Line-scanning hyperspectral real-time anomaly detection method and system

Abstract

The invention discloses a line-scanning hyperspectral real-time anomaly detection method. Hyperspectral image data of a target object are obtained by an imaging spectrometer in a linear array push-broom manner; anomaly detection processing operation is performed on the obtained hyperspectral image data of the target object, and result data obtained after detection processing operation and original data are stored in a microcomputer; a discrimination threshold of anomaly information is determined, and the anomaly information is detected in real time in the push-broom imaging operation of the imaging spectrometer on the basis of the discrimination threshold of the anomaly information and is output; an anomaly condition thematic image is generated based on the output anomaly information. The method can solve the problem that the detection efficiency is reduced due to increased data size of a hyperspectral image, and realizes real-time anomaly detection of push-broom hyperspectral remote sensing images. The invention further discloses a line-scanning hyperspectral real-time anomaly detection system.

Description

technical field [0001] The invention relates to the technical field of remote sensing, in particular to a line scanning hyperspectral real-time anomaly detection method and system. Background technique [0002] At present, in the existing technology, hyperspectral images have the characteristics of map-spectrum integration, that is, the spatial information and spectral information of the target can be observed at the same time, which provides an effective remote sensing technical means for target classification and identification. However, hyperspectral also has the remarkable characteristics of complex images and massive data, which makes the process of hyperspectral image processing long and complicated, and it is difficult to meet the needs of special industries for real-time or quasi-real-time processing of hyperspectral data. Research institutions at home and abroad have done a lot of research on high-speed real-time processing technology for spectral data, such as the ...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is how to provide a line scanning hyperspectral real-time anomaly detection method and system, which can solve the key problem in current hyperspectral remote sensing that the target cannot be detected in real time due to the large number of bands and the large amount of data calculation

Images