Title :
Change Field: A New Change Measure for VHR Images
Author :
Leigang Huo ; Xiangchu Feng ; Chunlei Huo ; Zhixin Zhou ; Chunhong Pan
Author_Institution :
Sch. of Math. & Stat., Xidian Univ., Xi´an, China
Abstract :
Due to the complexity of very high resolution (VHR) images and the inaccurate correspondence, change feature extraction is the key difficulty of VHR image change detection. In this letter, change field is proposed to represent the complex changes between VHR images. Change field measures the complex changes based on the displacements and the compensated distance. Based on change field, a novel change detection approach is proposed, where the inter-class variability is improved and the changed class and the unchanged class can be separated effectively. Experiments demonstrate the effectiveness of the proposed approach.
Keywords :
feature extraction; image processing; VHR images; change detection approach; change feature extraction; change field; compensated distance; displacements; inter-class variability; very high resolution images; Feature extraction; Remote sensing; Robustness; Spatial resolution; Training; Vectors; Change detection; change field; progressive transductive classification; very high resolution (VHR) images;
Journal_Title :
Geoscience and Remote Sensing Letters, IEEE
DOI :
10.1109/LGRS.2014.2310202