Soil body strength identification method and system based on image analysis and machine learning
The invention discloses a soil body strength identification method and system based on image analysis and machine learning. The method comprises the following steps: acquiring a surface image and a spectral image of a soil body; identifying particles in the surface image to obtain the particle size...
Gespeichert in:
Hauptverfasser: | , , , , , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention discloses a soil body strength identification method and system based on image analysis and machine learning. The method comprises the following steps: acquiring a surface image and a spectral image of a soil body; identifying particles in the surface image to obtain the particle size of the particles, and determining the particle gradation of the soil body according to the particle size of the particles; obtaining an RGB mean value of the surface image, and determining the moisture content of the soil body according to the RGB mean value; identifying the spectral image to obtain mineral components and contents in the image; and determining the shear strength of the soil body according to the grain composition, the moisture content, the mineral composition and the content of the soil body and the trained strength identification model. And accurate identification of the shear strength of the soil body is realized.
本发明公开的一种基于图像分析与机器学习的土体强度识别方法及系统,包括:获取土体的表面图像和光谱图像;对表面图像中颗粒进行识别,获取颗粒粒径,根据颗粒粒径确定土体的颗粒 |
---|