Abstract
Rock quality designation (RQD) characteristics for assessing the degree of rock mass fracture make it a key parameter in rock grading or other rating systems. Traditional core characterization relies on subjective manual visual inspection by geologists. Currently, convolutional neural networks are used in borehole images to classify intact and nonintact cores in core rows for automatic RQD estimation. Classification networks cannot predict the exact locations of the intact cores, and drill core characterization is not intuitive. Alternatively, an attention mechanism combining channel and spatial attention modules is proposed to improve the YOLOv5 algorithm for drill core characterization. The model was trained on 657 artificial core tray images generated by the developed preprocessor to accurately predict the bounding boxes of the intact cores on the row centerline, and the automatic RQD calculation of the row was implemented with the developed postprocessing program. Our method performed RQD estimation on 602 new granite rows and 180 new quartz sandstone rows, with average error rates of 1.27% and 1.12%, respectively. It processed 50 m of cores on average in 1 s on a GPU. Furthermore, this method provides an innovative method for automatically processing and quantifying geological image databases.
Highlights
-
Drill core images are automatically analyzed to estimate the RQD of the rows.
-
An attention mechanism combining channel and spatial attention modules is proposed.
-
YOLOv5 is combined with an attention mechanism for detecting intact cores.
-
The proposed method is tested on granite and quartz sandstone images, yielding an average error rate of 1.24%.
Similar content being viewed by others
Data availability statement
Data will be made available on request.
References
Ahsan MM, Uddin MR, Farjana M et al (2022) Image data collection and implementation of deep learning-based model in detecting Monkeypox disease using modified VGG16. arXiv. https://doi.org/10.48550/arXiv.2206.01862
Alemdag S, Sari M, Seren A (2022) Determination of rock quality designation (RQD) in metamorphic rocks: a case study (Bayburt-Kırklartepe Dam). Bull Eng Geol Environ 81:214. https://doi.org/10.1007/s10064-022-02675-2
Alzubaidi F, Mostaghimi P, Swietojanski P et al (2021) Automated lithology classification from drill core images using convolutional neural networks. J Petroleum Sci Eng 197:107933. https://doi.org/10.1016/j.petrol.2020.107933
Alzubaidi F, Mostaghimi P, Si G et al (2022) Automated rock quality designation using convolutional neural networks. Rock Mech Rock Eng 55:3719–3734. https://doi.org/10.1007/s00603-022-02805-y
Balestriero R, Baraniuk RG (2022) Batch normalization explained. arXiv. https://doi.org/10.48550/arXiv.2209.14778
Barton N, Lien R, Lunde J (1974) Engineering classification of rock masses for the design of tunnel support. Rock Mech 6:189–236. https://doi.org/10.1007/BF01239496
Bieniawski ZT (1973) Engineering classification of jointed rock masses. Trans S Afr Inst Civ Eng 1973:335–343
Bochkovskiy A, Wang C-Y, Liao H-YM (2020) Yolov4: optimal speed and accuracy of object detection. arXiv. https://doi.org/10.48550/arXiv.2004.10934
Bradski G (2000) The openCV library. Dr Dobb’s J Software Tools Prof Progr 25:120–123
Chen J, Zhou M, Huang H et al (2021) Automated extraction and evaluation of fracture trace maps from rock tunnel face images via deep learning. Int J Rock Mech Min Sci 142:104745. https://doi.org/10.1016/j.ijrmms.2021.104745
Cui L, Ma R, Lv P et al (2018) MDSSD: multi-scale deconvolutional single shot detector for small objects. arXiv. https://doi.org/10.48550/arXiv.1805.07009
Deere DU (1964) Technical description of rock cores for engineering purpose. Rock Mech Eng Geol 1:17–22
Elfwing S, Uchibe E, Doya K (2018) Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw 107:3–11. https://doi.org/10.1016/j.neunet.2017.12.012
Farid AT, Rizwan M (2017) Prediction of in situ permeability for limestone rock using rock quality designation index. Intl J Geotech Geol Eng 11:948–951. https://doi.org/10.5281/zenodo.1132311
