Abstract
The motion track is an important feature to show the spatio-temporal relationship of a video object. In this thesis, we propose a novel motion track representation based on MPEG-7 motion descriptor. A new descriptor is proposed to represent the motion track in the X-Y plane and the trend of velocity changes. We use the 1st/ 2nd/ 3rd order polynomials to model the trajectory of moving objects and use the associated coefficients as their features. Moreover, a new similarity measure for comparing two motion tracks based on the motion trajectory and velocity differences is proposed. The trajectory is compared by the properties of the polynomials such as the peaks and tangent lines, and the velocity is compared by the different trends such as speeding up and speeding down. Furthermore, the motion track segmentation method is proposed to handle a complicated motion behavior. The indexing and matching algorithm are also considered and the relevance feedback is used to improve the query results. The experiments show the query processing is efficient and the precision is near 85%, which is higher than other approaches.