Human detection for a robot tractor using omni-directional stereo vision

It is critical to detect and identify obstacles for safe operation of robot tractors. This study focused on human detection using an omni-directional stereo vision (OSV). The Lucas-Kanade optical flow detection method was used to detect human in a panoramic image. A 3D panoramic image that was reconstructed from stereo rectified images using the sum of squared differences (SSDs) method was used to locate the position of a human. To evaluate the performance of the developed human detection method, two RTK-GPSs were used to investigate the accuracy of the detection method under stationary and motion conditions of a robot tractor. The results of field experiments indicated that a human could be detected successfully under both given conditions in the daytime. The RMS error of measured distance was less than half a meter compared with the reference distance measured by the RTK-GPSs.

[1]  Yajun Fang,et al.  Depth-based target segmentation for intelligent vehicles: fusion of radar and binocular stereo , 2002, IEEE Trans. Intell. Transp. Syst..

[2]  Allen R. Hanson,et al.  Fast construction of dynamic and multi-resolution 360 degrees panoramas from video sequences , 2006, Image Vis. Comput..

[3]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Luc Van Gool,et al.  Automatic detection and tracking of pedestrians from a moving stereo rig , 2010 .

[5]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[6]  Jun-Wei Hsieh.  Fast stitching algorithm for moving object detection and mosaic construction , 2004, Image Vis. Comput..

[7]  Noboru Noguchi,et al.  An obstacle identification algorithm for a laser range finder-based obstacle detector , 2005 .

[8]  Naoshi Kondo,et al.  Man-machine Cooperative System for Agricultural Robot (Part 2) , 1999 .

[9]  L Guo,et al.  Agricultural machinery safety alert system using ultrasonic sensors. , 2002, Journal of agricultural safety and health.

[10]  Ta-Te Lin,et al.  Development of a virtual reality GIS using stereo vision , 2008 .

[11]  Frank Dellaert,et al.  Probabilistic structure matching for visual SLAM with a multi-camera rig , 2010, Comput. Vis. Image Underst..

[12]  Peng Chang,et al.  Collision sensing by stereo vision and radar sensor fusion , 2008, 2008 IEEE Intelligent Vehicles Symposium.

[13]  Martin Glavin,et al.  Detection of pedestrians in far-infrared automotive night vision using region-growing and clothing distortion compensation , 2010 .

[14]  Rafael Arnay,et al.  Real-time adaptive obstacle detection based on an image database , 2011, Comput. Vis. Image Underst..

[15]  Zhengyou Zhang,et al.  Flexible camera calibration by viewing a plane from unknown orientations , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[16]  Noboru Noguchi,et al.  Development of a master-slave robot system for farm operations , 2004 .

[17]  Pedro U. Lima,et al.  Omni-directional catadioptric vision for soccer robots , 2001, Robotics Auton. Syst..

[18]  Tom Duckett,et al.  Self-localization in non-stationary environments using omni-directional vision , 2007, Robotics Auton. Syst..

[19]  Patricio A. Vela,et al.  Personnel tracking on construction sites using video cameras , 2009, Adv. Eng. Informatics.

[20]  E. Riseman,et al.  Panoramic virtual stereo vision of cooperative mobile robots for localizing 3D moving objects , 2000, Proceedings IEEE Workshop on Omnidirectional Vision (Cat. No.PR00704).