원문정보
보안공학연구지원센터(IJSIA)
International Journal of Security and Its Applications
Vol.9 No.2
2015.02
pp.21-28
피인용수 : 0건 (자료제공 : 네이버학술정보)
초록
영어
The bandwidth of kernel function is invariance in Mean-Shift tracking process which led to the problem of actual process of tracking failure. To solve this question a method is proposed to combine object contour, RGB color histogram and Mean-Shift tracking algorithm. In each frame the contour and color feature of target object are extracted to as a model. Meanwhile the size of contour is used as the bandwidth for kernel function in the next frame. Based on this Method the accuracy of Mean-Shift tracking is improved and the error of Mean-Shift tracking is reduced.
목차
Abstract
1. Introduction
2. The Improvement of Overall Scheme
3. Establish the Mathematical Model of Tracked Target
4. Target Tracking Algorithm of Mean-Shift based on the Variable of Kernel Function Window for Bilateral Filtering Detection
4.1. The Method for Determining the Bandwidth of Mean-Shift Kernel Function based on Bilateral Edge Detection Filtering
4.2. The Target Tracking of Mean-Shift Algorithm
4.3. Similarity Metric Coefficient between Tracked Target and Candidate Target
4.4. Position the Tracked Target in Subsequent Frames
5. Experimental Result
6. Conclusions
Acknowledgements
References
1. Introduction
2. The Improvement of Overall Scheme
3. Establish the Mathematical Model of Tracked Target
4. Target Tracking Algorithm of Mean-Shift based on the Variable of Kernel Function Window for Bilateral Filtering Detection
4.1. The Method for Determining the Bandwidth of Mean-Shift Kernel Function based on Bilateral Edge Detection Filtering
4.2. The Target Tracking of Mean-Shift Algorithm
4.3. Similarity Metric Coefficient between Tracked Target and Candidate Target
4.4. Position the Tracked Target in Subsequent Frames
5. Experimental Result
6. Conclusions
Acknowledgements
References
저자정보
참고문헌
자료제공 : 네이버학술정보