Moving Object Detection from Mobile Platforms Using Stereo Data Registration

This chapter describes a robust approach for detecting moving objects from on-board stereo vision systems. It relies on a feature point quaternion-based registration, which avoids common problems that appear when computationally ex- pensive iterative-based algorithms are used on dynamic environments. The proposed approach consists of three main stages. Initially, feature points are extracted and tracked through consecutive 2D frames. Then, a RANSAC based approach is used for registering two point sets, with known correspondences in the 3D space. The computed 3D rigid displacement is used to map two consecutive 3D point clouds into the same coordinate system by means of the quaternion method. Finally, mov- ing objects correspond to those areas with large 3D registration errors. Experimental results show the viability of the proposed approach to detect moving objects like ve- hicles or pedestrians in different urban scenarios.

[1]  Gaurav S. Sukhatme,et al.  Mobile Robot Simultaneous Localization and Mapping in Dynamic Environments , 2005, Auton. Robots.

[2]  Antonio M. López,et al.  Registration-based moving object detection from a moving camera , 2008 .

[3]  Michalis E. Zervakis,et al.  A survey of video processing techniques for traffic applications , 2003, Image Vis. Comput..

[4]  Pavel Krsek,et al.  Robust Euclidean alignment of 3D point sets: the trimmed iterative closest point algorithm , 2005, Image Vis. Comput..

[5]  Gérard G. Medioni,et al.  A GPU-based implementation of motion detection from a moving platform , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[6]  S. Shankar Sastry,et al.  An Invitation to 3-D Vision: From Images to Geometric Models , 2003 .

[7]  Roland Siegwart,et al.  Stereo-Based Ego-Motion Estimation Using Pixel Tracking and Iterative Closest Point , 2006, Fourth IEEE International Conference on Computer Vision Systems (ICVS'06).

[8]  A. Vedaldi.  An open implementation of the SIFT detector and descriptor , 2007 .

[9]  Sebastian Thrun,et al.  Online simultaneous localization and mapping with detection and tracking of moving objects: theory and results from a ground vehicle in crowded urban areas , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[10]  Ezzeddine Zagrouba,et al.  A robust framework for joint background/foreground segmentation of complex video scenes filmed with freely moving camera , 2009, Multimedia Tools and Applications.

[11]  Lu Wang,et al.  Extraction of Moving Objects From Their Background Based on Multiple Adaptive Thresholds and Boundary Evaluation , 2010, IEEE Transactions on Intelligent Transportation Systems.

[12]  David B. Cooper,et al.  Pose Estimation of Free-Form 3D Objects without Point Matching using Algebraic Surface Models , 1998 .

[13]  Bernd Neumann,et al.  Computer Vision — ECCV’98 , 1998, Lecture Notes in Computer Science.

[14]  Badrinath Roysam,et al.  Image change detection algorithms: a systematic survey , 2005, IEEE Transactions on Image Processing.

[15]  Gérard G. Medioni,et al.  Object modelling by registration of multiple range images , 1992, Image Vis. Comput..

[16]  Francis Schmitt,et al.  A Solution for the Registration of Multiple 3D Point Sets Using Unit Quaternions , 1998, ECCV.

[17]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[18]  Sang Wook Lee,et al.  ICP Registration Using Invariant Features , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Berthold K. P. Horn,et al.  Closed-form solution of absolute orientation using unit quaternions , 1987 .

[20]  Takeshi Oishi,et al.  A Fast Registration Method Using IP and Its Application to Ultrasound Image Registration , 2009, IPSJ Trans. Comput. Vis. Appl..

[21]  Tomaso A. Poggio,et al.  Pedestrian detection using wavelet templates , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[22]  S. Shankar Sastry,et al.  An Invitation to 3-D Vision , 2004 .

[23]  H. Chui,et al.  A feature registration framework using mixture models , 2000, Proceedings IEEE Workshop on Mathematical Methods in Biomedical Image Analysis. MMBIA-2000 (Cat. No.PR00737).

[24]  David Fofi,et al.  A review of recent range image registration methods with accuracy evaluation , 2007, Image Vis. Comput..

[25]  Angel D. Sappa,et al.  Adaptive Image Sampling and Windows Classification for On-board Pedestrian Detection , 2007 .

[26]  Katsushi Ikeuchi,et al.  An Adaptive and Stable Method for Fitting Implicit Polynomial Curves and Surfaces , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Rozenn Dahyot.  Unsupervised Camera Motion Estimation and Moving Object Detection in Videos , 2006 .

[28]  Saeed Shiry,et al.  Robust Moving Object Detection from a Moving Video Camera Using Neural Network and Kalman Filter , 2008, RoboCup.

[29]  Qian Yu,et al.  Map-Enhanced Detection and Tracking from a Moving Platform with Local and Global Data Association , 2007, 2007 IEEE Workshop on Motion and Video Computing (WMVC'07).

[30]  Shigeru Okuma,et al.  Active frame subtraction for pedestrian detection from images of moving camera , 2003, SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483).

[31]  Angel D. Sappa,et al.  Edge registration versus triangular mesh registration, a comparative study , 2005, Signal Process. Image Commun..

[32]  Andrew W. Fitzgibbon,et al.  Robust Registration of 2D and 3D Point Sets , 2003, BMVC.

[33]  Yutaka Satoh,et al.  Moving object detection by mobile Stereo Omni-directional System (SOS) using spherical depth image , 2006, Pattern Analysis and Applications.

[34]  Jean Ponce,et al.  Detecting Abandoned Objects With a Moving Camera , 2010, IEEE Transactions on Image Processing.

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

[36]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[37]  Baba C. Vemuri,et al.  A robust algorithm for point set registration using mixture of Gaussians , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[38]  Sergiu Nedevschi,et al.  Road Surface and Obstacle Detection Based on Elevation Maps from Dense Stereo , 2007, 2007 IEEE Intelligent Transportation Systems Conference.