A New Identification Method for Surface Cracks from UAV Images Based on Machine Learning in Coal Mining Areas

被引:39
|
作者
Zhang, Fan [1 ]
Hu, Zhenqi [2 ]
Fu, Yaokun [1 ]
Yang, Kun [1 ]
Wu, Qunying [3 ]
Feng, Zewei [4 ]
机构
[1] China Univ Min & Technol, Inst Land Reclamat & Ecol Restorat, Beijing 100083, Peoples R China
[2] China Univ Min & Technol, Sch Environm Sci & Spatial Informat, Xuzhou 221116, Jiangsu, Peoples R China
[3] Yulin Econ Dev Zone, Yulin 719000, Peoples R China
[4] Shenmu Hanjiawan Coal Min Co Ltd, Shanxi Coal & Chem Ind Grp, Shenmu 719315, Peoples R China
关键词
crack classification; UAV images; machine learning; FISSURES; FOREST;
D O I
10.3390/rs12101571
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Obtaining real-time, objective, and high-precision distribution information of surface cracks in mining areas is the first task for studying the development regularity of surface cracks and evaluating the risk. The complex geological environment in the mining area leads to low accuracy and efficiency of the existing extracting cracks methods from unmanned air vehicle (UAV) images. Therefore, this manuscript proposes a new identification method of surface cracks from UAV images based on machine learning in coal mining areas. First, the acquired UAV image is cut into small sub-images, and divided into four datasets according to the characteristics of background information: Bright Ground, Dark Dround, Withered Vegetation, and Green Vegetation. Then, for each dataset, a training sample is established with cracks and no cracks as labels and the RGB (red, green, and blue) three-band value of the sub-image as feature. Finally, the best machine learning algorithms, dimensionality reduction methods and image processing techniques are obtained through comparative analysis. The results show that using the V-SVM (Support vector machine with V as penalty function) machine learning algorithm, principal component analysis (PCA) to reduce the full features to 95% of the original variance, and image color enhancement by Laplace sharpening, the overall accuracy could reach 88.99%. This proves that the method proposed in this manuscript can achieve high-precision crack extraction from UAV image.
引用
收藏
页数:20
相关论文
共 50 条
  • [1] Evaluation of Surface Crack Development and Soil Damage Based on UAV Images of Coal Mining Areas
    Zhang, Fan
    Hu, Zhenqi
    Liang, Yusheng
    Li, Quanzhi
    LAND, 2023, 12 (04)
  • [2] Ground Fissure Identification in Mining Areas from UAV Images Based on DN-CAMSCBNet
    Hu, Haibin
    Guo, Xinhui
    Xiao, Jie
    ELEKTRONIKA IR ELEKTROTECHNIKA, 2025, 31 (01) : 39 - 46
  • [3] Soil respiration estimation in desertified mining areas based on UAV remote sensing and machine learning
    Liu, Ying
    Lin, Jiaquan
    Yue, Hui
    EARTH SCIENCE INFORMATICS, 2023, 16 (04) : 3433 - 3448
  • [4] Soil respiration estimation in desertified mining areas based on UAV remote sensing and machine learning
    Ying Liu
    Jiaquan Lin
    Hui Yue
    Earth Science Informatics, 2023, 16 : 3433 - 3448
  • [5] Segmentation Method of Concrete Small Cracks Based on UAV Images
    Pan Y.
    Zou W.
    Xv Q.
    Zhao Y.
    Liang Q.
    Zhao T.
    Recent Advances in Computer Science and Communications, 2024, 17 (05) : 71 - 81
  • [6] Automatic Identification of Tree Species from UAV Images Using Machine Learning Approaches
    Vaghela Himali Pradipkumar
    R. A. Alagu Raja
    Journal of the Indian Society of Remote Sensing, 2022, 50 : 2447 - 2464
  • [7] Automatic Identification of Tree Species from UAV Images Using Machine Learning Approaches
    Pradipkumar, Vaghela Himali
    Raja, R. A. Alagu
    JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING, 2022, 50 (12) : 2447 - 2464
  • [8] Ground Fissure Extraction Method based on Improved Active Contour Model for UAV Images in Mining Areas
    Hao M.
    Lin H.
    Gao Y.
    Journal of Geo-Information Science, 2022, 24 (12) : 2448 - 2457
  • [9] A New Method for CTC Images Recognition Based on Machine Learning
    He, Binsheng
    Lu, Qingqing
    Lang, Jidong
    Yu, Hai
    Peng, Chao
    Bing, Pingping
    Li, Shijun
    Zhou, Qiliang
    Liang, Yuebin
    Tian, Geng
    FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY, 2020, 8
  • [10] Early Identification of Oil Palm Health based on UAV images using Feature-Based Machine Learning
    Lee, Chang Yi
    Tay, Lee Choo
    Tan, Weng Chun
    Lai, Weng Kin
    Lee, Sheng Siang
    2024 IEEE INTERNATIONAL CONFERENCE ON SMART COMPUTING, SMARTCOMP 2024, 2024, : 302 - 307