Fellgett M, Hall A, Harris S et al (2023) CoreScore: a machine learning approach to assess legacy core condition. Geol Soc 527:SP527-2021–2200. https://doi.org/10.1144/SP527-2021-200
Fu D, Su C, Wang W et al (2022) Deep learning based lithology classification of drill core images. PLoS ONE 17:e0270826. https://doi.org/10.1371/journal.pone.0270826
Ge Z, Liu S, Wang F et al (2021) Yolox: exceeding yolo series in 2021. arXiv. https://doi.org/10.48550/arXiv.2107.08430
Girshick R, Donahue J, Darrell T et al (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition. 580–587. https://doi.org/10.1109/CVPR.2014.81
Girshick R (2015) Fast r-cnn. Proceedings of the IEEE international conference on computer vision. 1440-1448. https://doi.org/10.1109/ICCV.2015.169
GitHub (2021) YOLOV5-Master. https://github.com/ultralytics/yolov5/tree/v6.1
Haftani M, Chehreh HA, Mehinrad A et al (2015) Practical investigations on use of weighted joint density to decrease the limitations of RQD measurements. Rock Mech Rock Eng 49:1551–1558. https://doi.org/10.1007/s00603-015-0788-9
Hasan M, Shang Y, Shao P et al (2022) Evaluation of engineering rock mass quality via integration between geophysical and rock mechanical parameters. Rock Mech Rock Eng 55:2183–2203. https://doi.org/10.1007/s00603-021-02766-8
He K, Zhang X, Ren S et al (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37:1904–1916. https://doi.org/10.1109/TPAMI.2015.2389824
He MM, Li N, Yao XC et al (2020) A new method for prediction of rock quality designation in borehole using energy of rotary drilling. Rock Mech Rock Eng 53:3383–3394. https://doi.org/10.1007/s00603-020-02091-6
Hou Q, Zhou D, Feng J (2021) Coordinate attention for efficient mobile network design. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 13713-13722. https://doi.org/10.48550/arXiv.2103.02907
Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. Proceedings of the IEEE conference on computer vision and pattern recognition. 7132-7141. https://doi.org/10.48550/arXiv.1709.01507
Jiang B, Luo R, Mao J et al. (2018) Acquisition of localization confidence for accurate object detection. Proceedings of the European conference on computer vision (ECCV). 784–799. https://doi.org/10.48550/arXiv.1807.11590
LeCun Y, Bengio Y (1995) Convolutional networks for images, speech, and time series. Handbook Brain Theory Neural Networks 3361:1995
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444. https://doi.org/10.1038/nature14539
Lemy F, Hadjigeorgiou J, Côté P et al (2013) Image analysis of drill core. Min Technol 110:172–177. https://doi.org/10.1179/mnt.2001.110.3.172
Li D, Zhao J, Ma J (2022) Experimental studies on rock thin-section image classification by deep learning-based approaches. Math 10:2317. https://doi.org/10.3390/math10132317
Li L, Ouellet S, Aubertin M (2009) An improved definition of rock quality designation, RQDc. Proceedings of the 3rd CANUS rock mechanics symposium, Toronto, May
Lin T-Y, Maire M, Belongie S et al. (2014) Microsoft coco: common objects in context. European conference on computer vision. Springer. 740–755. https://doi.org/10.1007/978-3-319-10602-1_48
Lin T-Y, Goyal P, Girshick R et al. (2017) Focal loss for dense object detection. Proceedings of the IEEE international conference on computer vision. 2980–2988. https://doi.org/10.1109/ICCV.2017.324
Lin T-Y, Dollár P, Girshick R et al. (2017) Feature pyramid networks for object detection. Proceedings of the IEEE conference on computer vision and pattern recognition. 2117–2125. https://doi.org/10.48550/arXiv.1612.03144
Liu F, Liu Y, Yang T et al (2021) Meticulous evaluation of rock mass quality in mine engineering based on machine learning of core photos. Chin J Geotech Eng 43:968–974
Liu H, Ren Y-L, Li X et al (2022) Rock thin-section analysis and identification based on artificial intelligent technique. Petroleum Sci 19:1605–1621. https://doi.org/10.1016/j.petsci.2022.03.011
