Forewarning Algorithm of Crane Collision With Transmission Lines Based on Feature Fusion and Random Forest

ZHAO Qinghang; WANG Xin; ZHENG Yihui; LI Lixue

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Forewarning Algorithm of Crane Collision With Transmission Lines Based on Feature Fusion and Random Forest

更新时间：2025-12-08

- Forewarning Algorithm of Crane Collision With Transmission Lines Based on Feature Fusion and Random Forest
- Vol. 46, Issue 2, Pages: 471-479(2020)
- 作者机构：
  
  上海交通大学电工与电子技术中心
- 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
ZHAO Qinghang, WANG Xin, ZHENG Yihui, et al. Forewarning Algorithm of Crane Collision With Transmission Lines Based on Feature Fusion and Random Forest[J]. 2020, 46(2): 471-479.
DOI：

ZHAO Qinghang, WANG Xin, ZHENG Yihui, et al. Forewarning Algorithm of Crane Collision With Transmission Lines Based on Feature Fusion and Random Forest[J]. 2020, 46(2): 471-479. DOI：

摘要

现有的输电线路防外力破坏技术无法自动识别目标

导致对吊车碰线的监测效果较差。因此

该文提出了1种基于特征融合与随机森林的预警算法来解决这一问题。该算法在分析吊车自身特点的基础上设计了"形状–纹理–颜色"的融合特征提取方式:首先采用改进的边缘直线检测方法提取吊臂形状特征

然后利用局部二值模式（local binary pattern

LBP）算子获取纹理特征

最后在两步量化后的色调饱和值（Hue

Saturation

Value

HSV）颜色空间内得到颜色特征。进行融合特征后采用随机森林分类器进行目标识别

当判定目标为吊车时

根据其姿态和距离参数发出不同等级的预警信息。实验结果表明:该算法对工程吊车的平均识别准确率达到90.6%

相比于3种单一特征提取方式分别提升17.3%、7.9%和12.6%。同时该算法具备较强的实时处理能力

适用于输电线路防外力破坏的智能监控场合。

Abstract

Lack of automatic target recognition in existing transmission line protection technology causes poor performance on crane collision monitoring. Therefore

we propose a forewarning algorithm based on feature fusion and random forest to solve this problem. By analyzing the unique characteristics of the cranes

we design a ―Shape-Texture-Color‖ fusion feature extraction method. By the method

firstly

the shape features of the arm are extracted by using improved edge line detection method; secondly

the texture features are extracted by using the LBP operator; thirdly

the color features in the two-step quantified HSV color space are extracted. After extracting the fusion features

the target will be identified by the random forest classifier. If the target is identified as a crane

a danger level will be generated according to the parameters of posture and distance. The experimental results show that the recognition accuracy of this algorithm on the crane image library averages 90.6%

increased by 17.3%

7.9% and 12.6% compared to those by a single feature extracting method

respectively. Meanwhile

this algorithm is capable of real-time processing when it is applied to intelligent video surveillance system of the transmission lines.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Electric Equipment Image Recognition Based on Deep Learning and Random Forest

Real-time State Assessment of 10 kV Distribution Transformer Under Severe Weather Based on Multi-source Data Fusion

Prediction for Low-voltage Trip of Distribution Transformer Based on Generative Adversarial Network and Random Forest Algorithm

Related Author

LI Junfeng

WANG Qinruo

LI Min

SHI Yajun

GU Jie

LI Nan

WANG Chunyi

MOU Hong

Related Institution

School of Automation, Guangdong University of Technology

School of Mathematics and Computer,Wuhan Textile University

Research Center for Big Data Engineering and Technologies, School of Electronic Information and Electrical Engineering,Shanghai Jiaotong University

State Grid Shandong Electric Power Company

State Grid Shandong Electric Power Company Linyi Power Supply Company

AI问答

⁰