基于改进的Mask R-CNN的露天矿边坡裂隙智能检测算法
DOI:
作者:
作者单位:

1.西安建筑科技大学管理学院;2.西安建筑科技大学资源工程学院;3.西安市智慧工业感知计算与决策重点实验室

作者简介:

通讯作者:

中图分类号:

基金项目:

国家自然科学基金面上项目(51974223);陕西省自然科学基础研究计划项目(2019JM-492)


An intelligent detection method for open-pit slope fracture based on the improved Mask R-CNN
Author:
Affiliation:

1.School of Management,Xi’an University of Architecture and Technology;2.School of Resources Engineering,Xi’an University of Architecture and Technology;3.Xi'4.'5.an Key Laboratory of Perception Computing and Decision making in Intelligent Industry;6.Xi&7.amp;8.#39;9.&

Fund Project:

National Natural Science Foundation of China(51974223) ; Shaanxi Natural Science Foundation of China(2019JM-492)

  • 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:

    露天矿边坡裂隙检测在露天矿安全生产管理中占主要地位,裂隙的非及时性检测将会导致露天矿边坡发生滑坡等严重危害。为了预防因露天矿边坡表面恶化而产生节理、裂隙或断裂等破坏边坡完整性所引发的安全事故,同时解决传统图像处理算法以及经典的深度学习模型直接应用于露天矿边坡裂隙检测效果不甚理想的问题,提出了一种基于改进的Mask R-CNN的露天矿边坡裂隙智能检测算法,运用了Mask R-CNN在目标检测、语义分割以及目标定位方面的集成性特点,改进了其在掩膜分支的边缘不清晰以及误检等缺点,构建了一个专门针对露天矿边坡裂隙图像的检测分割框架。该方法在掩膜分割分支引入了空洞卷积神经网络以及分类分割迭代上采样操作,能够解决边坡裂隙分割边缘粗糙的问题,实验结果表明,与传统的裂缝分割算法相比,该算法具有更高的识别精度以及更好的分割效果。

    Abstract:

    Slope fracture detection is critical in the safety management of the open-pit mine, and the non-timely detection of slope fractures may cause landslide or other serious consequences. To prevent the unexpected accidents caused by the failure of slope integrity, this paper proposes an intelligent fracture detection algorithm based on improved Mask R-CNN, which can address the limitations of traditional image processing algorithm and the classical deep learning model directly to the open-pit mine slope crack detection. In this paper, we use the integrated features of Mask R-CNN in target detection, segmentation and location, improve the shortcomings of Mask branch, such as unclear edges and false detections, and construct a detection and segmentation framework for slope fracture images of the open-pit mine. This method introduces dilated convolution neural network, and a classify segmentation iterative up-sampling operation into the mask branch, which can solve the problem of slope fracture mask’s rough edge. Experimental results show that compared with the traditional crack segmentation algorithm, this method has higher recognition accuracy and better segmentation effect.

    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:2021-08-16
  • 最后修改日期:2021-11-03
  • 录用日期:2021-11-04
  • 在线发布日期:
  • 出版日期: