Fast and Accurate Pedestrian Detection Using a Cascade of Multiple Features
We propose a fast and accurate pedestrian detection framework based on cascaded classifiers with two complementary features. Our pipeline starts with a cascade of weak classifiers using Haar-like features followed by a linear SVM classifier relying on the Co-occurrence Histograms of Oriented Gradients (CoHOG). CoHOG descriptors have a strong classification capability but are extremely high dimensional. On the other hand, Haar features are computationally efficient but not highly discriminative for extremely varying texture and shape information such as pedestrians with different clothing and stances. Therefore, the combination of both classifiers enables fast and accurate pedestrian detection. Additionally, we propose reducing CoHOG descriptor dimensionality using Principle Component Analysis. The experimental results on the DaimlerChrysler benchmark dataset show that we can reach very close accuracy to the CoHOG-only classifier but in less than 1/1000 of its computational cost.
KeywordsSupport Vector Machine Principle Component Analysis Linear Support Vector Machine Oriented Gradient Pedestrian Detection
Unable to display preview. Download preview PDF.
- 2.Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)Google Scholar
- 3.Dollar, P., Tu, Z., Tao, H., Belongie, S.: Feature mining for image classification. In: CVPR, pp. 1–8 (2007)Google Scholar
- 7.Kozakaya, T., Ito, S., Kubota, S., Yamaguchi, O.: Cat Face Detection with Two Heterogeneous Features. In: ICIP, pp. 1213–1216 (2009)Google Scholar
- 12.Viola, P., Jones, M., Snow, D.: Detecting pedestrians using patterns of motion and appearance. In: ICCV, pp. 734–741 (2003)Google Scholar
- 14.MATLAB SVM classifier: , http://www.mathworks.fr/access/helpdesk/help/toolbox/bioinfo/ref/svmtrain.html (last visited, June 2010)
- 15.The PASCAL Visual Object Classes Challenge (VOC), http://pascallin.ecs.soton.ac.uk/challenges/VOC/ (last visited, June 2010)
- 16.INRIA Person Dataset: , http://pascal.inrialpes.fr/data/human/ (last visited, June 2010)