Fast hyperspectral outlier detection method based on coarse localization and collaborative representation

Abstract

The invention discloses a hyperspectral abnormal point rapid detection method based on rough positioning and cooperative representation. First, the input hyperspectral remote sensing image is degraded in space; then the degraded image is compared with the original image, and the rough positioning Outliers: use coarsely located outliers to guide the collaborative representation between spatial dimension pixels, and use all the current background point pixels between the inner and outer windows for collaborative representation by setting the appropriate size of the inner and outer windows to reconstruct the central point image The final spatial anomaly response map is obtained by measuring the difference between the reconstruction center point pixel and the actual pixel; finally, the threshold is set, and the abnormal points are detected according to the spatial anomaly response map to obtain the final anomaly and background Detection map. The invention solves the problem of low detection accuracy of the hyperspectral remote sensing image anomaly detection method existing in the prior art while reducing the computational complexity.

Description

technical field [0001] The invention belongs to the technical field of remote sensing images, and in particular relates to a rapid hyperspectral abnormal point detection method based on rough positioning and cooperative representation. Background technique [0002] In the 1980s, with the rapid development of remote sensing technology, hyperspectral image technology has received widespread attention, and has gradually become an important research direction in the field of remote sensing science. Hyperspectral images are often defined as spectral images with a spectral resolution in the range of 10 nanometers, with hundreds or even thousands of bands. The spectral imager mounted on different space platforms records the target area with hundreds of continuous spectra, so that the hyperspectral image can not only obtain the spatial information of the imaged object, but also obtain the spectral information of the object, and obtain a three-dimensional The cube data of , where tw...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a hyperspectral anomaly detection method based on rough positioning and collaborative representation, which solves the problems of low efficiency and low detection accuracy of hyperspectral remote sensing image anomaly detection methods in the prior art

Images