Title :
Dense Corresponding Pixel Matching Between Aerial Epipolar Images Using an RGB-Belief Propagation Algorithm
Author :
Teng Hu ; Bingxuan Guo ; Huayi Wu ; Jianya Gong ; Tong Zhang
Author_Institution :
State Key Lab. of Inf. Eng. in Surveying, Mapping, & Remote Sensing, Wuhan Univ., Wuhan, China
Abstract :
A new algorithm, RGB-belief propagation (RGBBP), for dense corresponding pixel matching between aerial epipolar images is proposed in this letter. Evolved from the traditional belief-propagation algorithm, RGB-BP makes full use of all the three color components, R, G, and B, and simplifies the parameter settings. In order to reduce the impact of the obvious color differences between corresponding pixels, RGB-BP reduces the sensitivity of central pixels and increases the contribution of neighboring pixels. Three pairs of aerial epipolar images are tested using RGB-BP. The experimental results demonstrate the effectiveness of RGB-BP.
Keywords :
Markov processes; belief networks; geophysical image processing; image colour analysis; image matching; photogrammetry; RGB color components; RGB-BP; RGB-belief propagation algorithm; aerial epipolar images; central pixel sensitivity reduction; color differences; dense corresponding pixel matching; parameter settings; Accuracy; Belief propagation; Buildings; Image color analysis; Reliability; Sun; Testing; Belief propagation (BP); Markov random field (MRF); RGB-belief propagation (RGB-BP); dense corresponding pixel matching;
Journal_Title :
Geoscience and Remote Sensing Letters, IEEE
DOI :
10.1109/LGRS.2012.2188880