Cable inspection picture target detection method based on convolutional neural network

A convolutional neural network and target detection technology, which is applied in the field of target detection of cable inspection pictures based on convolutional neural network, can solve the problems of external environment background interference and other problems of the cable inspection picture target detection method, and achieve the effect of correct detection

Pending Publication Date: 2022-01-14
JIANGSU ELECTRIC POWER CO
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, most of the target detection methods for cable inspection pictures proposed in

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
  • Cable inspection picture target detection method based on convolutional neural network
  • Cable inspection picture target detection method based on convolutional neural network
  • Cable inspection picture target detection method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0036] The technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0037] A method of object detection in cable inspection pictures based on convolutional neural network, such as figure 1 shown, including the following steps:

[0038] Step 1: Obtain inspection pictures, establish classification categories for target detection, the classification categories include excavators (diggers), safety helmets (helmets) and construction enclosures (fences), and perform YOLO-TN based on the classification categories and YOLOv3 model construction;

[0039] Step 2: The completed model includes an input layer, a hidden layer, a succession layer, and an output layer, and then input a picture containing the classification category to the model;

[0040] Step 3: using the obtained pictures of the classified categories as training samples, using the initial weights and thresholds of the convolutional neural network, train...

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 relates to the technical field of power line communication, in particular to a cable inspection picture target detection method based on a convolutional neural network. The method comprises the following steps: 1, acquiring an inspection picture, and establishing a classification category of target detection; 2, inputting a picture containing the classification category into a model; 3, taking the obtained picture of the classification category as a training sample, training the network by using an initial weight and a threshold value of the convolutional neural network, and determining an optimal neural network structure; and 4, inputting a picture collected in real time into the convolutional neural network model trained in the step 3, and outputting a target graph detection result. According to the method, the convolutional neural network is used to detect the cable inspection picture target, the target detection model is introduced to determine the neural network structure and parameters with the optimal performance, the cable inspection picture target can be effectively detected, the calculation accuracy of the method can be uninfluenced by external environment background interference, and correct detection of the cable inspection picture target can be realized.

Description

technical field [0001] The invention relates to the technical field of power line communication, in particular to a method for detecting objects in cable inspection pictures based on a convolutional neural network. Background technique [0002] Cable inspection is generally divided into equipment inspection and channel inspection. Equipment inspection is mainly aimed at the identification of appearance changes and the measurement of electrical parameters for the main cable equipment and auxiliary facilities. Channel inspection is mainly to prevent external force damage to cable equipment caused by construction machinery on the ground above the underground cable channel. In the inspection pictures of the channel, if there are excavator-like mechanical equipment or construction enclosures and other objects, it often indicates that the drilling construction may cause serious damage to the nearby underground cable channel. Therefore, in the daily operation and maintenance of h...

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): G06F30/27G06F113/04G06F113/16G06K9/62G06N3/04G06N3/08G06V10/774G06V10/82
CPCG06F30/27G06N3/08G06F2113/04G06F2113/16G06N3/045G06F18/214
Inventor 孙鸣赫王东海周平陈伟姚天翼翟超超高源
Owner JIANGSU ELECTRIC POWER CO
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap