Moving object detection by mobile Stereo Omni-directional System (SOS) using spherical depth image

Moving object detection with a mobile image sensor is an important task for mobile surveillance systems running in real environments. In this paper, we propose a novel method to effectively solve this problem by using a Stereo Omni-directional System (SOS), which can obtain both color and depth images of the environment in real time with a complete spherical field of view. Taking advantage of the SOS that the frame-out problem never occurs, we develop a method to detect the regions of moving objects stably under arbitrary movement and pose change of the SOS, by using the spherical depth image sequence obtained by the SOS. The method first predicts the depth image for the current time from that obtained at the previous time and the ego-motion of the SOS, and then detects moving objects by comparing the predicted depth image with the actual one obtained at the current time.

[1]  Yutaka Satoh,et al.  Detection of Moving Object by Mobile Stereo Omni-directional System (SOS) , 2004 .

[2]  Carlo Tomasi,et al.  Fast, robust, and consistent camera motion estimation , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[3]  Jan-Olof Eklundh,et al.  A real-time system for epipolar geometry and ego-motion estimation , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[4]  R. Nevatia,et al.  Detecting moving objects from a moving platform , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[5]  David Beymer,et al.  Real-Time Tracking of Multiple People Using Continuous Detection , 1999 .

[6]  Larry S. Davis,et al.  Tracking humans from a moving platform , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[7]  Kazuhiko Yamamoto,et al.  Acquisition of three-dimensional information in a real environment by using the Stereo Omni-directional System (SOS) , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[8]  Yoshiaki Shirai,et al.  Recognizing Moving Obstacles for Robot Navigation using Real-time Omnidirectional Stereo Vision , 2002, J. Robotics Mechatronics.

[9]  Naokazu Yokoya,et al.  Real‐time tracking of multiple moving objects using split‐and‐merge contour models based on crossing detection , 1999 .

[10]  Evangelos E. Milios,et al.  Robot Pose Estimation in Unknown Environments by Matching 2D Range Scans , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Erwin Prassler,et al.  Tracking Multiple Moving Objects for Real-Time Robot Navigation , 2000, Auton. Robots.

[12]  Jean-Marc Odobez,et al.  Detection of multiple moving objects using multiscale MRF with camera motion compensation , 1994, Proceedings of 1st International Conference on Image Processing.

[13]  Masayuki Inaba,et al.  Walking human avoidance and detection from a mobile robot using 3D depth flow , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[14]  Jan-Olof Eklundh,et al.  Detecting and tracking moving objects from a mobile platform using a laser range scanner , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[15]  Mutsumi Watanabe,et al.  A moving object recognition method by optical flow analysis , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[16]  Yutaka Satoh,et al.  Location and pose estimation for active vision using panoramic edge histograms , 2004 .

[17]  Erwin Prassler,et al.  Fast and robust tracking of multiple moving objects with a laser range finder , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[18]  Kazuhiko Yamamoto,et al.  Moving object detection with mobile stereo omni-directional system (SOS) based on motion compensatory inter-frame depth subtraction , 2004, ICPR 2004.

[19]  Jake K. Aggarwal,et al.  Detecting unexpected moving obstacles that appear in the path of a navigating robot , 1994, Proceedings of 1st International Conference on Image Processing.

[20]  Michal Irani,et al.  Detecting and Tracking Multiple Moving Objects Using Temporal Integration , 1992, ECCV.

[21]  Anup Basu,et al.  Motion Tracking with an Active Camera , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Yutaka Satoh,et al.  Slant estimation for active vision using edge directions in omnidirectional images , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[23]  Naokazu Yokoya,et al.  Real-Time Tracking of Multiple Moving Object Contours in a Moving Camera Image Sequence , 2000 .

[24]  Maja J. Mataric,et al.  A laser-based people tracker , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[25]  Yoshiaki Shirai,et al.  Detection of moving objects against a changing background , 1999, Systems and Computers in Japan.