Real-Time Human Detection Using Contour Cues
A real-time and accurate human detector, C4, is proposed in this paper. C4 achieves 20 fps speed and stateof- the-art detection accuracy, using only one processing thread without resorting to special hardwares like GPU. Real-time accurate human detection is made possible by two contributions. First, we show that contour is exactly what we should capture and signs of comparisons among neighboring pixels are the key information to capture contours. Second, we show that the CENTRIST visual descriptor is particularly suitable for human detection, because it encodes the sign information and can implicitly represent the global contour. When CENTRIST and linear classifier are used, we propose a computational method that does not need to explicitly generate feature vectors. It involves no image pre-processing or feature vector normalization, and only requires O(1) steps to test an image patch. C4 is also friendly to further hardware acceleration. In a robot with embedded 1.2GHz CPU, we also achieved accurate and 20 fps high speed human detection.
Jianxin Wu Christopher Geyer James M. Rehg
School of Computer Engineering,Nanyang Technological University,Singapore iRobot Corporation,Bedford,MA 01730,USA Center for Behavior Imaging and the School of Interactive Computing at the Georgia Institute of Tech
国际会议
2011 IEEE International Conference on Robotics and Automation(2011年IEEE世界机器人与自动化大会 ICRA 2011)
上海
英文
860-867
2011-05-09（万方平台首次上网日期，不代表论文的发表时间）