Method of quickly extracting rivers from remote sensing image

Abstract

The invention discloses a method for quickly extracting rivers based on seed point scanning, and relates to the technical field of multispectral remote sensing image processing. The method mainly solves the problem that the prior method cannot extract rivers quickly from a large-size remote sensing image. The method comprises the following steps: carrying out manual selection of original seed points and automatically dividing a river into two parts according to the different positions of the original seed points; and scanning the two parts from the original seed points, constantly updating the seed points and a scanning mode thereof according to the flow direction of the river, and carrying out the scanning till the river scanning is completed. During the scanning, if a branch of the river appears or the flow direction changes or the river is cut off by a bridge, subsequent seed points and scanning mode are determined through windowed searching. The method can extract rivers quickly from an image with the size exceeding 50 million pixels, and has the advantage of high precision; therefore, the method can be used for quick extraction of river areas, bridge detection and water target detection from a multispectral remote sensing image.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to target segmentation of multispectral remote sensing images, in particular to a method for quickly scanning and extracting rivers based on seed points. This method can be used for rapid extraction of rivers, bridge recognition and water target recognition in remote sensing images. Background technique [0002] The extraction of water area information is an essential basic step for geographic information surveying and mapping update, urban wetland protection, water resource investigation, flood disaster monitoring, water target identification, such as bridges and ships, and multi-sensor or multi-temporal remote sensing image registration. . As a part of the water body, the extraction of rivers has important research significance, and is the basis for calculating the concentration of suspended solids in rivers, calculating water depth, and detecting bridges and other importa...

AI Technical Summary

Problems solved by technology

The DEM data source required by this method is difficult to obtain, and the processing method is complicated, so it is difficult to be widely used

Takako et al. proposed an automatic extraction method for rivers in tropical rainforests in JERS-1SAR images, using spectral and spatial information to extract narrow rivers and wide rivers respectively. This method works well, but it is not suitable for dealing with very wide rivers. , for example, when the river width is greater than 20km, due to the low resolution of the JERS-1SAR image, the river no longer appears to be elongated

[0004] Traditional thresholding methods, such as iterative thresholding and maximum between-class variance thresholding, can be used to extract rivers. These methods are simple and fast, but there are many noise points in the extracted rivers, and the effect is not ideal.

At present, some scholars have proposed some methods that can extract rivers more accurately, such as the SAR image water area recognition method based on grayscale statistics and area coding proposed by Wang Guiting, patent application number 200810236455.8, but most of them are processing this method Some sizes are smaller and the number of pixels is less than 10 6 image, when the number of pixels is 10 6 When the order of magnitude is high, these methods consume a lot of time, averaging between 80s and 200s

If the number of image pixels is greater than 10 7 When the order of magnitude is greater, its time consumption will be greater, and it can no longer meet the requirements of real-time performance

Images