Method for improving accuracy in extraction of lake surface area by low-space-resolution remote sensing image

Abstract

The invention discloses a method for improving accuracy in extraction of lake surface area by low-space-resolution remote sensing images. The method includes the steps: collecting multi-time-phase low-space-resolution remote sensing images of an area where a lake is located, and extracting lake surface area; collecting high-space-resolution remote sensing images similar to the low-space-resolution images in acquiring data as many as possible, and selecting a water body recognition method to extract lake surface area; analyzing lake surface area extracted by two same-time-phase remote sensing images, judging whether a relation between two lake surface areas needs to be segmented or not, if yes, calculating parameters according to area data in each segment, and if not, calculating parameters according to all area data; establishing a correction formula for segmentation according to the parameters acquired by calculation; for lake surface area extracted by low-space-resolution images of other time phases, judging the segment in which the lake surface area is positioned, and correcting the lake surface area according to the corresponding correction formula. By the method, accuracy in extraction of the lake surface area by the low-space-resolution remote sensing images can be improved effectively.

Description

technical field [0001] The invention relates to the field of lake area extraction based on remote sensing images, in particular to a method for improving the lake area extracted from low spatial resolution remote sensing images. Background technique [0002] How to improve the accuracy of lake area based on remote sensing images has always been an important topic in the field of remote sensing information extraction. At present, there are two main types of remote sensing monitoring of lakes: one is the direct extraction of lake-related information based on high-resolution SPOT, TM or ASTER data; the other is based on low-resolution data such as AVHRR, MODIS and other data combined with related algorithms to extract target information. In contrast, the use of low-resolution AVHRR, MODIS, etc. has great advantages in terms of time resolution, coverage, and cost, so it is widely used in large-scale lake area monitoring. However, due to the low spatial resolution, the accuracy...

AI Technical Summary

Problems solved by technology

However, due to the low spatial resolution, the accuracy of lake area extracted from low-resolution remote sensing images is generally low, and some existing extraction methods have not fully considered the advantages of using other high-resolution remote sensing images. The extraction results are difficult to accurately reflect the current situation of the lake area and its changing process

Images