Hyperspectral image target detection method based on sample mining and background reconstruction

Abstract

The invention discloses a hyperspectral image target detection method based on sample mining and background reconstruction, and mainly solves the problem of low target detection precision in the prior art. The method comprises the steps of performing coarse detection on an input hyperspectral image, and obtaining a training sample based on a coarse detection result; respectively constructing a generative adversarial network, a reverse auto-encoder network and an auto-encoder network, and respectively training the generative adversarial network, the reverse auto-encoder network and the auto-encoder network by using training samples; calculating a reconstruction error and a preliminary detection result of the autoencoder network for reconstructing the input hyperspectral image; obtaining an optimized hyperspectral image and a feature map according to the preliminary detection result, and further realizing second-stage sample mining, network training and target detection to obtain a second-stage detection result; and fusing the preliminary detection result and the second-stage detection result to obtain a final detection result. The method can make full use of background spectrum information, effectively inhibits background interference, improves the target detection precision, and can be used for environmental protection, mineral exploration, crop yield estimation and disaster prevention and relief.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a hyperspectral image target detection method, which can be used in environmental protection, mineral survey, crop yield estimation, disaster prevention and relief, and urban construction. Background technique [0002] Remote sensing technology was first produced in the 1960s, and then became a new interdisciplinary science and technology, which has developed rapidly. The spectral information in remote sensing images often characterizes the intrinsic characteristics of ground objects to a large extent, so the improvement of spectral resolution is helpful for the accurate identification and classification of ground objects. Since the 1980s, on the basis of multispectral remote sensing technology, its spectral resolution has been further enhanced, and hyperspectral remote sensing technology has emerged as the times require. Its spectral range covers from visibl...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to address the deficiencies of the above-mentioned prior art, and propose a hyperspectral image target detection method based on sample mining and background reconstruction to solve the existing The problem of low detection accuracy caused by insufficient utilization of background information of hyperspectral images, insufficient suppression of background interference and insufficient effective training samples

Images