Segmentation and Tracking of Human in Crowded Environments

Jun Feng Man; Hai Yu Lin; Qian Qian Li; Xiang Bing Wen

doi:10.4028/www.scientific.net/AMR.255-260.2281

Paper Titles

A Passive Third-Order Cascade PLL Filter
p.2262

Research on Exact Lower Bounding Segmentation of DTW Distance
p.2267

Affine Reconstruction Based on Parallel Plane and Infinity Point
p.2272

Research on Human Behavior Recognition in Video Surveillance
p.2276

Segmentation and Tracking of Human in Crowded Environments
p.2281

Plant Identification Based on Artificial Intelligence
p.2286

Robust Watermarking Algorithm Based on Hilbert-Huang Theory
p.2291

Some New Security Strategies Description about Grid
p.2296

Research on Pounding Response at Expansion Joint in the Linear Bridge and the Curved Bridge under Earthquake
p.2303

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 255-260Segmentation and Tracking of Human in Crowded...

Segmentation and Tracking of Human in Crowded Environments

Abstract:

The occlusion problem in crowded people environment makes human segmentation and tracking more difficult in video surveillance. Thus, a human segmentation method combing human model with body edge curve is presented. Because segmentation may result in serious defect and distortion, robust BP neural network model is adopted as tracking mode. For improving autonomous learning ability of BP network, Hierarchical Dirichlet Process (HDP) is used to decide whether new types of human body characteristic data is generated, which provides decision basis for BP network learning. The simulation experiments confirm that the method presented in this paper can effectively solve the problem of partial human body occlusion. Meanwhile, this method has unique advantage of simplicity and real-time over others.