24 April 2018 Crowd motion segmentation and behavior recognition fusing streak flow and collectiveness
Author Affiliations +
Abstract
Crowd motion segmentation and crowd behavior recognition are two hot issues in computer vision. A number of methods have been proposed to tackle these two problems. Among the methods, flow dynamics is utilized to model the crowd motion, with little consideration of collective property. Moreover, the traditional crowd behavior recognition methods treat the local feature and dynamic feature separately and overlook the interconnection of topological and dynamical heterogeneity in complex crowd processes. A crowd motion segmentation method and a crowd behavior recognition method are proposed based on streak flow and crowd collectiveness. The streak flow is adopted to reveal the dynamical property of crowd motion, and the collectiveness is incorporated to reveal the structure property. Experimental results show that the proposed methods improve the crowd motion segmentation accuracy and the crowd recognition rates compared with the state-of-the-art methods.
© 2018 Society of Photo-Optical Instrumentation Engineers (SPIE)
Mingliang Gao, Mingliang Gao, Jun Jiang, Jun Jiang, Jin Shen, Jin Shen, Guofeng Zou, Guofeng Zou, Guixia Fu, Guixia Fu, } "Crowd motion segmentation and behavior recognition fusing streak flow and collectiveness," Optical Engineering 57(4), 043109 (24 April 2018). https://doi.org/10.1117/1.OE.57.4.043109 . Submission: Received: 8 November 2017; Accepted: 3 April 2018
Received: 8 November 2017; Accepted: 3 April 2018; Published: 24 April 2018
JOURNAL ARTICLE
8 PAGES


SHARE
RELATED CONTENT


Back to Top