A Multi-Feature Fusion Based Pedestrian Detection Method

This paper proposes an improved pedestrian detection algorithm, the Haar-like feature and Adaboost cascade classifier Histogram of Oriented Gradient (HOG) feature are utilizing to construct hybrid features library, then the weak classifiers in Adaboost are trained by using the combined hybrid features. And the strong classifiers are built based on the weak classifiers. In the proposed algorithm, For improving the detection speed, the HOG feature is rapidly calculated by integral histogram instead of gradient histogram features, and the experimental results showed that the method proposed improved the detection performance and detection accuracy of pedestrians.