{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T02:42:12Z","timestamp":1775097732556,"version":"3.50.1"},"reference-count":49,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T00:00:00Z","timestamp":1686182400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&amp;D Program of China","doi-asserted-by":"publisher","award":["2021YFC3001000"],"award-info":[{"award-number":["2021YFC3001000"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The changes in cracks on the surface of rock mass reflect the development of geological disasters, so cracks on the surface of rock mass are early signs of geological disasters such as landslides, collapses, and debris flows. To research geological disasters, it is crucial to swiftly and precisely gather crack information on the surface of rock masses. Drone videography surveys can effectively avoid the limitations of the terrain. This has become an essential method in disaster investigation. This manuscript proposes rock crack recognition technology based on deep learning. First, images of cracks on the surface of a rock mass obtained by a drone were cut into small pictures of 640 \u00d7 640. Next, a VOC dataset was produced for crack object detection by enhancing the data with data augmentation techniques, labeling the image using Labelimg. Then, we divided the data into test sets and training sets in a ratio of 2:8. Then, the YOLOv7 model was improved by combining different attention mechanisms. This study is the first to combine YOLOv7 and an attention mechanism for rock crack detection. Finally, the rock crack recognition technology was obtained through comparative analysis. The results show that the precision of the improved model using the SimAM attention mechanism can reach 100%, the recall rate can achieve 75%, the AP can reach 96.89%, and the processing time per 100 images is 10 s, which is the optimal model compared with the other five models. The improvement is relative to the original model, in which the precision was improved by 1.67%, the recall by 1.25%, and the AP by 1.45%, with no decrease in running speed. This proves that rock crack recognition technology based on deep learning can achieve rapid and precise results. It provides a new research direction for identifying early signs of geological hazards.<\/jats:p>","DOI":"10.3390\/s23125421","type":"journal-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T02:02:28Z","timestamp":1686189748000},"page":"5421","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Rock Crack Recognition Technology Based on Deep Learning"],"prefix":"10.3390","volume":"23","author":[{"given":"Jinbei","family":"Li","sequence":"first","affiliation":[{"name":"School of Hydraulic Engineering, Dalian University of Technology, Dalian 116024, China"}]},{"given":"Yu","family":"Tian","sequence":"additional","affiliation":[{"name":"Department of Water Resources Research, China Institute of Water Resources and Hydropower Research, Beijing 100038, China"}]},{"given":"Juan","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Water Resources Research, China Institute of Water Resources and Hydropower Research, Beijing 100038, China"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Hydraulic Engineering, Dalian University of Technology, Dalian 116024, China"},{"name":"Department of Water Resources Research, China Institute of Water Resources and Hydropower Research, Beijing 100038, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,6,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1016\/j.scitotenv.2019.03.415","article-title":"The human cost of global warming: Deadly landslides and their triggers (1995\u20132014)","volume":"682","author":"Haque","year":"2019","journal-title":"Sci. Total Environ."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/j.earscirev.2016.08.011","article-title":"Landslides in a changing climate","volume":"162","author":"Gariano","year":"2016","journal-title":"Earth-Sci. Rev."