Scholarlink

The existing rock mass joint monitoring methods are mainly based on manual identification, which has the problems of low detection efficiency and strong subjectivity. In order to solve this problem, this paper proposes a method of rock mass joint detection and segmentation based on YOLOv8.In this paper, 4057 surrounding rock joint images collected by the Equatorial Guinea project are trained and identified. The experimental results show that the optimized algorithm Box(P) and BOX(R) performance evaluation indicators reach 84.8% and 77.6%. It performs well in practical engineering applications and basically meets the needs of practical engineering.

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

Rapid Detection and Application of Surrounding Rock Joint Characteristics Based on YOLOv8

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Zicheng Li,
  • Jiannan Zhang,
  • Huixing Li,
  • Ping Zhou,
  • Cong Chen,
  • Jiefeng Zhang

摘要

The existing rock mass joint monitoring methods are mainly based on manual identification, which has the problems of low detection efficiency and strong subjectivity. In order to solve this problem, this paper proposes a method of rock mass joint detection and segmentation based on YOLOv8.In this paper, 4057 surrounding rock joint images collected by the Equatorial Guinea project are trained and identified. The experimental results show that the optimized algorithm Box(P) and BOX(R) performance evaluation indicators reach 84.8% and 77.6%. It performs well in practical engineering applications and basically meets the needs of practical engineering.