Target detection and tracking based on improved HOG-color feature fusion
Tianle Dai, Ziqiang Hao, Zhongyuan Wang, Weida Zhan, Yanfeng Tang · IOP Conference Series Materials Science and Engineering · 2020
Abstract In the process of constructing the target appearance model, the traditional HOG feature does not take into account the relationship between adjacent regions when the image is segmented in the feature extraction process, resulting in the regional aliasing effect, and the single feature is inefficient in target detection and tracking. An improved HOG-color feature fusion method for target detection and tracking is proposed. Firstly, HOG feature and color feature were extracted from the target samples respectively. During the HOG feature extraction process, trilinear interpolation was used to eliminate regional aliasing effect. Secondly, Bhattacharyya distance is used to select the HOG feature after interpolation, and the appropriate feature is selected as the HOG feature. Then combine the HOG feature after selection with the color feature; Finally, the filter is obtained by learning the kernel correlation filter, and the image is correlated detected with the filter, and the response output is obtained. The experimental results show that this method is superior to the traditional HOG-color feature fusion target detection and tracking method in both tracking speed and tracking efficiency.