원문정보
보안공학연구지원센터(IJSIP)
International Journal of Signal Processing, Image Processing and Pattern Recognition
vol.2 no.4
2009.12
pp.13-28
피인용수 : 0건 (자료제공 : 네이버학술정보)
초록
영어
Automatic video segmentation plays an important role in real-time MPEG-4 encoding systems. This paper presents a video segmentation algorithm for MPEG-4 camera system with change detection, background registration techniques and real time adaptive threshold techniques. This algorithm can give satisfying segmentation results with low computation load. Besides, it has shadow cancellation mode, which can deal with light changing effect and shadow effect. Furthermore, this algorithm also implemented real time adaptive threshold techniques by which the parameters can be decided automatically.
목차
Abstract
1. Introduction
2. Baseline mode
3. Shadow Cancellation Mode
3.1 Proposed Shadow Cancellation Algorithm:
4. Adaptive Threshold Mode
4.1 Threshold in Non ROC
4.2 Thresholding in ROC
5. Experimental Results
5.1. Objective Evaluation
5.2. Subjective Evaluation
6. Conclusion
References
1. Introduction
2. Baseline mode
3. Shadow Cancellation Mode
3.1 Proposed Shadow Cancellation Algorithm:
4. Adaptive Threshold Mode
4.1 Threshold in Non ROC
4.2 Thresholding in ROC
5. Experimental Results
5.1. Objective Evaluation
5.2. Subjective Evaluation
6. Conclusion
References
키워드
저자정보
참고문헌
자료제공 : 네이버학술정보