The template update problem 论文
2004IEEE Transactions on Pattern Analysis and Machine Intelligence引用 762
Video Surveillance and Tracking MethodsAdvanced Image and Video Retrieval TechniquesVideo Analysis and Summarization
详细信息
- 发表期刊/会议
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 发表日期
- 2004-04-26
- 发表年份
- 2004
关键词
Video Surveillance and Tracking MethodsAdvanced Image and Video Retrieval TechniquesVideo Analysis and Summarization
摘要
Template tracking dates back to the 1981 Lucas-Kanade algorithm. One question that has received very little attention, however, is how to update the template so that it remains a good model of the tracked object. We propose a template update algorithm that avoids the "drifting" inherent in the naive algorithm.