Method for rapidly and accurately detecting edge line of high-resolution remote sensing image

Abstract

The invention relates to a high-resolution remote sensing image edge line rapid and accurate detection method, and belongs to the technical field of remote sensing image processing and information extraction. The method comprises the following steps: S1, image smoothing processing: performing smoothing processing on a high-resolution remote sensing image by using a simple linear iterative clustering algorithm, and eliminating the influence of image noise and a same-object different-spectrum phenomenon on image edge line detection; s2, image initial edge line detection: detecting the smooth image edge line by using a dual-threshold edge line tracking algorithm to obtain an initial image edge line detection result; and S3, optimization processing of an image edge line detection result: optimizing the initial image edge line detection result by using a skeleton line extraction algorithm to obtain a smooth, continuous and single-pixel image edge line detection result with good image ground object boundary adhesion. The method can effectively overcome the influence of image noise and image same-object different-spectrum phenomena on image edge line detection, and obtains an accurate image edge line detection result.

Description

technical field [0001] The invention relates to a fast and accurate detection method for high-resolution remote sensing image edge lines, belonging to the technical field of remote sensing image processing and information extraction. Background technique [0002] With the development of Earth-to-Earth observation technology, the data acquisition of high-resolution remote sensing images is increasing, and they have been widely used in urban planning, disaster monitoring, agricultural management and military reconnaissance. As a key technology for automatic extraction, analysis and understanding of image information, high-resolution remote sensing image edge line detection plays an important role in image target detection, image segmentation and feature extraction. At present, traditional image edge line detection methods such as Sobel, Robert, Prewitt, Kirsch, Gauss-Laplace and Canny are usually used to process images to obtain image edge line detection results. However, tra...

AI Technical Summary

Problems solved by technology

[0003] Aiming at the problem of image edge line detection by high-resolution remote sensing image noise and homogeneous phenomenon, the present invention proposes a fast and accurate detection method for high-resolution remote sensing image fast edge line

Images