Title :
A Multilevel Contextual Approach to Change Detection for very high Resolution Images
Author :
Huo, Chunlei ; Chen, Keming ; Zhou, Zhixin ; Lu, Hanqing ; Cheng, Jian ; Liu, Qingshan
Author_Institution :
Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing
Abstract :
A multilevel contextual approach is proposed in this paper for change detection of VHR images. By representing the change features in a hierarchical contextual manner, the changes are detected level-by-level. By taking advantages of SVMs, the ambiguity of changes is mitigated and the optimal changes are detected peculiar to the specific user. Compared to the traditional methods, the proposed approach is more accurate, more robust and faster. Experiments demonstrate the effectiveness and advantages of the proposed approach.
Keywords :
geophysical signal processing; geophysical techniques; image processing; remote sensing; support vector machines; SVM; change detection; hierarchical context; multilevel contextual approach; support vector machine; very high resolution images; Context-aware services; Discrete wavelet transforms; Feature extraction; Image resolution; Laboratories; Multispectral imaging; Narrowband; Pattern recognition; Robustness; Spatial resolution; coarse-to-fine refinement; contextual change features; multilevel change detection; scale propagation;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2008. IGARSS 2008. IEEE International
Print_ISBN :
978-1-4244-2807-6
Electronic_ISBN :
978-1-4244-2808-3
DOI :
10.1109/IGARSS.2008.4779688
