What is it about?
Change detection technique can be applied to detect the land cover changes that have occurred in the investigated area by using remote sensing images acquired in the same geographical area at two different dates . It has been proved that three change categories may occur in a changed pixel; however, Change Vector Analysis (CVA) or Spectral Angle Mapper (SAM) alone can only detect two of the three change categories properly. Hence, we propose a novel approach integrating the advantages of them to acquire a better change map.
Featured Image
Why is it important?
Unlike classical methods, this approach acquires two difference images through CVA and SAM and then yields a novel difference image by fusing them in coefficients domains of discrete wavelet transform. This novel difference image integrates the advantages of CVA and SAM when they are employed to describe the difference in multitemporal multispectral images.
Perspectives
The typical CVA, using the magnitude of the spectral vector, ignores the influence of spectral angle, which is utilized in SAM. Theoretical analysis on the performance of CVA and SAM when they are used for change detection in multitemporal multispectral images indicates that (1) three change categories may occur in a changed pixel; (2) CVA or SAM alone can only detect two of the three change categories properly. Combining CVA and SAM can fully exploit the information of spectral vector so that it is feasible to detect all three change categories in change detection of multitemporal multispectral images.
Huifu Zhuang
China University of Mining and Technology
Read the Original
This page is a summary of: An approach based on discrete wavelet transform to unsupervised change detection in multispectral images, International Journal of Remote Sensing, May 2017, Taylor & Francis,
DOI: 10.1080/01431161.2017.1331475.
You can read the full text:
Contributors
The following have contributed to this page
