Support vector tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence(2004)
摘要
Support Vector Tracking (SVT) integrates the Support Vector Machine (SVM) classifier into an optic-flow-based tracker. Instead of minimizing an intensity difference function between successive frames, SVT maximizes the SVM classification score. To account for large motions between successive frames, we build pyramids from the support vectors and use a coarse-to-fine approach in the classification stage. We show results of using SVT for vehicle tracking in image sequences.
更多查看译文
关键词
successive frame,SVM classification score,Support Vector Machine,Support Vector Tracking,classification stage,coarse-to-fine approach,image sequence,intensity difference function,large motion,optic-flow-based tracker,support vector tracking
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络