SHIAE-2006 Project

In recent years, there has been rapidly growing interest in content-based functionalities of video data, such as video editing, content-based image retrieval, video indexing, video event analysis, etc. Video segmentation as a challenging and active research area is a key technique for semantic object extraction and plays an important role in digital video processing and computer vision. The task of segmenting/tracking a video object emerges in many applications, such as traffic monitoring, surveillance and video conferencing, etc.
 

§        To investigate the saliency model for extracting objects of interest from videos.

§        To develop novel automatic video object segmentation techniques for generic and specific (e.g., video surveillance, videoconferencing) applications based on saliency model.

§        To develop real time object segmentation techniques based on saliency model and fast transforms.