarks and to provide local motion estimates. The 3D coordinates of each point feature are computed by Stereovision, and an interest point matching algorithm solves the data association problem. The estimation of the errors on the local motion estimations, on the landmark initialisations and on the landmark observations are depicted, and results with lo wa ltitude aerial images are presented.
-
ICRA - Fast Dense Panoramic Stereovision
Proceedings of the 2005 IEEE International Conference on Robotics and Automation, 2005Co-Authors: Jose Joel Gonzalez-Barbosa, Simon LacroixAbstract:The particular geometry of panoramic cameras defines complex epipolar lines equations. In this paper, we present a way to warp images from a panoramic Stereovision bench, so that the epipolar lines become parallel straight lines, thus allowing the use of an optimized fast pixel correlation based Stereovision algorithm. The paper first introduces the geometric characterization of panoramic camera composed of parabolic and spherical mirrors, that computes both the intrinsic parameters of the system (mirror surfaces and intrinsic camera parameters) and the errors alignment between the mirrors. Then, it presents the warping equations that allow to generate rectified images. Calibration and Stereovision results are presented.
-
Fast dense panoramic Stereovision
Proceedings - IEEE International Conference on Robotics and Automation, 2005Co-Authors: Jose Joel Gonzalez-Barbosa, Simon LacroixAbstract:The particular geometry of panoramic cameras defines complex epipolar lines equations. In this paper, we present a way to warp images from a panoramic Stereovision bench, so that the epipolar lines become parallel straight lines, thus allowing the use of an optimized fast pixel correlation based Stereovision algorithm. The paper first introduces the geometric characterization of panoramic camera composed of parabolic and spherical mirrors, that computes both the intrinsic parameters of the system (mirror surfaces and intrinsic camera parameters) and the errors alignment between the mirrors. Then, it presents the warping equations that allow to generate rectified images. Calibration and Stereovision results are presented.
-
simultaneous localization and mapping with Stereovision
ISRR, 2003Co-Authors: Ilkyun Jung, Simon LacroixAbstract:This paper presents as imultaneous localization and mapping approach based on an extended kalman filter ,u sing only as et of non-registered Stereovision image pairs. Invariant image point features are used to detect 3D landmarks and to provide local motion estimates. The 3D coordinates of each point feature are computed by Stereovision, and an interest point matching algorithm solves the data association problem. The estimation of the errors on the local motion estimations, on the landmark initialisations and on the landmark observations are depicted, and results with lo wa ltitude aerial images are presented.
Philippe Paillou - One of the best experts on this subject based on the ideXlab platform.
-
Trinocular Stereovision by generalized hough transform
Pattern Recognition, 1996Co-Authors: Jun Shen, Philippe PaillouAbstract:Abstract In this paper we generalize the Hough transform to match the edge segments in trinocular Stereovision and determine the parameters of the segments in 3-D (three-dimensional) space. We show that the corresponding segment triplet candidates can be detected by a generalized Hough transform in the parameter plane (ω, θ) which characterizes the 3-D segment orientation. These triplets can then be verified and the position parameters of the 3-D segments can be detected by a Hough transform in the parameter plane (Y, Z). So the matching of geometric primitives in trinocular Stereovision images can be found by the cascade of searchings in two 2-D parameters spaces only. Experimental results are satisfactory. Our method shows the following advantages: (1) trinocular Stereovision image matching is transformed into searching in 2-D parameter spaces, which much reduces the computational complexity. (2) Matching can be carried out completely in parallel. (3) No a priori similarity between images is needed, so very different views can be used, which improves the precision of 3-D reconstruction. (4) It is very efficient to solve false targets. (5) Our method gives good results even for partially hidden segments.
