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

Substation pointer instrument identification method based on improved YOLOV3 model

A recognition method and pointer technology, applied in the field of computer vision, can solve the problems of long training time, poor detection effect of multiple targets and small targets, and large hardware consumption, so as to improve real-time performance, improve detection and recognition effect, and improve accuracy. degree of effect

Active Publication Date: 2020-04-24
WUHAN UNIV OF SCI & TECH
View PDF8 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional YOLOV3 training takes too long, consumes a lot of hardware, and the detection effect on multi-target and small targets is not good.

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
  • Substation pointer instrument identification method based on improved YOLOV3 model
  • Substation pointer instrument identification method based on improved YOLOV3 model
  • Substation pointer instrument identification method based on improved YOLOV3 model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] A detailed description will be given below with reference to the accompanying drawings and the technical solutions in the embodiments of the present invention.

[0054] like figure 1 The overall flow chart of the substation pointer meter identification method based on the improved YOLOV3 model is shown in the overall flow chart, including creating a data set, clustering, constructing a new frame network, and using the new loss function to train the network for training, and finally get the results quickly.

[0055] The present invention is based on the Anaconda Prompt console environment under the 64-bit system of Windows 10 and the 3.6 version of python. All the auxiliary functions in the scheme and the original YOLOV3 structure are based on the 2.2.1 version of the keras framework, and the activation functions and machine learning algorithms belong to the keras callable library functions.

[0056] The method of the present invention specifically comprises the followi...

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 substation pointer instrument identification method based on an improved YOLOV3 model, and the method comprises the following steps: firstly collecting an instrument image, making a data set, and carrying out the calibration; then, clustering the bounding box through a Mini Batch Kmeans algorithm to find an optimal clustering coordinate; modifying a framework network DarkNet-53 of the basic YOLOV3 into a lightweight network MobileNet, and accelerating a training process by virtue of a better activation function; modifying a loss function of coordinate prediction to enable the model to better fit instrument data; and finally, enabling the trained model to be better applied to the detection and identification task of the substation inspection robot, and a small-target instrument panel and a multi-target instrument panel can be quickly and accurately obtained for subsequent processing in the detection process. On the premise that the accuracy is guaranteed, the detection speed is increased, the real-time performance is enhanced, and the detection effect on small targets and multiple instrument panels is greatly improved.

Description

technical field [0001] The invention relates to the field of computer vision and the technical field of target detection, in particular to a detection and identification method of a pointer-type instrument in an unattended substation. Background technique [0002] The pointer meter has the characteristics of low manufacturing cost, wide industrial application, simple structure, high precision and easy maintenance, etc. It is widely used in scientific research and large-scale industrial production testing. These precision instruments require periodic calibration to maintain the high accuracy of the instrument. In the past, the traditional method of pointer instrument panel detection is to observe the position through the human eye, and this method may cause errors or even errors due to personal reasons and environmental reasons, causing great losses to the company. First of all, there are differences between the eyes of different people, and the resolution of the human eye i...

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): G06K9/00G06K9/62
CPCG06V20/10G06V2201/02G06F18/23213G06F18/214Y04S10/50
Inventor 吴怀宇刘家乐陈洋李想成
Owner WUHAN UNIV OF SCI & TECH
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