Scholarlink

<p>During the process of laying the cable pipeline, there will be some foreign objects such as municipal waste and stones in the pipeline, which will affect the smooth laying of the cable and even result in serious consequences such as power failure and short circuit. However, most of the existing detection techniques are unable to stably and accurately detect foreign objects in pipelines.In this paper, a method of detecting foreign objects of cable pipeline based on stereo vision depth perception is proposed to ensure the quality and efficiency of cable concealed engineering acceptance.Firstly, a second-order semi-global stereo matching method is adopted to obtain a more robust disparity map. Secondly, color features and position features are extracted from the image to obtain different proposals. Then, the conditional random field is used to fuse the features to obtain the final saliency map to achieve accurate detection of foreign objects. On the basis of foreign objet detection results, combined with binocular stereo vision, the object size measurement is realized.The experimental results of the actual detection environment (110&#xa0;kV power transmission line) show that the algorithm in this paper can accurately detect the foreign object inside the pipeline and complete the accurate measurement of the foreign object size.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Foreign object detection of cable pipeline based on stereo vision

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月7日

查看全文
  • Ye Lu,
  • Qianxiang Meng,
  • Xingming Feng,
  • Yunpeng Cheng,
  • Zheng Xu,
  • Jingjing Bai

摘要

During the process of laying the cable pipeline, there will be some foreign objects such as municipal waste and stones in the pipeline, which will affect the smooth laying of the cable and even result in serious consequences such as power failure and short circuit. However, most of the existing detection techniques are unable to stably and accurately detect foreign objects in pipelines.In this paper, a method of detecting foreign objects of cable pipeline based on stereo vision depth perception is proposed to ensure the quality and efficiency of cable concealed engineering acceptance.Firstly, a second-order semi-global stereo matching method is adopted to obtain a more robust disparity map. Secondly, color features and position features are extracted from the image to obtain different proposals. Then, the conditional random field is used to fuse the features to obtain the final saliency map to achieve accurate detection of foreign objects. On the basis of foreign objet detection results, combined with binocular stereo vision, the object size measurement is realized.The experimental results of the actual detection environment (110 kV power transmission line) show that the algorithm in this paper can accurately detect the foreign object inside the pipeline and complete the accurate measurement of the foreign object size.