Outlier rejection by oriented tracks to aid pose estimation from video

This paper introduces a method for rejecting the false matches of points between successive views in a video sequence used to perform Pose from Motion for a mobile sensing platform. Typical methods for pose estimation require point correspondences to estimate the epipolar geometry between the two views. Algorithms for determining these correspondences invariably output false matches along with the good. We present an algorithm for identifying and removing these mismatches for scenes generated by a mobile scanning platform. The algorithm utilizes the motion characteristics of a rear-wheel drive sensing platform to identify correct point matches through their common motion trajectories. Our algorithm works in cases where the percentage of false matches may be as high as 80%, providing a set of correspondences whose correct/incorrect match ratio is higher than the mutual best match approach found in the literature. This algorithm is intended as a post-processing step for any point correspondence algorithm and its output can be used in standard pose estimation algorithms to enhance their speed and accuracy. Experimental results show the computational savings of our approach over the mutual best match method, resulting in comparable or better outlier rejection-increasing the true/false match ratio by 2-3 times-in only a fraction of the time.

[1]  Maarten Vergauwen,et al.  Video-to-3D , 2002 .

[2]  Andrew Zisserman,et al.  Motion From Point Matches Using Affine Epipolar Geometry , 1994, ECCV.

[3]  Cordelia Schmid,et al.  Comparing and evaluating interest points , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[4]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[5]  Jean Ponce,et al.  Computer Vision: A Modern Approach , 2002 .

[6]  Ehud Rivlin,et al.  Image-based robot navigation in unknown indoor environments , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[7]  Matthew P. Wand,et al.  Kernel Smoothing , 1995 .

[8]  Christian Früh,et al.  3D model generation for cities using aerial photographs and ground level laser scans , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[9]  Emanuele Trucco,et al.  Improving Feature Tracking with Robust Statistics , 1999, Pattern Analysis & Applications.

[10]  Yoshiaki Shirai,et al.  Three-Dimensional Computer Vision , 1987, Symbolic Computation.

[11]  Ettore Stella,et al.  Passive navigation using egomotion estimates , 2000, Image Vis. Comput..

[12]  Ryosuke Shibasaki,et al.  Reconstructing urban 3D model using vehicle-borne laser range scanners , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[13]  Xavier Armangué,et al.  A survey addressing the fundamental matrix estimation problem , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[14]  Reinhard Koch,et al.  Self-Calibration and Metric Reconstruction Inspite of Varying and Unknown Intrinsic Camera Parameters , 1999, International Journal of Computer Vision.

[15]  Emanuele Trucco,et al.  Title : Making Good Features to Track Better , 1998 .

[16]  Andrew E. Johnson,et al.  Machine vision for autonomous small body navigation , 2000, 2000 IEEE Aerospace Conference. Proceedings (Cat. No.00TH8484).

[17]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[18]  Yu Liang,et al.  Rejection of mismatched correspondences along the affine epipolar line , 2000, Image Vis. Comput..

[19]  Zhengyou Zhang,et al.  Determining the Epipolar Geometry and its Uncertainty: A Review , 1998, International Journal of Computer Vision.

[20]  Xavier Armangué,et al.  A review on egomotion by means of differential epipolar geometry applied to the movement of a mobile robot , 2003, Pattern Recognit..

[21]  ZhangZhengyou.  Determining the Epipolar Geometry and its Uncertainty , 1998 .

[22]  Peter I. Corke,et al.  Visual servoing of a car-like vehicle - an application of omnidirectional vision , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[23]  C. D. Kemp,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[24]  Martin A. Fischler,et al.  Computational Stereo , 1982, CSUR.

[25]  Peter I. Corke.  An inertial and visual sensing system for a small autonomous helicopter , 2004 .

[26]  Reinhard Koch,et al.  Self-calibration and metric reconstruction in spite of varying and unknown internal camera parameters , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[27]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Richard I. Hartley,et al.  In defence of the 8-point algorithm , 1995, Proceedings of IEEE International Conference on Computer Vision.

[29]  Reinhard Koch,et al.  Automated reconstruction of 3D scenes from sequences of images , 2000 .

[30]  Ehud Rivlin,et al.  ROR: Rejection of Outliers by Rotations , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Markus Vincze,et al.  Fusion of Vision and Inertial Data for Motion and Structure Estimation , 2004, J. Field Robotics.

[32]  Peter Corke.  An Inertial and Visual Sensing System for a Small Autonomous Helicopter , 2004, J. Field Robotics.

[33]  Klaus Jaeger,et al.  Image-based 3D scene analysis for navigation of autonomous airborne systems , 2001, SPIE Optics East.