The Study on Automatic Moving-Object Tracking Method by Tree Filtering and Raindrop Filtering in the Open Space

• Main Authors: Sing-Syong Su, 蘇信雄
• Other Authors: Thou-Ho (Chao-Ho) Chen
• Format: Others
• Language: zh-TW
• Published: 2008
• Online Access: http://ndltd.ncl.edu.tw/handle/06050303398385340895

碩士 === 國立高雄應用科技大學 === 電子與資訊工程研究所碩士班 === 96 === Detection and tracking moving objects in image sequences is a fundamental and crucial research topic. It has vast applications in many visual systems, e.g. video surveillance, traffic monitoring, moving objects detection, and video editing, etc. In this thesis, we aim at explore and implement a detection and tracking of object method in the open space. The system consists of four major blocks: (1)moving objects detection: An efficient and effective method based on background subtraction is adopted to detect moving objects. (2)Tree filtering: filterint out those tree from the detected moving objects. (3)Raindrop filtering: filterint out those raindrop from the detected moving objects. (4)moving objects tracking: Finally, we utilize a set of color vector features extracted from the detected moving objects to track moving object in the open space. We demonstrate our tracking system with real-life image sequences. Experimental results show that our algorithm is fair robust and effective.