Spatio-Temporal Video Search Using the. . .

Object-based video representation provides great promises for new search and editing functionalities. Feature regions in video sequences are automatically segmented, tracked, and grouped to form the basis for content-based video search and higher levels of abstraction. We present a new system for video object segmentation and tracking using feature fusion and region grouping. We also present efficient techniques for spatio-temporal video query based on the automatically segmented video objects. 1. Introduction New functionality of video applications, such as search and editing, require a flexible framework of video representation, which allows for content based access. We have proposed a hierarchical object-based video model for this purpose [8]. It facilitates efficient search at the low level of features as well as the high level of semantic abstraction. This model is also synergistic with the new video compression standard such as MPEG-4 [2]. The hierarchical object-based model co..