裂缝检测模型数据集的低监督快速标注算法
作者:
作者单位:

同济大学 土木工程学院,上海 200092

作者简介:

刘 超(1977—),男,副教授,工学博士,主要研究方向为桥梁智能监测。E-mail:lctj@tongji.edu.cn

通讯作者:

中图分类号:

TU375.1

基金项目:


Fast Labeling Algorithm of Crack Detection Dataset with Low Supervision
Author:
Affiliation:

College of Civil Engineering, Tongji University, Shanghai 200092, China

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:

    为解决裂缝检测深度学习模型训练时数据集标注效率低、成本高的现状,以及现有计算机标注算法对复杂环境适应性较弱的问题,基于计算机视觉与概率统计理论,提出低监督快速标注的概念,并以计算机标注和人工标注相融合的全新标注模式,形成了完整的裂缝检测模型数据集的快速标注算法。与人工逐像素标注相比,标注精度均为84%以上,且可节省至少85%的时间;与传统计算机标注方式相比,标注干涉和简单人工标注方式可以较好地处理复杂背景问题。经U?Net深度学习模型验证,测试集的平均交并比可达0.90。

    Abstract:

    Manual dataset labeling is always at the expense of low efficiency and high cost in the deep learning model training of crack detection. The adaptability of existing automatic labeling algorithms to complex environment is weak as well. Aiming at these problems, the concept of fast labeling with low supervision is proposed based on computer vision and the probability statistics theory. In addition, a novel fast labeling algorithm for crack dataset is formed, composed of computer labeling and manual labeling. Compared with manual pixel-by-pixel labeling, the labeling accuracy of the proposed automatic method is more than 84%, and can save at least 85% of the time. Compared with traditional computer labeling, complex background can be better dealt with by labeling interference and simple manual labeling. Validated by U-Net deep learning model, the average intersection ratio of test sets can reach 0.90.

    参考文献
    相似文献
    引证文献
引用本文

刘超,许木南,曹思娴,牛圣尧,朱安琪.裂缝检测模型数据集的低监督快速标注算法[J].同济大学学报(自然科学版),2023,51(11):1692~1700

复制
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:2022-04-05
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2023-12-01
  • 出版日期: