Abstract
To solve the spatial optimization of sampling sites in the process of remote sensing image classification, a data refinement method of sampling sites for remote sensing data was proposed in this study. Firstly, uniformity factor and uniformity curve were constructed to detect the uniformity of sampling sites in geographical space. According to the uniformity degree, the sampling sites were divided into uniform samples, aggregate samples and sparse samples. Secondly, the aggregate samples were deleted, and the sparse samples were matched in adjacent mode and separated mode. The sparse regions were supplemented, and the sampling layout was optimized by iterative sampling space optimization process. Finally, the sampling space optimization effects were evaluated based on the uniformity curve of sampling sites. The results showed that there were two aggregate samples and three sparse samples, and the uniformity factor was -1.70, -1.63, 0.99, 1.03, 1.15, respectively, and there were no aggregate samples and sparse samples after data refinement. The method developed in this study can realize the uniform and unbiased samples in geographical space and feature space, and provide theoretical support for the selection of sampling sites for remote sensing data.
Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
