Application of Target Detection Based on Deep Learning in Intelligent Mineral Identification
Abstract
:1. Introduction
2. YOLOv8 Model
2.1. C3 Module and C2f Modules
2.2. Backbone Network, Neck Network, and Head Network
2.3. Decoupled-Head
2.4. SPPF Module
2.5. Label Assignment with a Loss Function
3. Dataset Construction and Preprocessing
3.1. Acquisition of the Mineral Image Dataset
3.2. Data Preprocessing and Annotation
4. Design and Training of Intelligent Mineral Recognition Mode
4.1. Model Training and Initial Parameters
- Epochs: This parameter defines how many times the entire training dataset is passed through the model. Each epoch involves a full forward and backward pass to update the model’s parameters. While the model was set to train for 500 epochs, the optimal performance was achieved at epoch 258.
- Batch Size: This is the number of samples processed before updating the model parameters in each iteration. A larger batch size enhances GPU utilization and speeds up training, but may lead to high memory consumption. For our model, the batch size was set to 64 after several adjustments.
- Image Size (Imgsz): This parameter specifies the dimensions of the input images used during training and inference. The image size for our model was set to 640 pixels after testing.
- Pre-trained Weight File: We utilized YOLOv8x.pt, which includes weights optimized from training on a large-scale dataset. The “x” indicates a larger model variant with a deeper network and more parameters, enhancing performance.
- Learning Rate: This hyperparameter controls the step size for parameter updates during training. We started with an initial learning rate of 0.0001 and employed a cosine learning rate scheduler to adjust the rate over time for improved convergence.
4.2. Model Evaluation
5. Application Case Test
6. Discussion
7. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Zhou, Y.Z.; Zuo, R.G.; Liu, G.; Yuan, F.; Mao, X.C.; Guo, Y.J.; Xiao, F.; Liao, J.; Liu, Y.P. The Great-leap-forward Development of Mathematical Geoscience During 2010–2019: Big Data and Artificial Intelligence Algorithm Are Changing Mathematical Geoscience. Bull. Mineral. Petrol. Geochem. 2021, 40, 556–573. [Google Scholar] [CrossRef]
- Zhang, L.J.; Lu, W.h.; Zhang, J.D.; Peng, G.X.; Bu, J.C.; Tang, K.; Xie, J.C.; Xu, Z.B.; Yang, H.Y. Rock and mineral thin section identification based on deep learning. Geosci. Front. 2024, 31, 498–510. [Google Scholar] [CrossRef]
- Zhou, Y.Z.; Zhang, L.J.; Zhang, A.D.; Wang, J. Big Data Mining & Machine Learning in Geoscience. Sun Yat-sen University Press: Zhuhai, China, 2018. [Google Scholar]
- Xu, S.T.; Zhou, Y.Z. Artificial Intelligence Identification of Ore Minerals under Microscope Based on Deep Learning Algorithm. Acta Petrol. Sin. 2018, 34, 3244–3252. Available online: http://html.rhhz.net/ysxb/20181110.htm (accessed on 8 September 2018).
- Alerigi, D.P.S.R.; Li, W. Method for providing rock characterization and classification for geo-exploration, involves applying deep learning models to newly received data that includes data, and predicting properties based on newly received geo-exploration data. Saudi Arabian Oil Co 2022, D65162. Available online: https://webofscience.clarivate.cn/wos/alldb/full-record/DIIDW:2022D65162 (accessed on 19 August 2022).
