A Target Recognition Method for Hyperspectral Remote Sensing Images Based on Segmented Sparse Representation

Abstract

The invention discloses a hyperspectral remote sensing image target recognition method based on segmented sparse representation. Using the present invention can achieve good target detection effects in different scenarios. The present invention starts from the combination of local features through spectral segmentation, fully emphasizes and utilizes more stable local spectral features, and improves the target detection effect; utilizes the characteristics of sparse representation and dictionary learning self-adaptability, without the need for target and Any assumptions are made about the distribution of the background, which avoids the inaccuracy of modeling caused by too many a priori assumptions and manual features. The invention adopts the characteristic of local feature matching so that the pollution of a few bands will not seriously affect the overall feature matching result, and has a certain effect of resisting band pollution.

Description

technical field [0001] The invention relates to the technical fields of remote sensing image processing and computer vision, in particular to a hyperspectral image target detection method based on sparse representation and dictionary learning. Background technique [0002] Object detection and recognition is an important part of computer vision. Hyperspectral remote sensing uses the spatial information and spectral information of the target to finely identify the ground objects in the scene. It has been widely used in geological and mineral exploration, vegetation and water research, atmospheric science, marine science, urban planning, agriculture, national defense and military and other fields. increasingly widespread applications. The key to target detection is to use the prior knowledge of the target and the background to detect the target from the background. Theoretically, hyperspectral remote sensing images contain two-dimensional spatial distribution information of ...

AI Technical Summary

Problems solved by technology

First, the traditional methods based on statistical theory often require a strong prior distribution assumption of the target and background, but the actual situation is complex and changeable and it is difficult to accurately model it

There are many factors that affect spectral changes, including light intensity and angle, atmospheric transmission, geometric shape of the object itself, changes in physical properties of surface materials, etc., and it is often difficult for models to take these factors into account in an accurate and detailed manner.

Second, most of the traditional methods start directly from the original spectral curves, lacking the mining of more robust spectral features

Spectral variability makes the spectral curve of the same surface feature fluctuate to a certain extent, and the existing methods are often sensitive to such fluctuations. In the final analysis, the original spectral features are less robust.

Third, common phenomena such as cloud occlusion pollute the spectrum, which leads to severe performance degradation of existing methods

[0006] Aiming at the problems that the current target detection algorithm is sensitive to spectral variability and does not fully exploit spectral features, it is necessary to design a more robust target detection and recognition method, which can adaptively mine the features of the target and the background, and perform feature matching , complete the identification of the target

Images