Title :
A region segmentation and region labeling algorithm in aerial images about bridge over water
Author :
Dong, Yinwen ; Yuan, Bingcheng ; Shi, Zhaoming ; An, Jingxin ; Zhu, Minglei
Author_Institution :
College of Electronic Engineering, Naval University of Engineering, Wuhan, China
Abstract :
Aiming at region segmentation and region labeling for bridge recognition in aerial images, a region segmentation algorithm based on gradient mean square variance is proposed. The noises are removed by using binary pixel density method in water area segmentation. And a new region labeling for connective area algorithm based on pixel in binary image is put forward. 6 neighborhood connection rule is used to label connective areas in the binary image, and connective areas are all labeled by only one scan. Experiments show it is effective for water region segmentation and labeling and can be applied in bridge recognition automatically.
Keywords :
bridge recognition; mean square variance; pixel density; region labeling; region segmentation;
Conference_Titel :
Image and Signal Processing (CISP), 2012 5th International Congress on
Conference_Location :
Chongqing, Sichuan, China
Print_ISBN :
978-1-4673-0965-3
DOI :
10.1109/CISP.2012.6469670