Title :
Landslide Detection Using a Local Similarity Measure
Author :
Khairunniza-Bejo, S. ; Petrou, Maria ; Ganas, Athanassios
Author_Institution :
CVSSP, Surrey Univ., Guildford
Abstract :
In this paper, a new simple method of landslide detection and identification is proposed. It is based on the use of local mutual information and image thresholding. A binary change image is then produced. Connected component analysis is used to identify the connected regions. Landslides are identified as the largest connected regions in this image. Mathematical morphology is used to approximate the landslide region. This method is simple and suitable for the detection of large changed regions with ratio of the unchanged to changed pixels in the image of the order of a few tens
Keywords :
image segmentation; mathematical morphology; connected component analysis; identification method; image thresholding; landslide detection; local similarity measure; mathematical morphology; Earth; Educational institutions; Electric variables measurement; Geologic measurements; Image registration; Mutual information; Remote monitoring; Terrain factors; Vegetation mapping; Working environment noise;
Conference_Titel :
Signal Processing Symposium, 2006. NORSIG 2006. Proceedings of the 7th Nordic
Conference_Location :
Rejkjavik
Print_ISBN :
1-4244-0412-6
Electronic_ISBN :
1-4244-0413-4
DOI :
10.1109/NORSIG.2006.275262
