원문정보
보안공학연구지원센터(IJMUE)
International Journal of Multimedia and Ubiquitous Engineering
Vol.9 No.8
2014.08
pp.85-94
피인용수 : 0건 (자료제공 : 네이버학술정보)
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
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
저자정보
참고문헌
자료제공 : 네이버학술정보