- Zeng, X.; Ji, X.H.; Xiao, Y.C.; Wang, G.W. Mineral Identification Based on Deep Learning That Combines Image and Mohs Hardness. Minerals 2020, 11, 506. [Google Scholar] [CrossRef]
- Wang, J.B.; Xue, L.F.; Gao, X. Identification Method of Volcanic Rock Slices Based on A Deep Residual Shrinkage Network. In Proceedings of the Fourth International Conference on Geoscience and Remote Sensing Mapping, Wuhan, China, 14–16 April 2023; Volume 12551, pp. 389–394. [Google Scholar] [CrossRef]
- Zhang, Y.; Li, M.C.; Han, S.; Ren, Q.B.; Shi, J. Intelligent Identification for Rock-Mineral Microscopic Images Using Ensemble Machine Learning Algorithms. Sensors 2019, 18, 3914. [Google Scholar] [CrossRef]
- Zhang, S.X.; Yang, Y.Y.; Sun, F.C.; Fang, B. Application of Image Sensing System in Mineral/Rock Identification: Sensing Mode and Information Process. Adv. Intell. Syst. 2023, 5, 2300206. [Google Scholar] [CrossRef]
- Shi, C.J.; Zhang, W.M.; Chen, H.R.; Ge, L.L. Survey of Salient Object Detection Based on Deep Learning. J. Front. Comput. Sci. Technol. 2023, 38, 21–50. [Google Scholar] [CrossRef]
- Joseph, R.; Santosh, D.; Ross, G.; Ali, F. You Only Look Once: Unified, Real-Time Object Detection. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 779–788. [Google Scholar] [CrossRef]
- Tan, L.; Huangfu, T.R.; Wu, L.Y.; Chen, W.Y. Comparison of RetinaNet, SSD, and YOLO v3 for real-time pill identification. BMC medical informatics and decision making. 2021, 21, 1–11. [Google Scholar] [CrossRef]
- Ren, S.Q.; He, K.M.; Ross, G.; Sun, J. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 39, 1137–1149. [Google Scholar] [CrossRef]
- Tan, M.; Pang, R.; Le, Q.V. EfficientDet: Scalable and Efficient Object Detection. In Proceedings of the 2020 IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020; pp. 10778–10787. [Google Scholar] [CrossRef]
- He, K.M.; Gkioxari, G.; Dollar, P.; Girshick, R. Mask R-CNN. In Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCVW), Venice, Italy, 22–29 October 2017; pp. 2980–2988. [Google Scholar] [CrossRef]
- Zhang, J.Y.; Gao, Q.; Luo, H.L.; Long, T. Mineral Identification Based on Deep Learning Using Image Luminance Equalization. Appl. Sci. 2022, 12, 7055. [Google Scholar] [CrossRef]
- Liu, Y.; Zhang, Z.L.; Liu, X.; Wang, L.; Xia, X.H. Ore image classification based on small deep learning model: Evaluation and optimization of model depth, model structure and data size. Miner. Eng. 2021, 172, 107020. [Google Scholar] [CrossRef]
- Wan, D.H.; Lu, R.S.; Wang, S.L.; Shen, S.Y.; Xu, T.; Lang, X.L. YOLO-HR: Improved YOLOv5 for Object Detection in High-Resolution Optical Remote Sensing Images. Remote Sens. 2023, 15, 614. [Google Scholar] [CrossRef]
- Pratama, B.G.; Qodri, M.F.; Sugarbo, O. Building YoloV4 models for identification of rock minerals in thin section. IOP Conf. Ser. Earth Environ. Sci. 2023, 1151, 012046. [Google Scholar] [CrossRef]
- Mimura, K.; Nakamura, K.; Yasukawa, K.; Sibert, E.C.; Ohta, J.; Kitazawa, T.; Kato, Y. Applicability of Object Detection to Microfossil Research: Implications From Deep Learning Models to Detect Microfossil Fish Teeth and Denticles Using YOLO-v7. Earth Space Sci. 2024, 11, e2023EA003122. [Google Scholar] [CrossRef]
- Mimura, K.; Nakamura, K.; Takao, K.; Yasukawa, K.; Kato, Y. Automated Detection of Hydrothermal Emission Signatures From Multibeam Echo Sounder Images Using Deep Learning. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2023, 16, 2703–2710. [Google Scholar] [CrossRef]
- Ehsani, M.R.; Upadhyaya, S.K.; Slaughter, D.; Shafii, S.; Pelletier, M. A NIR Technique for Rapid Determination of Soil Mineral Nitrogen. Precis. Agric. 1999, 1, 219–236. [Google Scholar] [CrossRef]
- Aswini, E.; Vijayakumaran, C. Auto Detector for Huanglongbing Citrus Greening Disease using YOLOV7. In Proceedings of the 2023 World Conference on Communication & Computing (WCONF), Raipur, India, 14–16 July 2023; pp. 1–6. [Google Scholar] [CrossRef]
- Mei, H.; Wang, Q.Y.; Yu, L.; Zeng, Q. A deep learning-based algorithm for intelligent prediction of adverse geologic bodies in tunnels. Meas. Sci. Technol. 2024, 35, 096119. [Google Scholar] [CrossRef]
- Williams, J.M.; Scuderi, L.A.; McClanahan, T.P.; Banks, M.E.; Baker, D.M.H. Comparative planetology–Comparing cirques on Mars and Earth using a CNN. Geomorphology 2023, 440, 108881. [Google Scholar] [CrossRef]
- Li, W.W.; Wang, S.Z.; Arundel, S.T.; Hsu, C.Y. GeoImageNet: A multi-source natural feature benchmark dataset for GeoAI and supervised machine learning. GeoInformatica 2023, 27, 619–640. [Google Scholar] [CrossRef]
- Shi, Z.X.; Mo, G.Q.; Cui, Y.R.; Yan, L.B.; Lu, Y.S.; Hou, L.N.; Lv, L.S.; Li, H.X. Automatic Identification of Cirques Based on RetinaNet Model and Pseudo-Color Image Fusion Method. Adv. Space Res. 2024, 74, 2930–2940. [Google Scholar] [CrossRef]
- Bickel, V.T.; Lanaras, C.; Manconi, A.; Loew, S.; Mall, U. Lunar Rockfall Detection and Mapping usinng Deep Neural Networks. In Proceedings of the 50th Lunar and Planetary Science Conference, The Woodlands, TX, USA, 18–22 March 2019; Available online: https://hdl.handle.net/21.11116/0000-0003-4120-F (accessed on 18 March 2019).
