Title :
Video segmentation using spatio-temporal information
Author :
Kim, Yong-Wan ; Ho, Yo-Sung
Author_Institution :
Kwangju Inst. of Sci. & Technol., South Korea
Abstract :
This paper presents a new segmentation algorithm that processes segmentation by combining spatial segmentation and motion information. This algorithm uses morphological filters and the watershed algorithm. The proposed segmentation algorithm consists of six parts: preprocessing, image simplification, feature extraction, decision, region merging and postprocessing. By combining spatial and temporal information intelligently, we can get visually meaningful segmentation results. Simulation results show the efficiency of the proposed technique
Keywords :
feature extraction; filtering theory; image segmentation; mathematical morphology; motion estimation; video coding; content based coding; decision; efficiency; feature extraction; image simplification; morphological filters; motion information; postprocessing; preprocessing; region merging; simulation results; spatio-temporal information; very low bit rate video coding; video segmentation algorithm; watershed algorithm; Change detection algorithms; Feature extraction; Filters; Image segmentation; Merging; Motion estimation; Multimedia databases; Object detection; Shape; Videoconference;
Conference_Titel :
TENCON '97. IEEE Region 10 Annual Conference. Speech and Image Technologies for Computing and Telecommunications., Proceedings of IEEE
Conference_Location :
Brisbane, Qld.
Print_ISBN :
0-7803-4365-4
DOI :
10.1109/TENCON.1997.648541
