10 November 2007 A knowledge-based segmentation technology for remote sensing optical images
Author Affiliations +
Proceedings Volume 6795, Second International Conference on Space Information Technology; 679547 (2007) https://doi.org/10.1117/12.774558
Event: Second International Conference on Spatial Information Technology, 2007, Wuhan, China
Abstract
In this paper, we propose a whole scheme of remote sensing image segmentation process, from fast detection to accurate edge location. As we know, more structure information is acquired in high resolution remote sensing images. However, traditional image processing algorithms will produce meaningless results without priori knowledge. We aim at solving the problem in which regions may be distinguishable in intensity but belong to the same target by the ground truth. This is done by multi-threshold segmentation. What's more, In order to get a more regular shape, we use random field model to introduce spatial constraint at a small scale, and active contour model to smooth the whole edge at a larger scale. Simulation results demonstrate the effectiveness of our method in extracting ships from the satellite images. This paper also introduces the potential of integrating the image segmentation and subsequent image analysis tasks.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiao Yuan, Xiao Yuan, Hongwen Yang, Hongwen Yang, } "A knowledge-based segmentation technology for remote sensing optical images", Proc. SPIE 6795, Second International Conference on Space Information Technology, 679547 (10 November 2007); doi: 10.1117/12.774558; https://doi.org/10.1117/12.774558
PROCEEDINGS
5 PAGES


SHARE
Back to Top