Method and system for extracting typical region in satellite remote sensing image

Abstract

The invention discloses a method and system for extracting a typical area in a satellite remote sensing image, and belongs to the field of agricultural engineering, and the method comprises the following steps: S101, obtaining a to-be-detected image with a lake or a planting area through a satellite remote sensing device, and converting the to-be-detected image into a to-be-detected frame sequence according to the shooting time sequence; S103, extracting a frame from the to-be-detected frame sequence, and converting the frame into a grayscale image as a current frame. The problems of long time consumption and low efficiency when similar satellite remote sensing images are manually processed on a large scale by using professional image processing software in traditional agricultural engineering are solved; the detection probability of a designated area is improved, the error rate is reduced, and the method can be better adapted to a computer to quickly process remote sensing image detection tasks on a large scale; and the method can be better adapted to the automatic contour detection task of different satellites, different remote sensing devices, different seasons, different lakes or planting areas.

Description

technical field [0001] The invention relates to the technical field of agricultural engineering, in particular to a method and system for extracting typical regions in satellite remote sensing images. Background technique [0002] In agricultural engineering, it is often necessary to process the contours of lakes or large or larger planting areas obtained based on satellite remote sensing images. The traditional contour extraction method is to obtain satellite remote sensing images, import images in PNG or JPG format into professional tools such as Photoshop, and obtain their edge points manually. The traditional method is suitable for small-batch satellite remote sensing image processing, which can obtain appropriate boundaries manually, and can add, delete or adjust edge points appropriately, but in large-scale remote sensing images, this method is time-consuming and laborious, and the efficiency is extremely low . In the method of automatically obtaining the outline of ...

AI Technical Summary

Problems solved by technology

Under this method, all the edge points in the remote sensing image are generally extracted, including roads, residential areas, etc. It is difficult to directly obtain the outline of the target area, and even the edge points cannot form an effective connected area, and subsequent manual processing is still required. It is very inconvenient to deal with remote sensing image processing on a large scale

In addition, satellite remote sensing images are significantly affected by satellite orbits, seasons, light, ground lakes or the status of planted crops, and traditional automatic processing methods cannot be effectively applied to a wide range

Images