Name of the inventor: Shih-fu Chang
Segmenting, Tracking Semantic Video Objects:
The method and system comprises of a processor receiving an initial frame of video image data and a succeeding frame from the digital video information. An input device defines an object boundary in the initial frame of video image data. A display device displays the video image data. The processor partitions the initial frame of video image data into multiple regions based on substantially homogenous video features. The object boundary is tracked in the succeeding frames of the video image data.
Video Tracking System:
The system provides an innovative method for combining low level automatic region segmentation and tracking with an active method for defining and tracking video objects at a higher level.