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

Ore scale measurement method based on deep learning and application system

A technology of deep learning and measurement methods, applied in measurement devices, optical devices, image data processing, etc., can solve problems such as low accuracy, low overlap, low contrast, etc., to improve efficiency and accuracy, and enhance detection capabilities. , the effect of improving the accuracy

Inactive Publication Date: 2019-10-29
合肥合工安驰智能科技有限公司
View PDF8 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are many problems in the ore segmentation algorithm. Most of the methods are only for the ore image with low ore accumulation and overlap, high contrast between the ore and the background, and better imaging quality.
For ore images with low signal-to-noise ratio, low contrast and serious ore accumulation, the existing segmentation methods cannot effectively segment them correctly
The mineral processing site is in a complex environment such as high dust and high pollution, and the signal-to-noise ratio of the image is low. Using traditional image processing algorithms, these existing noises will directly affect the result of ore segmentation
[0004] In summary, there are a lot of manual operations in the traditional ore size detection, and the detection method based on the traditional segmentation algorithm has technical problems such as low accuracy and inability to segment stacked ore

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
  • Ore scale measurement method based on deep learning and application system
  • Ore scale measurement method based on deep learning and application system
  • Ore scale measurement method based on deep learning and application system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0084] refer to Figure 1-2 , a method of ore scale measurement based on deep learning, including:

[0085] S1. Obtain the image of the ore block, and convert the frame of the video into a picture according to a certain time interval;

[0086] S2. Preprocessing the ore block image into a marked image, dividing the processed marked image into a training sample and a test sample;

[0087] S3. Excluding abnormal marked image data;

[0088] S4, using the processed training samples to train the preset RetinaNet target recognition network;

[0089] S5. Input the test sample to the target recognition network to obtain a target recognition result and calculate the ore size.

[0090] refer to image 3 , the step of obtaining the ore block image in the step S1 includes:

[0091] S11, installing a camera at a position where the vertical distance above the belt is h, the focal length of the camera is f, and the camera can be installed at multiple angles to achieve multi-directional m...

Embodiment 2

[0131] refer to Figure 8-9 , a deep learning-based ore scale measurement application system based on embodiment 1, comprising: a video acquisition system, a detection and recognition system, a business system and a background production management system; the video acquisition system collects belt images through a camera, and passes the images The queue is sent to the detection and identification system; the detection and identification system receives the video frames collected by the video acquisition system, and the trained RetinaNet target recognition network outputs the size of the ore block, and notifies the business of the ore block of abnormal size through the message queue system, the detection and identification system is connected with the video acquisition system 11; the business system provides functions such as operator interface, real-time status monitoring and log management, and the business system is connected with the detection and recognition system; the ba...

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 an ore scale measurement method based on deep learning and an application system. The method comprises the following steps: obtaining an ore block image; image preprocessing: processing the implemented ore block image into a marked image, and dividing the marked image subjected to processing into training sample boxes and test samples; removing the abnormal marked image data; training a preset RetinaNet target recognition network by using the processed training sample; inputting the test sample to a target identification network to obtain a target identification result,and calculating the size of the ore; the invention discloses an ore scale measurement method based on deep learning and an application system. The RetinaNet target recognition network is trained by adopting a labeled ore image sample; the trained network model is obtained to be used for classifying and positioning the ore blocks, the real sizes of the ore blocks are calculated, complex features do not need to be extracted manually, the detection efficiency is high, and the problem that efficiency is low in traditional ore scale measurement is solved.

Description

technical field [0001] The invention relates to the technical field of ore size image detection, in particular to an ore size measurement method and application system based on deep learning. Background technique [0002] Non-ferrous metals are an important part of contemporary energy, information technology and modern materials, and an important foundation for the development of modern social economy and high technology. At present, the scale of mining and dressing of non-ferrous metal mines in my country is small, and the degree of automation and informatization is low, resulting in low utilization rate of mineral resources, serious energy consumption in the production process, resulting in a large waste of mineral resources, and also makes mining enterprises lack Sufficient international competitiveness. Most of the ores mined by mines are lean ores containing a large amount of gangue, except for a few rich in useful ores. For the metallurgical industry, due to the low c...

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): G06T7/60G01B11/00G06K9/62G06F9/54
CPCG06T7/60G01B11/00G06F9/546G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/30184G06F2209/548G06F18/241
Inventor 段章领金柳颀刘邵凡
Owner 合肥合工安驰智能科技有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com