A method for automatic extraction of water body information from remote sensing satellite multispectral images

Abstract

A method for automatic extraction of water body information from remote sensing satellite multispectral images is as follows: (1) extract the normalized water index from the apparent reflectance data of domestic remote sensing satellite multispectral images to form a normalized normalized water index image NDWI; (2) ) Perform global threshold segmentation based on the maximum inter-class variance algorithm on the normalized water index image to initially extract water body information; (3) perform local buffer expansion and threshold segmentation on the preliminary water body information to obtain a stable water body unit result set; ( 4) Obtain the slope and shadow information according to the elevation data and remove the shadow from the water body unit result set, and finally complete the water body information extraction. The invention adopts the method of computer automatic interpretation, utilizes the idea of ​​from global segmentation to local iterative segmentation, and extracts the normalized water body index in a streamlined manner, with high extraction precision and easy engineering.

Description

technical field [0001] The invention relates to a method for automatically extracting water body information from multispectral images of remote sensing satellites, which is suitable for extracting water body information from multispectral images of domestic remote sensing satellites without cloud coverage, and belongs to the field of remote sensing information processing Background technique [0002] With the development of the economy, the damage to the global environment is becoming more and more serious. The frequent occurrence of droughts, floods, and water pollution seriously affects people's lives, social and economic development, and social stability. The monitoring and evaluation of water resources, timely grasp of water resources information, and timely adoption of corresponding countermeasures play an important role in the rational planning and protection of water resources. [0003] The remote sensing monitoring of water body is mostly carried out through the cha...

AI Technical Summary

Problems solved by technology

[0007] In general, the above methods have the following disadvantages: (1) The method is relatively primitive and the extraction accuracy is low; (2) The extraction process requires auxiliary manual intervention, and even requires on-site measurement and manual sketching, which is time-consuming and laborious ; (3) Different calculation models and thresholds are required for different remote sensing satellite multispectral data, and the universality is low; (4) The extraction effect is poor for mountainous areas with shadow interference, and it is difficult to implement engineering applications

Images