Liu W, Anguelov D, Erhan D et al (2016) Ssd: Single shot multibox detector. European conference on computer vision. Springer. 21–37. https://doi.org/10.1007/978-3-319-46448-0_2
Liu S, Qi L, Qin H et al (2018) Path aggregation network for instance segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition. 8759–8768. https://doi.org/10.1109/CVPR.2018.00913
Loshchilov I, Hutter F (2016) Sgdr: stochastic gradient descent with warm restarts. arXiv. https://doi.org/10.48550/arXiv.1608.03983
Marinos P, Hoek E (2000) GSI: a geologically friendly tool for rock mass strength estimation. ISRM international symposium. OnePetro
Oliphant TE (2006) A guide to NumPy. Trelgol Publishing USA
Olson L, Samson C, McKinnon SD (2015) 3-D laser imaging of drill core for fracture detection and rock quality designation. Int J Rock Mech Min Sci 73:156–164. https://doi.org/10.1016/j.ijrmms.2014.11.004
Paszke A, Gross S, Massa F et al. (2019) Pytorch: an imperative style, high-performance deep learning library. Adv Neural Inform Processing Syst. 32
Ren S, He K, Girshick R et al. (2015) Faster r-cnn: towards real-time object detection with region proposal networks. Adv Neural Inform Processing Syst. 28
Salaamah AF, Fathani TF, Wilopo W (2018) Correlation of P-wave velocity with rock quality designation (RQD) in volcanic rocks. J Appl Geol 3:62–72. https://doi.org/10.22146/jag.48594
Saricam T, Ozturk H (2018) Estimation of RQD by digital image analysis using a shadow-based method. Int J Rock Mech Min Sci 112:253–265. https://doi.org/10.1016/j.ijrmms.2018.10.032
Smith PR (1981) Bilinear interpolation of digital images. Ultramicroscopy 6:201–204. https://doi.org/10.1016/0304-3991(81)90061-9
Steger C (1998) An unbiased detector of curvilinear structures. IEEE Trans Pattern Anal Mach Intell 20:113–125. https://doi.org/10.1109/34.659930
Tian Z, Shen C, Chen H et al (2019) Fcos: fully convolutional one-stage object detection. Proceedings of the IEEE/CVF international conference on computer vision. 9627–9636. https://doi.org/10.48550/arXiv.1904.01355
van Rossum G, de Boer J (1991) Interactively testing remote servers using the Python programming language. Cwi Quarterly 4:283–303
Wang C-Y, Liao H-YM, Wu Y-H et al. (2020) CSPNet: a new backbone that can enhance learning capability of CNN. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops. 390–391
Wang Q, Wu B, Zhu P et al. (2020) Supplementary material for ‘ECA-Net: Efficient channel attention for deep convolutional neural networks. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, pp 13–19
Woo S, Park J, Lee J-Y et al. (2018) Cbam: convolutional block attention module. Proceedings of the European conference on computer vision (ECCV). 3–19. https://doi.org/10.48550/arXiv.1807.06521
Xu Z, Ma W, Lin P et al (2021) Deep learning of rock images for intelligent lithology identification. Comput Geosci 154:104799. https://doi.org/10.1016/j.cageo.2021.104799
Zhang L (2016) Determination and applications of rock quality designation (RQD). J Rock Mech Geotech Eng 8:389–397. https://doi.org/10.1016/j.jrmge.2015.11.008
Zheng Z, Wang P, Liu W et al (2020) Distance-IoU loss: faster and better learning for bounding box regression. Proceedings of the AAAI conference on artificial intelligence. 12993–13000. https://doi.org/10.1609/aaai.v34i07.6999
Acknowledgements
This study is sponsored by the National Natural Science Foundation of China (Grant No. 51579089).
Funding
This study was funded by the National Natural Science Foundation of China (Grant No. 51579089).
Author information
Authors and Affiliations
Contributions
DF, CS and XL collected and prepared the data; DF, and CS performed the experiments; DF and XL analyzed the results of the experiments; DF wrote the paper.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Fu, D., Su, C. & Li, X. Automatic Estimation Of Rock Quality Designation Based On An Improved YOLOv5. Rock Mech Rock Eng 57, 3043–3061 (2024). https://doi.org/10.1007/s00603-023-03729-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00603-023-03729-x