-
Trinocular Stereovision by generalized Hough transform
Proceedings of SPIE, 1995Co-Authors: Jun Shen, Philippe PaillouAbstract:In this paper, we present the generalized Hough transform to match the edge segments in trinocular Stereovision. We show that the corresponding segment triplet candidates can be detected by a generalized Hough transform in the parameter space ((theta) ,(phi) ) which characterizes the 3D segment orientation. These triplets can then be verified, and the position parameters of the 3D segments can be detected by a generalized Hough transform in the parameter space (Y,Z). So the matching of geometric primitives in trinocular Stereovision images can be found by the cascade of two generalized Hough transforms in the spaces of only two dimensions. Experimental results are reported also. Our method shows the following advantages: (1) Trinocular Stereovision image matching is transformed into Hough transforms in 2D parameter spaces, which reduces much the computational complexity. (2) Matching can be done completely in parallel. (3) No a priori similarity between images is needed, so very different views can be used, which improves the precision of 3D reconstruction. (4) It is very efficient to solve false targets. (5) Our method gives good results even for partially hidden segments.© (1995) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.
-
Trinocular Stereovision by matching in parameter space
International Conference on Intelligent Manufacturing, 1995Co-Authors: Jun Shen, Philippe PaillouAbstract:In this paper, we generalize the Hough transform to match the edge segments in trinocular Stereovision and to determine the parameters of the segments in 3-D space. We show that the corresponding segment triplet candidates can be detected by a Hough transform in the parameter plane ((theta) , (phi) ) which characterizes the 3-D segment orientation. These triplets can then be verified, and the position parameters of the 3-D segments can be detected by a Hough transform in the parameter plane (Y, Z). So the matching of geometric primitives in trinocular Stereovision images can be found by the cascade of searchings in two 2-D parameter spaces only. Experimental results are satisfactory. Our method shows the following advantages: (1) Trinocular Stereovision image matching is transformed into searching in 2-D parameter spaces, which much reduces the computational complexity. (2) Matching can be done completely in parallel. (3) No a priori similarity between images is needed, so very different views can be used, which improves the precision of 3-D reconstruction. (4) It is very efficient to solve false targets. (5) Our method gives good results even for partially hidden segments.© (1995) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.
Jianhua Wang - One of the best experts on this subject based on the ideXlab platform.
-
Effect of Calibration Error on Reconstruction Accuracy of Stereovision System
The Open Automation and Control Systems Journal, 2013Co-Authors: Jianhua Wang, Zhao Yang, Yu Ping WuAbstract:This paper investigates the relation between the calibration error and reconstruction accuracy of Stereovision system through simulation experiment. According to the model of a typical non-parallel Stereovision system, an array of points in the common view field of the two cameras is projected onto the image plane of the left and right camera respec- tively, forming the left image and right image. After changing the calibration parameter slightly around its ground truth, the array of points is reconstructed. By comparing the reconstruction result of the points in the array with their original position, the major factors affecting reconstruction accuracy are summarized, which include the abscissa of the principal point, the component of the rotation vector along the ordinate axis, the first order radial distortion coefficient, the compo- nent of the translation vector along the abscissa axis, and the abscissa of the principal length. Especially, the abscissa of the principal point and the component of the rotation vector along the ordinate axis have prominent effect on reconstruc- tion accuracy. In the process of calibration, the error of the major factors must be controlled strictly, so that the accuracy requirement of the Stereovision system can be satisfied.
-
Calibration Accuracy and Reconstruction Accuracy of Stereovision System
Applied Mechanics and Materials, 2013Co-Authors: Jianhua Wang, Zhao Yang, Yu Ping WuAbstract:Error of Stereovision reconstruction comes from feature extraction, correspondence and calibration. This paper is focused on investigation of the relation between reconstruction accuracy and calibration accuracy of a Stereovision. A model of Stereovision system is established, which consists of two cameras configured with their coordinate not paralleled. An array of points in the common view field of the two cameras is projected onto the image planes of the left and right cameras respectively and forms the left image and right image. After changing the calibration parameters of the Stereovision system, including intrinsic parameters of the cameras and their relative position and pose, the array of points are reconstructed and compared with their original positions. The main factors affecting the reconstruction errors are discussed.
