Data Augmentation Method for Disconnecting Switch Images and Its Application in Automatic State Recognition

LIU Ziquan; WANG Huifang; GUAN Minyuan; HUANG Xiaoming; WU Guoqiang; WANG Di

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Data Augmentation Method for Disconnecting Switch Images and Its Application in Automatic State Recognition

更新时间：2025-12-08

- Data Augmentation Method for Disconnecting Switch Images and Its Application in Automatic State Recognition
- Vol. 46, Issue 2, Pages: 441-447(2020)
- 作者机构：
  
  1. 浙江大学电气工程学院
  2. 国网浙江省电力有限公司湖州供电公司
  3. 国网浙江省电力有限公司电力科学研究院
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published Online：29 February 2020，
  
  Published：2020
- 稿件说明：
移动端阅览
LIU Ziquan, WANG Huifang, GUAN Minyuan, et al. Data Augmentation Method for Disconnecting Switch Images and Its Application in Automatic State Recognition[J]. 2020, 46(2): 441-447.
DOI：

LIU Ziquan, WANG Huifang, GUAN Minyuan, et al. Data Augmentation Method for Disconnecting Switch Images and Its Application in Automatic State Recognition[J]. 2020, 46(2): 441-447. DOI：

摘要

针对隔离开关分合状态自动识别算法效果受到巡检图像训练样本限制的问题

提出了一种结合三维空间信息的隔离开关图像数据扩充方法。首先

通过隔离开关的二维图像

结合关于隔离开关三维形状的先验知识

求解隔离开关各关键点的三维坐标;然后

在三维空间中对隔离开关进行多次旋转变换

以模拟拍摄角度发生变化的情况;最后

通过透视投影变换将三维空间的隔离开关重新投影到二维平面

生成新的隔离开关图像数据

实现训练样本的扩充。算例结果表明

相比于平移、放缩、旋转、改变长宽比、改变亮度等传统图像数据扩充方法

所提出的隔离开关图像数据扩充方法对于隔离开关位置和分合状态识别效果有更显著的提升。

Abstract

To solve the problem that the algorithm effect of disconnecting switch state recognition is limited by training samples

an augmentation method of disconnecting switch images combined with three-dimensional spatial information is proposed. Firstly

through the two-dimensional images

along with the prior knowledge about the three-dimensional shapes of the disconnecting switches

the three-dimensional coordinates of the disconnecting switch key points are solved. Then

the disconnecting switches are rotated and transformed for several times in a three-dimensional space to simulate the change of shooting angles. Finally

the disconnecting switches in a three-dimensional space are projected to a two-dimensional plane by perspective projection transformation

in order to generate new images and augment training samples. The results of the case study show that

compared with the traditional image augmentation methods

such as translation

scaling

rotation

changing aspect ratios and changing brightness

the proposed image augmentation method can improve the position and state recognition effect of disconnecting switches more significantly.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Measurement Method and System for Transient Platform Potential Rise and Electromagnetic Disturbance of Ultra-high Voltage Series Compensation Device

Insulator String Positioning and State Recognition Method Based on Improved YOLOv3 Algorithm

Insulation Defect Detection Method for Disconnecting Switches Based on Time-frequency Analysis of 3D Electric Fields

Typical Fittings Detection Method with Faster R-CNN Combining KL Divergence and Shape Constraints

Early Warning of Lithium-ion Battery Fire Based on Image Recognition of Gas-liquid Escape

Related Author

YU Jinsong

LIU Huiwen

ZHANG Weidong

HU Rong

CUI Xiang

MA Qiyan

CHEN Jinxin

YAN Hongwen

Related Institution

Chinese Electric Power Research Institute

State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University

EPRI Science and Technology Co. Ltd.

School of Computer&Communication Engineering,Changsha University of Science&Technology

State Grid Shaanxi Electric Power Research Institute

AI问答

⁰