Histograms of Oriented Gradients for Human Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Vision-based interception of a moving target with a nonholonomic mobile robot
Robotics and Autonomous Systems
Engineering Applications of Artificial Intelligence
Image-Based Visual Servoing for Nonholonomic Mobile Robots Using Epipolar Geometry
IEEE Transactions on Robotics
Motion-Estimation-Based Visual Servoing of Nonholonomic Mobile Robots
IEEE Transactions on Robotics
Hi-index | 0.00 |
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.