Hyperspectral image anomaly detection system based on FPGA (Field Programmable Gata Array)

Abstract

The invention relates to a hyperspectral image anomaly detection system based on an FPGA (Field Programmable Gate Array). The hyperspectral image anomaly detection system comprises a data input module, a covariance matrix solving module, a generalized inverse solving module and a result solving module; the data input module is used for equalizing window matrix data; the output end of the data input module is connected with the input end of the covariance matrix solving module; the output end of the covariance matrix solving module is connected with the input end of the generalized inverse solving module; the generalized inverse solving module is used for solving the generalized inverse of a covariance matrix; and the output end of the generalized inverse solving module is connected with the input end of the result calculating module. By adopting the hyperspectral image anomaly detection system based on the FPGA, the high-speed real-time processing of hyperspectral image data can be realized, hardware can be updated as requirement, and thus the requirement of high performance can be realized.

Description

technical field [0001] The invention relates to an FPGA-based hyperspectral image anomaly detection system. Background technique [0002] Although hyperspectral remote sensing images perform well in terms of number of bands and resolution, their huge data volume and extremely high data rate pose a great obstacle to time-sensitive data processing. To solve this problem, researchers have proposed many new methods. High-efficiency data processing method to process hyperspectral images. [0003] The rapid development of hyperspectral remote sensing technology has led to a massive increase in remote sensing image data. The data processing central station located on the earth's ground cannot process the explosively growing remote sensing image data in a timely manner, which seriously hinders the effective and full utilization of massive valuable data. [0004] Moreover, due to the limitation of the bandwidth of the transmission link, hyperspectral remote sensing images need to be...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the problem that the computing efficiency of the PC cannot meet the real-time requirements when performing abnormal detection processing on hyperspectral images, and propose a hyperspectral image processing implementation device based on FPGA

Images