| Summary: | 碩士 === 朝陽科技大學 === 資訊工程系 === 104 === Object tracking is an important function of video surveillance system. For the same object in a multi-camera environment, how to assign the same label to the same object is so-called consistent labeling. In this study, a consistent labeling method is proposed for the PTZ (Pan-Tilt-Zoom) camera. That is, the same object is assigned the same label while the FOV (Field-of-View) of the PTZ camera is adjusted. In order to achieve the above goal, the proposed approach using several methods, such as temporal differencing, template matching, mean-shift tracking, Kalman filter, and so on. A template cache is designed for preserving the template of an object and a least recently used (LRU) replacement mechanism is used to update the cache. The experimental results show that accuracy of the proposed approach for the consistent labeling of a PTZ camera is about 83%.
|
|---|
