The Study of a Vision-Based Pedestrian Interception System

This paper designs a vision-based pedestrian interception system with a mobile robot, which can be potentially utilized in such applications as service robots. Specifically, by employing the Histograms of Oriented Gradients(HOG), together with some Edge Detection (ED) method, we first propose a novel HOG-ED approach to detect a human being from the series of acquired images accurately, based on which the depth information is successfully extracted on the basis of some geometrical analysis. After that, a two-level vision-based control scheme integrating depth extraction is presented to drive a mobile robot to intercept the pedestrian. The accuracy of the proposed depth estimation method and the interception controller are validated through experimental results.

[1]  Xiaojing Song,et al.  A Kalman Filter-Integrated Optical Flow Method for Velocity Sensing of Mobile Robots , 2011, IEEE/ASME Transactions on Mechatronics.

[2]  Giuseppe Oriolo,et al.  Vision-based interception of a moving target with a nonholonomic mobile robot , 2007, Robotics Auton. Syst..

[3]  Andrey V. Savkin,et al.  Interception of a moving object with a specified approach angle by a wheeled robot: Theory and experiment , 2008, 2008 47th IEEE Conference on Decision and Control.

[4]  Shuicheng Yan,et al.  An HOG-LBP human detector with partial occlusion handling , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[5]  R. Sreerama Kumar,et al.  An artificial neural network based dynamic controller for a robot in a multi-agent system , 2009, Neurocomputing.

[6]  Andrey V. Savkin,et al.  Vision-Based Interception of a Moving Target by a Mobile Robot , 2007, 2007 IEEE International Conference on Control Applications.

[7]  Leena Vachhani,et al.  Single image based depth estimation for robotic applications , 2011, 2011 IEEE Recent Advances in Intelligent Computational Systems.

[8]  Widodo Budiharto,et al.  A navigation system for service robot using stereo vision and Kalman Filtering , 2011, 2011 11th International Conference on Control, Automation and Systems.

[9]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[10]  Antonio Bicchi,et al.  Closed loop steering of unicycle like vehicles via Lyapunov techniques , 1995, IEEE Robotics Autom. Mag..

[11]  Xi Liu,et al.  Motion-Estimation-Based Visual Servoing of Nonholonomic Mobile Robots , 2011, IEEE Transactions on Robotics.

[12]  Y F Li,et al.  Determination of Stripe Edge Blurring for Depth Sensing , 2011, IEEE Sensors Journal.

[13]  Widodo Budiharto,et al.  An Improved Face Recognition System for Service Robot Using Stereo Vision , 2011 .

[14]  R. Sreerama Kumar,et al.  Intelligent task planning and action selection of a mobile robot in a multi-agent system through a fuzzy neural network approach , 2007, Eng. Appl. Artif. Intell..

[15]  Giuseppe Oriolo,et al.  Local incremental planning for nonholonomic mobile robots , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[16]  Giuseppe Oriolo,et al.  Image-Based Visual Servoing for Nonholonomic Mobile Robots Using Epipolar Geometry , 2007, IEEE Transactions on Robotics.