- Feldens, P.; Darr, A.; Feldens, A.; Tauber, F. Detection of boulders in side scan sonar mosaics by a neural network. Geosciences 2019, 9, 159. [Google Scholar] [CrossRef]
- Bickel, V.T.; Loew, S.; Aaron, J.; Goedhart, N. A global perspective on lunar granular flows. Geophys. Res. Lett. 2022, 49, e2022GL098812. [Google Scholar] [CrossRef]
- Ma, S.M.; Huang, W.H. Application of Deep Learning Algorithms in Determination of Trace Rare Earth Elements of Cerium Group in Rocks and Minerals. Wirel. Commun. Mob. Comput. 2021, 2021, 9945141. [Google Scholar] [CrossRef]
- Wang, H.Y.; Cao, W.; Zhou, Y.Z.; Yu, P.P.; Yang, W. Multitarget intelligent recognition of petrographic thin section images based on faster RCNN. Minerals 2023, 13, 872. [Google Scholar] [CrossRef]
- Arslan, E.A. Radio galaxy morphology classification with mask R-CNN. In Proceedings of the 2020 4th International Conference on Vision, Image and Signal Processing, Bangkok, Thailand, 9–11 December 2020; Volume 36, pp. 1–5. [Google Scholar] [CrossRef]
- Liu, X.B.; Wang, H.Y.; Jing, H.D.; Shao, A.L.; Wang, L.C. Research on intelligent identification of rock types based on faster R-CNN method. IEEE Access 2020, 8, 21804–21812. [Google Scholar] [CrossRef]
- Radulescu, M.; Dalal, S.; Lilhore, U.K.; Saimiya, S. Optimizing mineral identification for sustainable resource extraction through hybrid deep learning enabled FinTech model. Resour. Policy 2024, 89, 104692. [Google Scholar] [CrossRef]
- Munteanu, D.; Moina, D.; Zamfir, C.G.; Petrea, S.M.; Cristea, D.S.; Munteanu, N. Sea mine detection framework using YOLO, SSD and EfficientDet deep learning models. Sensors 2022, 22, 9536. [Google Scholar] [CrossRef]
- Jia, J.Q.; Fu, M.; Liu, X.F.; Zheng, B. Underwater object detection based on improved efficientdet. Remote Sens. 2022, 14, 4487. [Google Scholar] [CrossRef]
- Edvardsen, I.P.; Teterina, A.; Johansen, T.; Myhre, J.N.; Godtliebsen, F.; Bolstad, N.L. Automatic detection of the mental foramen for estimating mandibular cortical width in dental panoramic radiographs. UiT Nor. Arktiske Univ. 2022, 50, 03000605221135147. [Google Scholar]
- Kim, E.C.; Hong, S.J.; Kim, S.Y.; Lee, C.H.; Kim, S.; Kim, H.J.; Kim, G. CNN-based object detection and growth estimation of plum fruit (Prunus mume) using RGB and depth imaging techniques. Sci. Rep. 2022, 12, 20796. [Google Scholar] [CrossRef] [PubMed]
- Dong, L.H.; Wang, H.L.; Song, W.; Xia, J.X.; Liu, T.M. Deep sea nodule mineral image segmentation algorithm based on Mask R-CNN. In Proceedings of the ACM Turing Award Celebration Conference-China, Hefei, China, 30 July–1 August 2021; pp. 278–284. [Google Scholar]
- Iyas, M.R.; Setiawan, N.I.; Warmada, I.W. Mask R-CNN for rock-forming minerals identification on petrography, case study at Monterado. E3S Web Conf. 2020, 200, 06007. [Google Scholar] [CrossRef]
- Koh, E.J.; Amini, E.; McLachlan, G.J.; Beaton, N. Utilising convolutional neural networks to perform fast automated modal mineralogy analysis for thin-section optical microscopy. Miner. Eng. 2021, 173, 107230. [Google Scholar] [CrossRef]
- Caldas, T.D.P.; Augusto, K.S.; Iglesias, J.C.A.; Ferreira, B.A.P.; Santos, R.B.M.; Paciornik, S.; Domingues, A.L.A. A methodology for phase characterization in pellet feed using digital microscopy and deep learning. Miner. Eng. 2024, 212, 108730. [Google Scholar] [CrossRef]
- Mao, Z.H.; Zhu, J.L.; Wu, X.; Li, J. Review of YOLO Based Target Detection for Autonomous Driving. J. Comput. Eng. Appl. 2022, 58, 68–77. [Google Scholar] [CrossRef]
