基于点云特征提取的电力刀闸三维状态识别方法研究
DOI:
作者:
作者单位:

1.中国南方电网有限责任公司超高压输电公司南宁监控中心;2.华雁智能科技(集团)股份有限公司;3.华南理工大学

作者简介:

通讯作者:

中图分类号:

基金项目:

成都市重大科技创新项目(2019-YU08-0067-GG)


Research on 3D State Recognition Method of Power Switch Based on Point Cloud Feature Extraction
Author:
Affiliation:

1.Nanning Monitoring Center of China Southern Power Grid Co., Ltd. EHV Transmission Company;2.Huayan Intelligent Technology (Group) Co., Ltd;3.South China University of Technology

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    电力刀闸是电力系统基本组成部件,系统运维时刀闸状态往往需要人工多次确认。本文提出了一种新的刀闸状态识别方法。该方法将输入的三维刀闸图像转换为彩色点云数据,并从彩色点云数据中提取场景特征。然后,利用现有的方向直方图颜色特征描述算法,基于局部纹理和形状信息构建识别特征的描述符。给定提取的特征描述符,执行两阶段匹配过程以找到场景和目标的彩色点云模型之间的对应关系。其次,使用霍夫投票算法过滤对应集中的匹配误差,并估计刀闸的初始三维姿态。最后,姿态估计阶段采用随机样本一致性和假设验证算法来改进初始姿态,并过滤带有错误假设的不良估计结果。实验结果表明,该方法不仅能成功识别复杂电力场景中的刀闸部件,而且能准确估计目标的三维姿态信息。

    Abstract:

    The power switch is a basic component of the power system, and the status of the switch during system operation and maintenance often needs to be manually confirmed multiple times. This paper proposes a new method for recognizing the state of the knife switch. This method converts the input 3D knife gate image into color point cloud data, and extracts scene features from the color point cloud data. Then, using the existing direction histogram color feature description algorithm, based on the local texture and shape information, the descriptor of the recognition feature is constructed. Given the extracted feature descriptors, a two-stage matching process is performed to find the correspondence between the scene and the target's color point cloud model. Secondly, the Hough voting algorithm is used to filter the matching errors in the corresponding set, and the initial three-dimensional posture of the knife gate is estimated. Finally, in the pose estimation stage, random sample consistency and hypothesis verification algorithms are used to improve the initial pose and filter out bad estimation results with incorrect assumptions. The experimental results show that the method can not only successfully identify the switch parts in complex power scenes, but also accurately

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-06-09
  • 最后修改日期:2021-07-20
  • 录用日期:2021-09-11
  • 在线发布日期:
  • 出版日期: