Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Automatic shooting system for soil body grading image

An automatic shooting and grading technology, applied in character and pattern recognition, computer parts, computing, etc., can solve the problems of lack of sample database, difficulty in improving the accuracy of machine learning models, lack of image sample library, etc., to achieve a wide range of applications, The effect of easy operation

Pending Publication Date: 2022-03-01
BEIJING JIAOTONG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The bottleneck problem in the development of image-based soil grading recognition models: the lack of sample databases, that is, the lack of a large number of image sample libraries with known gradation curves
[0008] Insufficient data makes it difficult to improve the accuracy of machine learning models

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
  • Automatic shooting system for soil body grading image
  • Automatic shooting system for soil body grading image
  • Automatic shooting system for soil body grading image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] refer to Figure 1-Figure 3 , illustrate the embodiment of the present invention:

[0036] The present invention: an automatic shooting system for soil gradation images, comprising a camera system (7), a mixing drum (1) and a fixed support (10):

[0037] The mixing drum (1) and the camera connecting rod (4) are fixed on the fixed support (10), and the side wall of the fixed bearing (10) has a pipeline communicated with the camera connecting rod (4); the mixing drum (1 ) The inner rotating shaft (3) is a hollow rod, and the camera connecting rod (4) is inserted into the inner rotating shaft (3). The fan blade (5) is connected to the rotating shaft (3);

[0038] The mixing drum (1) is fixed on the fixed support (10) through the fixed anti-rotation connecting rod (6). A feeding port (2) is provided on the side wall of the mixing drum (1);

[0039] Light and camera (7) are at the head of connecting rod (4). There is a small gap between the rotating shaft (3) and the wa...

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 relates to an automatic shooting device for massive soil gradation images for machine learning sample collection. The automatic shooting device comprises a shooting system, a roller and a fixed support, a connecting rod connected with a camera system is arranged on the side wall of the fixed support, and two supports are arranged on the fixed support to support the roller. A shooting device is arranged in the hollow rotating shaft of the roller; a test soil sample enters the device through a feeding hole. After soil samples are filled, the soil samples can be uniformly mixed by rotating the rotating shaft handle, and grading photos are shot by the shooting system after each time of uniform mixing; and different photos with the same grading can be obtained by repeatedly shooting for multiple times. Soil materials can be added through the feeding port, so that the gradation of the soil samples is changed, and then pictures of the soil materials of different gradation are taken. The device is simple in structure and convenient to operate, and soil sample grading and photographing can be rapidly adjusted. The method can be used for quickly shooting pictures of different graded soil samples, so that a massive image database containing the different graded soil samples is formed. The database is a basis for constructing a soil gradation image recognition model based on machine learning.

Description

technical field [0001] The design of the invention belongs to the field of geotechnical engineering. Background technique [0002] Image-based soil gradation recognition models are in great demand in fields such as fill engineering and tunneling engineering. The bottleneck problem in the development of image-based soil gradation recognition models: the lack of sample databases, that is, the lack of a large number of image sample libraries with known gradation curves. Aiming at this bottleneck problem, the present invention designs a system capable of rapidly collecting soil sample gradation and images. [0003] By utilizing the invention, image databases of soil bodies with different particle gradations can be obtained quickly and conveniently. Each sample in the database is a photo of a soil sample with a known gradation curve, that is, the soil gradation information corresponds to the photo one-to-one. The establishment of this database can solve the sample problem in m...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06V10/147
Inventor 李旭罗鸣吉浩泽李茂彪王玉杰赵宇飞武雷杰姚敏原继东刘欢
Owner BEIJING JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products