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

Intelligent monitoring system for workshop operation safety

An intelligent monitoring system and safety technology, applied in the direction of instruments, biological neural network models, character and pattern recognition, etc., can solve the problem of single safety monitoring system for workshop operations, and achieve the effect of enhancing real-time performance

Pending Publication Date: 2021-05-07
DONGHUA UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is that the existing workshop operation safety monitoring system is aimed at a single behavior, but this paper considers two operation specification scenarios

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
  • Intelligent monitoring system for workshop operation safety
  • Intelligent monitoring system for workshop operation safety
  • Intelligent monitoring system for workshop operation safety

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0027]A intelligent monitoring system for safe operation safety, whose system is constitutedfigure 1As shown, including the following modules:

[0028]Module 1): Based on the body's key point detection module of lightweight OpenPOSE;

[0029]Module 2): Based on YOLOV3 security cap detection module;

[0030]Module 3): Man and safety cap matching module based on the intersection ratio;

[0031]Module 4): Matching modules based on joints and regional locations.

[0032]Among them, module 1) uses three consecutive volume of 1 * 1, 3 * 3, 7 * 7-size convolved nuclear instead of 7 * 7 volumes, and the void convolution is adopted in the 3 * 3 volume. 1) Use Mobile Net as a skeleton network; module 1) use depth separable operation.

[0033]Module 2) Implementation of YOLOV3 network; the YOLOV3 network involved in the module 2 uses multi-scale features to target predictions.

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 intelligent monitoring system for workshop operation safety. The intelligent monitoring system is characterized by comprising a human body key point detection module based on lightweight openpose, a safety helmet detection module based on YOLOv3, a human and safety helmet matching module based on intersection-union ratio and a dangerous area detection module based on joint and area position matching. Modules included in the system are rich in function, and each module is built by a lightweight model, so that the universal monitoring requirements among workshops can be met, and a guarantee is provided for the safe production of the workshops.

Description

Technical field[0001]The present invention relates to an intelligent monitoring system for a safe operation safety, belonging to machine learning, depth learning, image processing, and system integration.Background technique[0002]With the advancement of manufacturing automation and intelligent transformation upgrades, more and more automation equipment and industrial intelligent robots participate in workshop production operations, and gradually replaced some workshop workers, playing more than modern production Important role. Although the number of workshop workers has decreased in fact, this does not mean that robots can significantly and even replace human in workshop operations in the short term.[0003]At this stage, most types of automation robots can only perform jobs in accordance with pre-arranged instructions, such as palletizing robots, welding robots, and so on. These robots are generally in need of large, monotonic, mechanical, repetitive demand or feature, which can be ...

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): G06K9/00G06K9/46G06K9/62G06N3/04
CPCG06V40/10G06V10/44G06N3/045G06F18/22
Inventor 鲍劲松许开州王佳铖郑小虎王燕华
Owner DONGHUA UNIV