Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Soil classification method based on hyperspectral computing imaging system

A technology of computing imaging and classification methods, applied in computing, computer components, color/spectral characteristic measurement, etc., to achieve high classification accuracy, improve classification accuracy, and fast training speed

Inactive Publication Date: 2019-06-28
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the spectral differences between different soil types are small, how to highlight the characteristic differences between different soil types and improve the classification accuracy is an urgent problem to be solved

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Soil classification method based on hyperspectral computing imaging system
  • Soil classification method based on hyperspectral computing imaging system
  • Soil classification method based on hyperspectral computing imaging system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The present invention will be described in detail below with reference to the accompanying drawings and embodiments.

[0026] The invention provides a soil classification method based on a hyperspectral computing imaging system, which uses the LCTF-based hyperspectral computing imaging system to collect compressed measurement values ​​of different soil types. LCTF is used to modulate the spectral dimension of the spectral image, and the spectral image under different channels can be obtained by adjusting the central wavelength of the LCTF. The spectral image filtered by LCTF is a multispectral image in a narrow band around the central wavelength. Soil hyperspectral images can be reconstructed by compressive sensing theory, and the spectral resolution of soil spectral images can be improved. Then, the 3D-CNN method is used to classify the soil types in the reconstructed hyperspectral image, which fully reflects the characteristics of soil spatial and spectral dimensions...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a soil classification method based on a hyperspectral computing imaging system, thereby realizing rapid and accurate classification of different types of soil. According to theinvention, soil classification is carried out by using an LCTF-based hyperspectral computing imaging system; a compressed measurement value of a soil image is measured and reconstruction of an original spectral image is performed by using acompressed sensing theory, thereby improving the spectral resolution of the soil spectral image; on the basis of a spectral difference theory, differences between different soil types are enhanced by using spectral differences between all soil samples and all soil types as input features; and then classification is carried out by using a 3D-CNN, and advantages of the spectral images are utilized by using soil spectral image space and spectral information. According to a feature dimensionality reduction algorithm, the original spectral information is kept to the greatest extent, the spectral dimension is reduced, the training efficiency is improved, the type features of the soil are highlighted, and the classification accuracy is improved.

Description

technical field [0001] The present invention relates to the technical field of soil classification, in particular to a soil classification method based on a hyperspectral computing imaging system, which uses a deep learning method to analyze the soil collected by a liquid crystal tunable filter (Liquid Crystal Tunable Filter, LCTF) hyperspectral computing imaging system. Samples are classified. Background technique [0002] Soil classification can distinguish soil types according to soil properties and characteristics. Soil classification plays an important role in soil resource evaluation and provides a scientific basis for improving soil fertility and promoting agricultural technology. Because different types of soils have different reflectance spectral features, soil classification can be performed using spectral techniques. Visible-near-infrared spectrometer has the advantage of being fast and effective, so it is widely used in soil classification. However, spectromete...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G01N21/25G06K9/62G06N3/04
Inventor 许廷发余越申子宜张宇寒王茜徐畅樊阿馨
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products