Visual Persons Behavior Diary Generation Model based on Trajectories and Pose Estimation

2017 International Symposium on Application of Materials Science and Energy Materials

材料科学;能源学

Gang, Chen^1,2 ; Bin, Chen^2,3 ; Yuming, Liu^4 ; Hui, Li^4

Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu

610041, China^1

University of Chinese Academy of Sciences, Beijing

100049, China^2

Guangzhou Institute of Electric Technology, Chinese Academy of Science, Guangzhou

510070, China^3

Electronic Dispatch Control Center of Yunnan Power Grid Group Co. LTD, China^4

关键词: Appearance modeling;    Assignment algorithms;    Behavior patterns;    Context information;    Detection framework;    Linking algorithms;    Multi-person tracking;    Surveillance analysis;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/322/6/062020/pdf
DOI  :  10.1088/1757-899X/322/6/062020

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

The behavior pattern of persons was the important output of the surveillance analysis. This paper focus on the generation model of visual person behavior diary. The pipeline includes the person detection, tracking, and the person behavior classify. This paper adopts the deep convolutional neural model YOLO (You Only Look Once)V2 for person detection module. Multi person tracking was based on the detection framework. The Hungarian assignment algorithm was used to the matching. The person appearance model was integrated by HSV color model and Hash code model. The person object motion was estimated by the Kalman Filter. The multi objects were matching with exist tracklets through the appearance and motion location distance by the Hungarian assignment method. A long continuous trajectory for one person was get by the spatial-temporal continual linking algorithm. And the face recognition information was used to identify the trajectory. The trajectories with identification information can be used to generate the visual diary of person behavior based on the scene context information and person action estimation. The relevant modules are tested in public data sets and our own capture video sets. The test results show that the method can be used to generate the visual person behavior pattern diary with certain accuracy.