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Hui, E., Li, X., Chen, T., and Lang, W. (2020). Deciphering the spatial structure of China\u2019s megacity region: A new bay area\u2014The Guangdong-Hong Kong-Macao Greater Bay Area in the making. Cities, 105.","DOI":"10.1016\/j.cities.2018.10.011"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Mohammad, I., and Huang, H. (2010). Monitoring fatigue crack growth and opening using antenna sensors. Smart Mater. Struct., 19.","DOI":"10.1088\/0964-1726\/19\/5\/055023"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1007\/s11069-018-3427-4","article-title":"Real-time identification of urban rainstorm waterlogging disasters based on Weibo big data","volume":"94","author":"Xiao","year":"2018","journal-title":"Nat. Hazards"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Cao, C., Zhu, K., Song, T., Bai, J., Zhang, W., Chen, J., and Song, S. (2022). Comparative Study on Potential Landslide Identification with ALOS-2 and Sentinel-1A Data in Heavy Forest Reach, Upstream of the Jinsha River. Remote Sens., 14.","DOI":"10.3390\/rs14091962"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2313","DOI":"10.1080\/19475705.2022.2116357","article-title":"Accurate landslide identification by multisource data fusion analysis with improved feature extraction backbone network","volume":"13","author":"Jin","year":"2022","journal-title":"Geomat. Nat. Hazards Risk"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hu, Z., Liu, J., Jiang, C., Zhang, H., Chen, N., and Yang, Z. (2022). A high-precision detection method for coated fuel particles based on improved faster region-based convolutional neural network. Comput. Ind., 143.","DOI":"10.1016\/j.compind.2022.103752"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2013). Rich feature hierarchies for accurate object detection and semantic segmentation. Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 1311.","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_11","unstructured":"Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. IEICE Trans. Fundam. Electron. Commun. Comput. Sci., 1506."},{"key":"ref_12","unstructured":"Kaiming, H., Georgia, G., Piotr, D., and Ross, G. (2017). Mask r-cnn. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Cai, Z., and Vasconcelos, N. (2017). Cascade r-cnn: Delving into high quality object detection. arXiv.","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Lu, X., Li, B., Yue, Y., Li, Q., and Yan, J. (2018). Grid r-cnn. arXiv.","DOI":"10.1109\/CVPR.2019.00754"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2015). You only look once: Unified, real-time object detection. arXiv.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Redmon, J., and Farhadi, A. (2016). YOLO 9000: Better, faster, stronger. arXiv.","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref_17","unstructured":"Redmon, J., and Farhadi, A. (2018). YOLOv3. InYolov3: An incremental improvemen. arXiv."},{"key":"ref_18","unstructured":"Bochkovskiy, A., Wang, C., and Liao, H. (2020). Yolov4: Optimal Speed and Accuracy of Object Detection. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Christian, S., Reed, S., Fu, C., and Alexander, C. (2015). Ssd: Single shot multibox detector. arXiv.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_20","unstructured":"Wang, C., Bochkovskiy, A., and Liao, H. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv."},{"key":"ref_21","first-page":"43","article-title":"Crack recognition based on deep learning SSD target detection algorithm","volume":"43","author":"Li","year":"2021","journal-title":"J. Nanchang Univ. Eng. Technol."},{"key":"ref_22","first-page":"252","article-title":"Crack target detection method of bridge bottom based on YOLOv3","volume":"3","author":"Yang","year":"2022","journal-title":"China Sci."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zheng, J., Wu, H., Zhang, H., Wang, Z., and Xu, W. (2022). Insulator-Defect Detection Algorithm Based on Improved YOLOv7. Sensors, 22.","DOI":"10.3390\/s22228801"},{"key":"ref_24","first-page":"240","article-title":"A classification and location of surface defects method in hot rolled steel strips based on YOLOV7","volume":"62","author":"Sun","year":"2023","journal-title":"Metallurgy"},{"key":"ref_25","first-page":"134","article-title":"Research on tracking and prediction of rock fissure development based on improved Faster R-CNN algorithm","volume":"41","author":"Huang","year":"2022","journal-title":"J. Henan Polytech. Univ. Nat. Sci."},{"key":"ref_26","unstructured":"Jie, H., Li, S., Samuel, A., Gang, S., and Enhua, W. (2017). Squeeze-and-Excitation Networks. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2020). ECAnet. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. arXiv.","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Gao, Z., Xie, J., Wang, Q., and Li, P. (2019). Global Second-order Pooling Convolutional Networks. arXiv.","DOI":"10.1109\/CVPR.2019.00314"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhu, L., Wu, Y., and Yang, Y. (2020). Gated Channel Transformation for Visual Recognition. arXiv.","DOI":"10.1109\/CVPR42600.2020.01181"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Qin, Z., Zhang, P., Wu, F., and Li, X. (2021). FcaNet: Frequency Channel Attention Networks. arXiv.","DOI":"10.1109\/ICCV48922.2021.00082"},{"key":"ref_31","unstructured":"Max, J., Karen, S., Andrew, Z., and Koray, K. (2016). Spatial Transformer Networks. arXiv."