Object-based video data representations enable unprecedented functionalitie
s of content access and manipulation. In this paper, we present an integrat
ed approach using region-based analysis for semantic video object segmentat
ion and retrieval. We first present an active system that combines low-leve
l region segmentation with user inputs for defining and tracking semantic v
ideo objects. The proposed technique is novel in using an integrated featur
e fusion framework for tracking and segmentation at both region and object
levels. Experimental results and extensive performance evaluation show exce
llent results compared to existing systems. Building upon the segmentation
framework, we then present a unique region-based query system for semantic
video object. The model facilitates powerful object search, such as spatio-
temporal similarity searching at multiple levels.