Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B7, 517-522, 2016
https://doi.org/10.5194/isprs-archives-XLI-B7-517-2016
© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.
 
21 Jun 2016
OBJECT-ORIENTED CHANGE DETECTION BASED ON MULTI-SCALE APPROACH
Yonghong Jia1, Mingting Zhou1, and Ye Jinshan2 1Institute of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
2Institute of Remote Sensing and Digital Earth,Beijing 100101, China
Keywords: Optimal scale; multi-scale; CART tree; object-oriented techniques Abstract. The change detection of remote sensing images means analysing the change information quantitatively and recognizing the change types of the surface coverage data in different time phases. With the appearance of high resolution remote sensing image, object-oriented change detection method arises at this historic moment. In this paper, we research multi-scale approach for high resolution images, which includes multi-scale segmentation, multi-scale feature selection and multi-scale classification. Experimental results show that this method has a stronger advantage than the traditional single-scale method of high resolution remote sensing image change detection.
Conference paper (PDF, 2126 KB)


Citation: Jia, Y., Zhou, M., and Jinshan, Y.: OBJECT-ORIENTED CHANGE DETECTION BASED ON MULTI-SCALE APPROACH, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B7, 517-522, https://doi.org/10.5194/isprs-archives-XLI-B7-517-2016, 2016.

BibTeX EndNote Reference Manager XML