-
Stereovision aided navigation of an Autonomous Surface Vehicle
2011 3rd International Conference on Advanced Computer Control, 2011Co-Authors: Jianhua Wang, Pingping Huang, Changfeng Chen, Wei GuAbstract:This paper presents a Stereovision system to aid in navigating an Autonomous Surface Vehicle (ASV). The ASV is guided to follow a path mainly by GPS, while the Stereovision system is designed for assisting it to avoid obstacles or follow a target floating on water surface. After calibration, the Stereovision system can estimate the positions of floating objects founded simultaneously by both cameras, which can be used to plan the path such that the ASV can reach the target fast and avoid collision with other objects around. In fine sea state, when an obstacle is large enough and its color is different from the water surface obviously, the Stereovision system can navigate the ASV to avoid it successfully. If the obstacle is small or difficult for the ASV to distinguish from the background, the operator in front of the console of the base station on a mother ship or on the shore can intervene in and guide the ASV remotely according to the couples of images from the two cameras.
Didier Aubert - One of the best experts on this subject based on the ideXlab platform.
-
Long Range Obstacle Detection Using Laser Scanner and Stereovision
2006Co-Authors: Mathias Perrollaz, Nicolas Hautiere, Raphaël Labayrade, Cyril Royere, Didier AubertAbstract:To be exploited for driving assistance purpose, a road obstacle detection system must have a good detection rate and an extremely low false detection rate. Moreover, the field of possible applications depends on the detection range of the system. With these ideas in mind, we propose in this paper a long range generic road obstacle detection system based on fusion between Stereovision and laser scanner. The obstacles are detected and tracked by the laser sensor. Afterwards, Stereovision is used to confirm the detections. An overview of the whole method is given. Then the confirmation process is detailed: three algorithms are proposed and compared on real road situations.
-
Cooperative fusion for multi-obstacles detection with use of Stereovision and laser scanner
Autonomous Robots, 2005Co-Authors: Raphaël Labayrade, Cyril Royere, Dominique Gruyer, Didier AubertAbstract:We propose a new cooperative fusion approach between Stereovision and laser scanner in order to take advantage of the best features and cope with the drawbacks of these two sensors to perform robust, accurate and real time-detection of multi-obstacles in the automotive context. The proposed system is able to estimate the position and the height, width and depth of generic obstacles at video frame rate (25 frames per second). The vehicle pitch, estimated by Stereovision, is used to filter laser scanner raw data. Objects out of the road are removed using road lane information computed by Stereovision. Various fusion schemes are proposed and one is experimented. Results of experiments in real driving situations (multi-pedestrians and multi-vehicles detection) are presented and stress the benefits of our approach.
Yu Ping Wu - One of the best experts on this subject based on the ideXlab platform.
-
Effect of Calibration Error on Reconstruction Accuracy of Stereovision System
The Open Automation and Control Systems Journal, 2013Co-Authors: Jianhua Wang, Zhao Yang, Yu Ping WuAbstract:This paper investigates the relation between the calibration error and reconstruction accuracy of Stereovision system through simulation experiment. According to the model of a typical non-parallel Stereovision system, an array of points in the common view field of the two cameras is projected onto the image plane of the left and right camera respec- tively, forming the left image and right image. After changing the calibration parameter slightly around its ground truth, the array of points is reconstructed. By comparing the reconstruction result of the points in the array with their original position, the major factors affecting reconstruction accuracy are summarized, which include the abscissa of the principal point, the component of the rotation vector along the ordinate axis, the first order radial distortion coefficient, the compo- nent of the translation vector along the abscissa axis, and the abscissa of the principal length. Especially, the abscissa of the principal point and the component of the rotation vector along the ordinate axis have prominent effect on reconstruc- tion accuracy. In the process of calibration, the error of the major factors must be controlled strictly, so that the accuracy requirement of the Stereovision system can be satisfied.
-
Calibration Accuracy and Reconstruction Accuracy of Stereovision System
Applied Mechanics and Materials, 2013Co-Authors: Jianhua Wang, Zhao Yang, Yu Ping WuAbstract:Error of Stereovision reconstruction comes from feature extraction, correspondence and calibration. This paper is focused on investigation of the relation between reconstruction accuracy and calibration accuracy of a Stereovision. A model of Stereovision system is established, which consists of two cameras configured with their coordinate not paralleled. An array of points in the common view field of the two cameras is projected onto the image planes of the left and right cameras respectively and forms the left image and right image. After changing the calibration parameters of the Stereovision system, including intrinsic parameters of the cameras and their relative position and pose, the array of points are reconstructed and compared with their original positions. The main factors affecting the reconstruction errors are discussed.
