AN ASSESSMENT METHOD FOR OPTIMAL SEGMENTATION SCALE OF
REMOTE SENSING IMAGE BASED ON SIMILARITY BETWEEN OBJECTS
1)Institute of Geological Engineering and Surveying, Chang’an University, Xi’an 710054
2)The Department of Information Engineering, University of Armed Police Forces of Engineering, Xi’an 710086
Abstract:on objects was presented. Firstly, typical objects are determined as reference objects by field mapping and visual interpretation.Then the assessment function and the optimal segmentation scale can be obtained through caliculating the gray similarity and the shape similarity between reference and segmentation objects. The validity and applicability of the method is verified by practical treatment of World View2 multispectral images based on this assessment function.
$author.xingMing_EN,$author.xingMing_EN,$author.xingMing_EN. AN ASSESSMENT METHOD FOR OPTIMAL SEGMENTATION SCALE OF
REMOTE SENSING IMAGE BASED ON SIMILARITY BETWEEN OBJECTS[J]. jgg, 2013, 33(6): 137-140.