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

Under-mine drilling machine drill rod counting method based on computer vision

A computer vision and counting method technology, applied in computer parts, computing, image data processing, etc., to reduce the cost of the mine, reduce the work flow, and improve the utilization of equipment.

Pending Publication Date: 2021-09-03
成都光束慧联科技有限公司
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The object of the present invention is to aim at the above-mentioned deficiencies in the prior art, to provide a kind of computer vision-based method for counting drill rods of an underground drilling rig, to solve or improve the above-mentioned problems

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
  • Under-mine drilling machine drill rod counting method based on computer vision
  • Under-mine drilling machine drill rod counting method based on computer vision
  • Under-mine drilling machine drill rod counting method based on computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] Embodiment one, refer to figure 1 , the computer vision-based method for counting drill rods of an underground drilling rig in this program specifically includes the following steps:

[0058] Step S1. Obtain the image data of the drill pipe, divide the image data of the drill pipe into two types of data, and use the two types of data as inputs for training the monitor network and training the re-identification network respectively;

[0059] Step S2, performing image enhancement processing on the two kinds of data;

[0060] Step S3, adding different proportions of Gaussian white noise to each cleaned image, simulating the influence caused by silicon dioxide and dust;

[0061] Step S4, after the sample picture is read, it is locked into a 416*416 image, the image includes three scales, and the image is cut into 13*13, 26*26, 52*52 areas respectively, and each area passes through Darknet;

[0062] Step S5, perform classification and regression tasks on whether the image ...

Embodiment 2

[0068] Embodiment two, refer to figure 1 , this embodiment will describe Embodiment 1 in detail;

[0069] This implementation scheme uses the camera covered in the underground coal mine as the image data source, runs the entire calculation process in the server room, and can realize the parallel processing structure of multiple algorithms for one camera, with the following functional characteristics:

[0070] First, through an effective data enhancement method, the reliability of low-quality image data caused by the dark underground working environment is greatly improved.

[0071] Second, by migrating the idea of ​​pedestrian re-identification, re-identify the drill pipes, and assign an independent and unique mark to each drill pipe, which is convenient for subsequent counting.

[0072] Due to the complex and changeable working environment under the mine, the picture is not clear in many cases, and a large number of flying catkins appear, which seriously affects the detector...

Embodiment 3

[0110] Embodiment three, this embodiment adopts specific case to illustrate;

[0111] 1. Collect 5,000 images of drill pipes in the mine, and the data enhancement methods are symmetrical inversion, center interception, rotation and grayscale transformation. The number of images after enhancement reaches the level of 50,000. 70% of them are used for the training set, 15% for the verification set, and the model that passes the verification will be tested on the remaining 15% of the test set.

[0112] 2. Intercept each drill pipe image in the data set to generate a classified data set. According to the angle of the drill pipe, the data is divided into 180 categories representing the state of the drill pipe from 0° to 179°. ResNet18 is used to train the classification dataset, 80% of which are used as training set and 20% are used as test set. Save the classification model as best_classify.pth.

[0113] 3. All images are re-converted to 416*416 pixels before being input into th...

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 under-mine drilling machine drill rod counting method based on computer vision, the method comprises the following steps: S1, acquiring drill rod image data, and dividing the drill rod image data into two types of data; s2, performing image enhancement processing on the two kinds of data; s3, adding Gaussian white noise of different proportions into each cleaned image; s4, locking the sample picture as a 416 * 416 image after being read in, wherein each image area passes through Darknet; s5, performing classification and regression tasks on the image candidate frame and the central point, width and height of the candidate frame, and modifying the output of the classification task to be 1; s6, monitoring the network to output a plurality of detection candidate frames by training a minimum loss function; s7, taking the test frame with the maximum confidence coefficient in the test frames as an input frame, sequentially calculating the IOU of the overlapped test frames, and when the calculated IOU value is greater than a set threshold value, filtering and repeating the step S7; and S8, carrying out tracking calculation on the monitored target by adopting image classification, a Kalman filtering algorithm and a Hungary algorithm.

Description

technical field [0001] The invention belongs to the technical field of downhole drilling rod counting, in particular to a method for counting drill rods of an underground drilling rig based on computer vision. Background technique [0002] Gas accidents such as gas explosions and outbursts are the biggest safety hazards in the production process of coal mines. At present, the most commonly used measure in coal mine production is gas drainage, that is, by drilling, using drill holes (or roadways), pipelines and vacuum pumps to pump the gas in the coal seam or mining area to the ground to ensure the safety of mine operations. [0003] As the first step of gas drainage, drilling needs to consider the drilling depth. Since the path of the drill bit in the coal seam is difficult to obtain, the drilling depth is generally calculated indirectly by calculating the number of drill pipes to meet the drilling depth design requirements. Drilling depth is directly related to the number ...

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): G06T7/00G06T5/00G06T7/11G06T7/246G06T7/277G06K9/62
CPCG06T7/0004G06T5/00G06T7/11G06T7/246G06T7/277G06F18/22G06F18/2415
Inventor 李映萱陈俊星闫启宏
Owner 成都光束慧联科技有限公司
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