Earticle

초록

영어

In order to obtain a satisfactory performance of visual tracking and video surveillance in complex dynamic scenes without the supervision of qualified workers, an efficient visual detection and tracking method is proposed, which can realize target counting and surveillance, behavior analysis and abnormal detection. Multi-targets tracking method based on novel Bayesian tracking model can manage multimodal distributions without explicitly computing the association between tracked targets and detections. The proposed algorithm is compared with recent works, which shows that it is robust to erroneous, distorted and missing detections and it can be applied in security and management of access points.

목차

Abstract
 1. Introduction
 2. Moving Targets Detect and Statistical Method
  2.1. Building Moving Targets Templates
  2.2. Moving Targets Statistical
 3. Multiple Targets Tracking Model
  3.1. Particle filter tracking model
  3.2. Feature Selecting and Extracting
  3.3. Targets Area Prediction and Targets Tracking
 4. Security surveillance and abnormal action analysis
 5. Experiments
 6. Conclusions
 Acknowledgements
 References

키워드

저자

• Jie Su [ Harbin University of Science and Technology, Harbin, China, Harbin Engineering University, Harbin, China ]
• Gui-sheng Yin [ Harbin Engineering University, Harbin, China ]
• Chen Hailong [ Harbin University of Science and Technology, Harbin, China ]
• Luo Zhiyong [ Harbin University of Science and Technology, Harbin, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Multimedia and Ubiquitous Engineering

• 간기

  월간

• pISSN

  1975-0080

• 수록기간

  2008~2016

• 등재여부

  SCOPUS

• 십진분류

  KDC 505 DDC 605