A Pedestrian Tracking Method Based on Adaboost and Feature Fusion

2018 4th International Conference on Environmental Science and Material Application

生态环境科学;材料科学

Huang, Xueying^1

School of Automation, Wuhan University of Technology, Wuhan, China^1

关键词: Association matrix;    Exchange problems;    Foreground regions;    Gradient direction histograms;    Haar-like features;    Multi-feature fusion;    Multi-scale wavelet;    Pedestrian tracking;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/252/3/032137/pdf
DOI  :  10.1088/1755-1315/252/3/032137

来源: IOP

【 摘 要 】

In view of the existing time-consuming and identity exchange problems in the pedestrian tracking process. A multi feature fusion tracking method based on adaboost detection is proposed. Firstly, the multi-scale wavelet transform is used to extract the foreground regions of the moving target, and the Haar-like feature is used in the foreground region to detect human heads. Then the particle filter tracking algorithm is introduced by combining color and gradient direction histogram to track the detected heads. Finally, the pedestrians are tracked through the association matrix. The experimental results show that the proposed method has a good tracking result when there are the cross motion and short occlusion between the pedestrians.