Fast Human Detection by Boosting Histograms of Oriented Gradients
Hui-Xing Jia, Yu‐Jin Zhang · 2007
In this paper, a novel real-time human detection system based on Viola's face detection framework and Histograms of Oriented Gradients (HOG) features is presented. Each bin of the histogram is treated as a feature and used as the basic building element of the cascade classifier. The system keeps both the discriminative power of HOG features for human detection and the real-time property of Viola's face detection framework. Experiments on Daimler Chrysler pedestrian benchmark data set and INRIA human database demonstrate that this framework is more powerful than Viola's object detection framework on human detection.