Method for estimating abundance of hyperspectral image end member

Abstract

The invention discloses a method for estimating the abundance of a hyperspectral image end member. The method for estimating the abundance of the hyperspectral image end member comprises a first step of extracting the image end from an image and selecting mixed pixel points, conducting linear decomposition and obtaining a corresponding abundance value, a second step of evaluating a normalized spectral characteristic value which corresponds to the end member, a third step of tracing points under a rectangular coordinate system, a fourth step of conducting curve fitting and obtaining a quadratic curve expression, a fifth step of obtaining the abundance of the rest points by means of mapping the spectral characteristic value, and a sixth step of evaluating the root mean square error RMSE between an estimated value and an actual value and judging whether the RMSE meets the evaluated precision. According to the method for estimating the abundance of the hyperspectral image end member, an abundance value is rapidly predicted through establishment of certain relationship between the spectral feature value and the abundance of the end member, the defect that the corresponding abundance can be obtained when the liner decomposition is conducted on all mixed pixel points is overcome. In actual application process, due to the fact that the linear decomposition is conducted on only a small amount of pixel points which are evenly distributed, the abundance value which corresponds to end members of all pixel points can be obtained, and the time of decomposition of the pixel points can be effectively shortened.

Description

technical field [0001] The invention relates to a remote sensing image processing technology, in particular to a hyperspectral image endmember abundance estimation method. Background technique [0002] The number of bands of hyperspectral images obtained by remote sensing technology can reach dozens or even hundreds, so the amount of data is very large, which has advantages and disadvantages for its application field. Because it can bring not only rich ground object information, but also a lot of redundant information. Moreover, due to the mixing effect of remote sensing instruments and atmospheric transmission, mixed pixels commonly exist in images. Therefore, it is necessary to decompose the mixed pixel to obtain its basic components (ie, end members) and the proportion of these basic components (ie, abundance). [0003] At present, in the actual process, the acquisition of the corresponding abundance value of the end member in the hyperspectral image is realized by spec...

AI Technical Summary

Problems solved by technology

[0034] 4. Spectral information divergence

[0054] 6.2 Accuracy evaluation of unknown real data

[0061] From the calculation formula of the least squares method, it can be seen that whether it is an unconstrained or a constrained result, it needs to go through multiple operations of the matrix, and in order to make the result accurate, the fully constrained least squares method FCLS is generally used, and in this method The acquisition of the result requires multiple iterations of the matrix, which will undoubtedly make the acquisition of the endmember abundance value take too long, and cannot be used in occasions with strong real-time requirements.

Images