},{"key":"ref_32","unstructured":"Hu, J., Shen, L., and Samuel, A. (2019). Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks. arXiv."},{"key":"ref_33","unstructured":"Alexey, D., Lucas, B., and Alexander, K. (2021). An image is worth 16 \u00d7 16 words: Transformrs for image recognition at scale. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., and Wei, Y. (2017). Deformable Convolutional Networks. arXiv.","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhang, Y., Liu, S., Shi, J., Loy, C., Lin, D., and Jia, J. (2018, January 8\u201314). PSANet: Point-wise Spatial Attention Network for Scene Parsing. Proceedings of the Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref_36","unstructured":"Prajit, R., Niki, P., and Ashish, V. (2019). SASA, Stand-Alone Self-Attention in Vision Models. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J., and Kweon, I. (2019). CBAM: Convolutional Block Attention Module. arXiv.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_38","unstructured":"Guo, M., Xu, T., Liu, J., Liu, J., Liu, Z., Jiang, P., Mu, T., Zhang, S., Martin, R., and Cheng, M. (2021). Attention Mechanisms in Computer Vision: A Survey. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., and Feng, J. (2021). Coordinate Attention for Efficient Mobile Network Design. arXiv.","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Liu, J., Hou, Q., Cheng, M., Wang, C., and Feng, J. (2020, January 13\u201319). Improving convolutional networks with self-calibrated convolutions. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01011"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, H., Xiao, J., Nie, L., Shao, J., Liu, W., and Chua, T. (2016). SCA-CNN: Spatial and channel-wise attention in convolutional networks for image captioning. arXiv.","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref_42","unstructured":"Abhijit, G., Nassir, N., and Christian, W. (2018). Recalibrating fully convolutional networks with spatial and channel \u201csqueeze and excitation\u201d blocks. arXiv."},{"key":"ref_43","unstructured":"Diganta, M., Trikay, N., Ajay, U., and Hou, Q. (2020). Rotate to attend: Convolutional triplet attention module. arXiv."},{"key":"ref_44","unstructured":"Yang, L., Zhang, R., Li, L., and Xie, X. (2021, January 18\u201324). SIMam: A simple, parameter-free attention module for convolutional neural networks. Proceedings of the 38th International Conference on Machine Learning, ser. Proceedings of MachineLearning Research, Virtual Event."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"11666","DOI":"10.1523\/JNEUROSCI.3414-05.2005","article-title":"Early and Late Mechanisms of Surround Suppression in Striate Cortex of Macaque","volume":"25","author":"Webb","year":"2005","journal-title":"J. Neurosci."},{"key":"ref_46","unstructured":"Arunabha, M., and Jayabrata, B. (2023). A Computer Vision Enabled damage detection model withimproved YOLOv5 based on Transformer Prediction Head. arXiv."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Cao, Z., Mei, F., Zhang, D., Liu, B., Wang, Y., and Hou, W. (2023). Recognition and Detection of Persimmon in a Natural Environment Based on an Improved YOLOv5 Model. Electronics, 12.","DOI":"10.3390\/electronics12040785"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Deng, Z., Yang, R., Lan, R., Liu, Z., and Luo, X. (2020). SE-IYOLOV3: An Accurate Small Scale Face Detector for Outdoor Security. Mathematics, 8.","DOI":"10.3390\/math8010093"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Cao, Y., Chen, J., and Zhang, Z. (2023). A sheep dynamic counting scheme based on the fusion between an improved-sparrow-search YOLOv5x-ECA model and few-shot deepsort algorithm. Comput. Electron. Agric., 206.","DOI":"10.1016\/j.compag.2023.107696"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/12\/5421\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:50:30Z","timestamp":1760125830000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/12\/5421"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,8]]},"references-count":49,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["s23125421"],"URL":"https:\/\/doi.org\/10.3390\/s23125421","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,8]]}}}