OBJECT INFORMATION EXTRACTION AND SIMILARITY MEASURE METHOD FOR OBJECT TRACKING IN EMBEDDED SYSTEMS
Hyun-Ki Ryu, Minchul Kim · 한국멀티미디어학회 국제학술대회 · 2007
This paper proposes a color relationship feature vector that can precisely track objects in occlusive and disocclusive situations. Reliable color relationship feature vector extraction is inevitable for event detection and the precise tracking of objects. Not only in terms of size and ratio but also the color relationship feature vector proposed in this paper are used to track the improved object. The proposed tracking method had an outstanding performance using to count any weakness of the vector. As a result of the experimental images, the proposed method allows for precise trajectory tracking even in cases of the occlusive and disocclusive situations of multi-objects.