Optical remote-sensing image, GIS automatic registration and water body extraction integrated method

Abstract

An optical remote-sensing image, GIS (Geographic Information System) automatic registration and water body extraction integrated method comprises the following steps: 1, segmenting input optical remote-sensing images to obtain initial segmentation results of water systems; 2, performing local level set evolution segmentation to obtain a set R; 3, matching basic geographic information water system layer vector objects with objects in the set R, registering the images, executing the step 4 if the registration is successful, otherwise, returning to the step 2; 4, obtaining unchanged water bodies, suspected newly-added water bodies and suspected changed water bodies through buffer detection, further filtering out suspected water body objects, and confirming real changed water bodies and unchanged water bodies; 5, taking the multispectral values of corresponding pixels in unchanged water body objects as positive samples, randomly selecting the multispectral values of pixels on the optical remote-sensing image except the area in the set R as negative samples, training an SVM (Support Vector Machine) classifier, verifying whether the objects in a filtered suspected water body object set are water bodies or not, and obtaining water body results of segmentation, registration and extraction.

Description

technical field [0001] The invention relates to heterogeneous data registration and water body extraction technology of optical images and vectors, and specifically relates to an integrated optical remote sensing image and GIS automatic registration and water body extraction method. Background technique [0002] Accurate acquisition of water body distribution information is of great significance for flood monitoring and disaster assessment, geographic information update, water resource investigation, comprehensive river basin management, water conservancy planning and other fields. Due to the characteristics of timeliness and economy, remote sensing has become one of the most extensive and effective means of extracting water bodies. [0003] The rapid development of high-resolution images in recent years has provided more and better data support for remote sensing information extraction, but it has also brought great challenges. Due to the widespread phenomenon of "same spe...

AI Technical Summary

Problems solved by technology

Although the above methods have achieved good extraction results in the experiment, there are still the following deficiencies in the face of practical application requirements: First, many methods have achieved good results for specific experimental data, and lack of various The universality of data processing; second, the parameters in the extraction method model need to be manually adjusted, or the model training samples need to be manually selected, which makes the automation of the extraction algorithm low; third, for the method of comprehensive analysis of multi-source data, its The premise assumption is that the multi-source data has been strictly registered, and the multi-source data faced in the actual processing process has differences in position and coordinate system, and it is necessary to manually select control points and perform geometric correction processing

[0005] To sum up, it can be seen that in the face of diverse representations of water bodies on remote sensing images and complex background interference, the existing water body extraction methods have problems such as poor universality and many manual interventions.

Images