سال انتشار: ۱۳۸۳
محل انتشار: دوازدهیمن کنفرانس مهندسی برق ایران
تعداد صفحات: ۶
Alireza Tavakkoli – Sharif University of Technology
Shohreh Kasaei – Sharif University of Technology
Gholamreza Amayeh – Sharif University of Technology
In this paper, a very fast, noise robust and accurate video object plane (VOP) extraction algorithm based on wavelet transform andwatershed segmentationtechniques is proposed. The proposed algorithm firstly, applies the wavelet transform on incoming frames and uses the approximation coefficient matrix of the first level through out the algorithm. This not only increases the speed of the algorithm but also reduces the camera noise. The proposed method subsequently uses a prediction method to apply the watershed algorithm on those areas of the sub-image that might contain a moving object. This prediction stage increases the speed of the segmentation process efficiently. The experimental results show the superiority of the proposed algorithm when compared with other available schemes.