Method and device for detecting artificial green targets

Abstract

The invention relates to a method and a device for detecting artificial green targets. The method comprises the following steps: acquiring hyperspectral image data of a to-be-detected scene, and preprocessing the hyperspectral image data; calculating a normalized difference vegetation index of each pixel according to the preprocessed hyperspectral image data, and screening pixels of which the normalized difference vegetation index is greater than a first preset value; and calculating a photochemical reflectance index of each pixel of which the normalized difference vegetation index is greater than the first preset value, and screening pixels of which the photochemical reflectance index is greater than a second preset value to serve as the artificial green targets. According to the method disclosed by the invention, a vegetation covered area is separated from a vegetation uncovered area by the normalized difference vegetation index, and real vegetations in the vegetation covered area are separated from the artificial green targets by the photochemical reflectance index, so that the artificial green targets are detected; and therefore, the existing problems of effectively detecting the artificial green targets with the 'isometric colors' as the real vegetations are solved.

Description

technical field [0001] The invention relates to the technical field of remote sensing detection, in particular to a detection method and device for an artificial green target. Background technique [0002] Camouflage refers to reducing or reducing the difference between the target and the background as much as possible in terms of color or geometric shape, increasing the similarity between the target and the background, and achieving the purpose of hiding the target or making it look like the real one, such as avoiding service in nature (chameleon), decorative fakes, etc. Flowers, fake grass, etc. At present, color camouflage is a kind of camouflage phenomenon that widely exists in nature and daily life. It is also the most common in public infrastructure, military and other fields, such as military green camouflage and fake lawn. Green material is an important artificial camouflage material. With the continuous development of detection methods, artificial camouflage not on...

AI Technical Summary

Problems solved by technology

from figure 1 It can be seen from the figure that the reflection spectrum curves of the artificial green target and the real vegetation are very similar, especially in the visible-near-infrared range (400-1000nm). There is a vegetation red edge effect in the band range, and vegetation reflection shoulders appear in the 800-950nm band range. These four artificial green targets and five real vegetation have almost reached the "same color and same spectrum", and it is difficult to use traditional techniques such as spectral matching. distinguish

Images