- Al Muksit, A.; Hasan, F.; Emon, M.F.H.B.; Haque, M.R.; Anwary, A.R.; Shatabda, S. YOLO-Fish: A robust fish detection model to detect fish in realistic underwater environment. Ecol. Inform. 2022, 72, 101847. [Google Scholar] [CrossRef]
- Zuraimi, M.A.B.; Zaman, F.H.K. Vehicle detection and tracking using YOLO and DeepSORT. In Proceedings of the 2021 IEEE 11th IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE), Penang, Malaysia, 3–4 April 2021; pp. 23–29. [Google Scholar] [CrossRef]
- Vilar-Andreu, M.; García, L.; Garcia-Sanchez, A.J.; Asorey-Cacheda, R.; Garcia-Haro, J. Enhancing Precision Agriculture Pest Control: A generalized Deep Learning Approach with YOLOv8-based Insect Detection. IEEE Access 2024, 12, 84420–84434. [Google Scholar] [CrossRef]
- Prinzi, F.; Insalaco, M.; Orlando, A.; Gaglio, S.; Vitabile, S. A yolo-based model for breast cancer detection in mammograms. Cogn. Comput. 2024, 16, 107–120. [Google Scholar] [CrossRef]
- Reddy, S.M.; Rakesh, K.; Aluvala, S.; Bindu, G.; Husseen, A. Fault Detection and Classification in Semiconductor Manufacturing for Sensor Screening Using Multi-Layer. In Proceedings of the 2024 International Conference on Distributed Computing and Optimization Techniques (ICDCOT), Deep Neural Network, Bengaluru, India, 15–16 March 2024; pp. 1–4. [Google Scholar] [CrossRef]
- Reis, D.; Kupec, J.; Hong, J.; Daoudi, A. Real-time flying object detection with YOLOv8. arXiv 2023, arXiv:2305.09972. [Google Scholar] [CrossRef]
- Wu, T.Y.; Dong, Y.K. YOLO-SE: Improved YOLOv8 for Remote Sensing Object Detection and Recognition. IEEE Trans. Appl. Sci. 2023, 13, 12977. [Google Scholar] [CrossRef]
- Zhang, M.H.; Wang, Z.H.; Song, W.; Zhao, D.F.; Zhao, H.J. Efficient Small-Object Detection in Underwater Images Using the Enhanced YOLOv8 Network. IEEE Trans. Appl. Sci. 2024, 14, 1095. [Google Scholar] [CrossRef]
- Wang, X.L.; Girshick, R.; Gupta, A.; He, K.M. Non-local neural networks. In Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–22 June 2018; pp. 7794–7803. [Google Scholar] [CrossRef]
- Redmon, J.; Farhadi, A. YOLOv3: An Incremental Improvement. arXiv 2018, arXiv:1804.02767. [Google Scholar] [CrossRef]
- Li, J.F.; Yan, C.X. YOLOv8 with Multi Strategy Integrated Optimization and Application in Object Detection. Autom. Mach. Learn. 2024, 5, 23–31. [Google Scholar] [CrossRef]
- Attallah, Y.; Minerals Identification & Classification. Kaggle. Retrieved 2023. Available online: https://www.kaggle.com/datasets/youcefattallah97/minerals-identification-classification (accessed on 8 February 2023).
- Webmineral. Webmineral. Retrieved 2023. Available online: http://webmineral.com/ (accessed on 21 October 2023).
Mineral Species | Training Sets Num (pics) | Verification Sets Num (pics) | Test Sets Num (pics) |
---|---|---|---|
biotite | 1073 | 290 | 200 |
quartz | 1185 | 240 | 200 |
bornite | 817 | 192 | 200 |
chrysocolla | 740 | 182 | 200 |
malachite | 998 | 258 | 200 |
muscovite | 844 | 232 | 200 |
pyrite | 1086 | 298 | 200 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
He, L.; Zhou, Y.; Zhang, C. Application of Target Detection Based on Deep Learning in Intelligent Mineral Identification. Minerals 2024, 14, 873. https://doi.org/10.3390/min14090873
He L, Zhou Y, Zhang C. Application of Target Detection Based on Deep Learning in Intelligent Mineral Identification. Minerals. 2024; 14(9):873. https://doi.org/10.3390/min14090873
Chicago/Turabian StyleHe, Luhao, Yongzhang Zhou, and Can Zhang. 2024. "Application of Target Detection Based on Deep Learning in Intelligent Mineral Identification" Minerals 14, no. 9: 873. https://doi.org/10.3390/min14090873