Share Email Print

Optical Engineering

Unsupervised spatiotemporal segmentation algorithm for on-chip video systems
Author(s): Chi-Chou Kao; Chuen-Yau Chen; Yen-Tai Lai
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

An efficient moving-object segmentation algorithm suitable for implementing on a chip is proposed. The basic idea is to use simultaneously a novel spatial segmentation algorithm and an effective temporal algorithm based on the accumulative information technique to produce the video objects. First, the spatial and the temporal segmentation algorithms are used simultaneously to produce the edges and the region of a moving object, respectively. Then, we make use of the edges with the region to obtain the object. It is found that the number of time-consuming motion estimation computations can be reduced dramatically. Hence, the overall processing speed is significantly accelerated to meet the hardware implementation requirement. Finally, a postprocessing step is applied to the object to smooth the object boundary. Good performance of this algorithm is demonstrated by experimental results.

Paper Details

Date Published: 1 May 2006
PDF: 8 pages
Opt. Eng. 45(5) 057401 doi: 10.1117/1.2203369
Published in: Optical Engineering Volume 45, Issue 5
Show Author Affiliations
Chi-Chou Kao, National Pingtung Institute of Commerce (Taiwan)
Chuen-Yau Chen, National Pingtung Institute of Commerce (Taiwan)
Yen-Tai Lai, National Pingtung Institute of Commerce (Taiwan)

© SPIE. Terms of Use
Back to Top