TY - GEN
T1 - Pedestrian detection via PCA filters based convolutional channel features
AU - Ke, Wei
AU - Zhang, Yao
AU - Wei, Pengxu
AU - Ye, Qixiang
AU - Jiao, Jianbin
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/8/4
Y1 - 2015/8/4
N2 - In this paper, we propose a kind of image representation, named PCA filters based convolutional channel features (PCA-CCF) for pedestrian detection. The motivation is to use the convolutional network architecture with orthogonal PCA filters to enhance the state-of-the-art aggregate channel features (ACF). In PCA-CCF, the convolutional operation improves the feature robustness to pedestrian local deformation. The learned PCA filters reduce the correlations among features of each channel, and therefore, improve feature discrimination capability. With the proposed PCA-CCF features and cascaded AdaBoost classifiers, we develop a coarse-to-fine pedestrian detection approach. Experiments show that such approach achieves 3.04%, 17.87% and 6.28% performance gain on the INRIA, Caltech Reasonable and Caltech Overall pedestrian datasets, respectively.
AB - In this paper, we propose a kind of image representation, named PCA filters based convolutional channel features (PCA-CCF) for pedestrian detection. The motivation is to use the convolutional network architecture with orthogonal PCA filters to enhance the state-of-the-art aggregate channel features (ACF). In PCA-CCF, the convolutional operation improves the feature robustness to pedestrian local deformation. The learned PCA filters reduce the correlations among features of each channel, and therefore, improve feature discrimination capability. With the proposed PCA-CCF features and cascaded AdaBoost classifiers, we develop a coarse-to-fine pedestrian detection approach. Experiments show that such approach achieves 3.04%, 17.87% and 6.28% performance gain on the INRIA, Caltech Reasonable and Caltech Overall pedestrian datasets, respectively.
KW - Channel features
KW - Convolutional network
KW - PCA
KW - Pedestrian detection
UR - https://www.scopus.com/pages/publications/84946070833
U2 - 10.1109/ICASSP.2015.7178199
DO - 10.1109/ICASSP.2015.7178199
M3 - 会议稿件
AN - SCOPUS:84946070833
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 1394
EP - 1398
BT - 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015
Y2 - 19 April 2014 through 24 April 2014
ER -