TY - GEN
T1 - A car detection system based on hierarchical visual features
AU - Tivive, Fok Hing Chi
AU - Abdesselam, Bouzerdoum
PY - 2009
Y1 - 2009
N2 - In this paper, we address the problem of detecting and localizing cars in still images. The proposed car detection system is based on a hierarchical feature detector in which the processing units are shunting inhibitory neurons. To reduce the training time and complexity of the network, the shunting inhibitory neurons in the first layer are implemented as directional nonlinear filters, whereas the neurons in the second layer have trainable parameters. A multi-resolution processing scheme is implemented so as to detect cars of different sizes, and to reduce the number of false positives during the detection stage, an adaptive thres holding strategy is developed. Tested on the UIUC car database, the proposed method achieves better classification results than some of the existing car detection approaches.
AB - In this paper, we address the problem of detecting and localizing cars in still images. The proposed car detection system is based on a hierarchical feature detector in which the processing units are shunting inhibitory neurons. To reduce the training time and complexity of the network, the shunting inhibitory neurons in the first layer are implemented as directional nonlinear filters, whereas the neurons in the second layer have trainable parameters. A multi-resolution processing scheme is implemented so as to detect cars of different sizes, and to reduce the number of false positives during the detection stage, an adaptive thres holding strategy is developed. Tested on the UIUC car database, the proposed method achieves better classification results than some of the existing car detection approaches.
UR - http://www.scopus.com/inward/record.url?scp=67650360770&partnerID=8YFLogxK
U2 - 10.1109/CIMSVP.2009.4925645
DO - 10.1109/CIMSVP.2009.4925645
M3 - Conference contribution
AN - SCOPUS:67650360770
SN - 9781424427710
T3 - 2009 IEEE Symposium Computational Intelligence for Multimedia Signal and Vision Processing, CIMSVP 2009 - Proceedings
SP - 35
EP - 40
BT - 2009 IEEE Symposium Computational Intelligence for Multimedia Signal and Vision Processing, CIMSVP 2009 - Proceedings
PB - IEEE Computer Society
T2 - 2009 IEEE Symposium Computational Intelligence for Multimedia Signal and Vision Processing, CIMSVP 2009
Y2 - 30 March 2009 through 2 April 2009
ER -