TY - GEN
T1 - Real-time human detection using contour cues
AU - Wu, Jianxin
AU - Geyer, Christopher
AU - Rehg, James M.
PY - 2011
Y1 - 2011
N2 - A real-time and accurate human detector, C4, is proposed in this paper. C4 achieves 20 fps speed and state-of-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.
AB - A real-time and accurate human detector, C4, is proposed in this paper. C4 achieves 20 fps speed and state-of-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.
UR - http://www.scopus.com/inward/record.url?scp=84856670921&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84856670921&partnerID=8YFLogxK
U2 - 10.1109/ICRA.2011.5980437
DO - 10.1109/ICRA.2011.5980437
M3 - Conference contribution
AN - SCOPUS:84856670921
SN - 9781612843865
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 860
EP - 867
BT - 2011 IEEE International Conference on Robotics and Automation, ICRA 2011
T2 - 2011 IEEE International Conference on Robotics and Automation, ICRA 2011
Y2 - 9 May 2011 through 13 May 2011
ER -