Abstract
Aiming at the change detection of water resources via remote sensing, the non-subsampling contour transformation method combining a log-vari model and the Stractural Similarity of Variogram (VSSIM) model, namely log-vari and VSSIM based non-subsampled contourlet transform (L-V-NSCT) approach, is proposed. Firstly, a differential image construction method based on non-subsampled contourlet transform (NSCT) texture analysis is designed to extract the low-frequency and high-frequency texture features of the objects in the images. Secondly, the texture features of rivers, lakes and other objects in the images are accurately classified. Finally, the change detection results of regions of interest are extracted and evaluated. In this experiment, the L-V-NSCT approach is compared with other methods with the results showing the effectiveness of this method. The change in Dongting Lake is also analyzed, which can be used as a reference for relevant administrative departments.
Highlights
With improvement in the level of software and hardware for remote sensing acquisition along with the increase in the quantity of data, the need for change detection is increasing, and the requirements for precision are getting higher and higher
To dynamically monitor the changes of inland surface resources such as Ocean Lake wetlands and lake swamps, this paper proposes an L-V-non-subsampled contourlet transform (NSCT) approach based on the NSCT and the logarithmic variation function
To verify the effectiveness of the L-V-NSCT method proposed in this paper, we used real datasets to conduct experiments and analyze the results
Summary
With improvement in the level of software and hardware for remote sensing acquisition along with the increase in the quantity of data, the need for change detection is increasing, and the requirements for precision are getting higher and higher. In lake water area change detection, remote sensing technology is used to monitor lake area change. In the remote sensing of water resources, Xu et al [1] used the NDWI model to extract the water bodies of the Tangjiashan barrier lake from the multisource satellite images to detect the changes in the barrier lake, pre- and post-earthquake. Zhao et al [3], by combining ecological quantity analysis with GIS technology based on land use data and remote sensing imagery, analyzed the changes in land use and land cover as well as the driving force in the mainstream of the Tarim River from 1973 to 2005. Sun et al [8] used Cosmo-Skymed ScanSAR mode (HH) data for one-year monitoring of seasonal changes in the water surface areas of Poyang Lake from January 2014 to December 2014. On the basis of the GF-2 image, the method regularly provided the relevant departments with test results and reference
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call