Unlock instant, AI-driven research and patent intelligence for your innovation.

A Miner Behavior Recognition Method Based on Sensor and Skeleton Information

A recognition method and sensor technology, applied in the field of miner behavior recognition, can solve problems such as inaccurate skeleton information, achieve the effect of improving accuracy, overcoming accuracy decline, and more robust recognition results

Active Publication Date: 2022-06-28
TAIYUAN UNIV OF TECH
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When this method is applied to miners in a coal mine environment, the skeleton information may be inaccurate due to environmental influences. The patent application number CN201910633168.9 uses only skeleton information for behavior recognition

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
  • A Miner Behavior Recognition Method Based on Sensor and Skeleton Information
  • A Miner Behavior Recognition Method Based on Sensor and Skeleton Information
  • A Miner Behavior Recognition Method Based on Sensor and Skeleton Information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] like Figure 1 to Figure 3 As shown, the present invention is a miner behavior recognition method based on sensors and skeleton information, which solves the problem that the existing method is accurate by using a miner behavior recognition method based on three-axis acceleration sensor and skeleton information and using a CNN-LSTM hybrid network to extract features and recognize behavior. The rate is affected by factors such as illumination and occlusion, and the real-time performance cannot meet the shortcomings.

[0039] A method for recognizing miner behavior based on sensor and skeleton information of the present invention includes the following steps:

[0040] Step 1: Data acquisition: the motion information of the worker during the movement is collected by the sensor, the skeleton information at the same time of the worker's movement is collected by the depth camera, the motion information and the skeleton information are sent to the microcontroller, and the micr...

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 miner behavior recognition method based on sensors and skeleton information, which belongs to the technical field of miner behavior recognition; the technical problem to be solved is: provide an improvement of a miner behavior recognition method based on sensors and skeleton information; solve the above technical problems using The technical solution is: the acceleration information of the sensors worn by the miners' legs and waist and the skeleton coordinate information are fused to generate a motion information matrix, and the behavior recognition is realized through the CNN‑LSTM combined neural network. Combined to improve the accuracy of behavior recognition; the invention is applied to coal mines.

Description

technical field [0001] The invention relates to a miner behavior identification method based on sensor and skeleton information, and belongs to the technical field of miner behavior identification methods. Background technique [0002] my country is a big country in coal production and consumption. With the improvement of the mechanization and intelligence of domestic coal mines, the safety of coal mine production has been improved, but coal mine accidents still occur from time to time. According to statistics and analysis, most coal mine accidents are caused by miners' irregularities. Therefore, accurate and efficient monitoring and identification of miners' behavior is very important to reduce the incidence of coal mine accidents and ensure the safety of enterprise property. [0003] In the prior art, the recognition of human behavior includes many methods, among which the deep learning method based on RGB images and the deep learning method based on skeleton information ...

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 Patents(China)
IPC IPC(8): G06V40/10G06V40/20G06K9/62G06N3/04G06V10/774G06V10/82
CPCG06V40/10G06V40/20G06N3/044G06N3/045G06F18/214
Inventor 乔铁柱陈宝全
Owner TAIYUAN UNIV OF TECH