Method for identifying hyperspectral material

Abstract

The invention provides a method for identifying a hyperspectral material. First a standard light source spectrum database is established, a spectral material standard database is established, and standard light source spectra are obtained through a difference method and a control variable method; spectral data information is shot for a material needing to be identified; through preprocessing and intrinsic material information extraction, spectral characteristics of the material are obtained, and then the spectral characteristics are matched with data in the spectral material standard database, so as to perform high-precision identification of the material. According to the method, the interference to spectral information of the material caused by complex factors such as different illumination conditions and material shape changes and the like can be resisted, the problems of metamerism and homogeneity and heterochrome which cannot be solved through conventional red green blue (RGB) and RGBD cameras are solved, and the identification precision rate is high.

Description

technical field [0001] The invention relates to the field of computational photography, in particular to a method for identifying the material of low-beam objects by using high-dimensional spectral information. Background technique [0002] In recent years, computational photography has become a hotspot in the research fields of computer vision, digital signal processing, graphics, depth intersection, etc. Material identification is also the focus of research work in recent years. Over the years, the methods and systems for material identification based on RGB color data have been increasingly perfected, most of which are based on characteristics such as chromaticity, brightness, and contour. And important depth information, and rich spectral information and depth information can often reveal many characteristics of objects and scene light, and can also make great progress in many fields of computer vision. [0003] In the field of remote sensing, hyperspectral technology h...

AI Technical Summary

Problems solved by technology

On the one hand, although RGB or RGBD information can be used to identify some materials with obvious contour and color characteristics, the RGB processing method cannot properly solve the typical "metamerism" problem and the problem of different colors of the same material.

On the other hand, the hyperspectral shooting data contains more details and reflects the chemical and physical characteristics of the material itself, but the data has poor anti-interference ability. Factors such as light intensity, light source, and angle will directly affect the spectral data, so the spectral data can be directly used Classification and identification often have problems such as poor marginality, discretization of classification and even misjudgment

Images