Anti-occlusion pedestrian tracking algorithm based on location prediction and deep feature rematch

• Published in: 高技术通讯（英文版） Vol. 26; no. 4; pp. 402 - 410
• Main Authors: Hu Zhentao, Mao Yihao, Fu Chunling, Liu Xianxing
• Format: Journal Article
• Language: English
• Published: College of Computer and Information Engineering, Henan University, Kaifeng 475004, P. R. China%School of Physics and Electronics, Henan University, Kaifeng 475004, P. R. China 01.12.2020
• Subjects: pedestrian tracking; deep feature; correlation filter; Kalman filter
• ISSN: 1006-6748
• DOI: 10.3772/j.issn.1006-6748.2020.04.007

Aiming to the problem of pedestrian tracking with frequent or long-term occlusion in complex scenes, an anti-occlusion pedestrian tracking algorithm based on location prediction and deep feature rematch is proposed. Firstly, the occlusion judgment is realized by extracting and utilizing deep fea-ture of pedestrian' s appearance, and then the scale adaptive kernelized correlation filter is intro-duced to implement pedestrian tracking without occlusion. Secondly, Karman filter is introduced to predict the location of occluded pedestrian position. Finally, the deep feature is used to the rematch of pedestrian in the reappearance process. Simulation experiment and analysis show that the pro-posed algorithm can effectively detect and rematch pedestrian under the condition of frequent or long-term occlusion.