A Real-Time Green and Lightweight Model for Detection of Liquefied Petroleum Gas Cylinder Surface Defects Based on YOLOv5
Source abstract
Abstract
Industry requires defect detection to ensure the quality and safety of products. In resource-constrained devices, real-time speed, accuracy, and computational efficiency are the most critical requirements for defect detection. This paper presents a novel approach for real-time detection of surface defects on LPG cylinders, utilising an enhanced YOLOv5 architecture referred to as GLDD-YOLOv5. The architecture integrates ghost convolution and ECA blocks to improve feature extraction with less computational overhead in the network’s backbone. It also modifies the P3–P4 head structure to increase detection speed. These changes enable the model to focus more effectively on small and medium-sized defects. Based on comparative analysis with other YOLO models, the proposed method demonstrates superior performance. Compared to the base YOLOv5s model, the proposed method achieved a 4.6% increase in average accuracy, a 44% reduction in computational cost, a 45% decrease in parameter counts, and a 26% reduction in file size. In experimental evaluations on the RTX2080Ti, the model achieved an inference rate of 163.9 FPS with a total carbon footprint of 0.549 × 10−3 gCO2e. The proposed technique offers an efficient and robust defect detection model with an eco-friendly solution compatible with edge computing devices.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Offshore Engineering and Technologies · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Engineering, Faculty of Technology, Isparta University of Applied Sciences, 32100 Isparta, Turkey
Funding
AYGAZ A.Ş.
References (86)
Show source-provided references
1. Liquefied Petroleum Gas Systems: A Review on Design and Sizing Guidelines
2. Turkish Standards Institute (TSE) (2024, December 27). TS EN 1439: LPG Equipment and Accessories—Periodic Inspection and Testing of LPG Cylinders. Available online: https://intweb.tse.org.tr/Standard/Standard/StandardAra.aspx.
3. Automated surface defect detection framework using machine vision and convolutional neural networks10.1007/s10845-021-01878-w ↗
4. Bai, J., Wu, D., Shelley, T., Schubel, P., Twine, D., Russell, J., Zeng, X., and Zhang, J. (2024). A comprehensive survey on machine learning-driven material defect detection: Challenges, solutions, and future prospects. arXiv.
5. Fast and non-invasive surface crack detection of press panels using image processing10.1016/j.proeng.2017.04.459 ↗
6. Improved Sobel algorithm for defect detection of rail surfaces with enhanced efficiency and accuracy10.1007/s11771-016-3350-3 ↗
7. Automated surface defect detection for cold-rolled steel strip based on wavelet anisotropic diffusion method
8. Defect detection of steel surfaces with global adaptive percentile thresholding of gradient image10.1007/s40031-017-0296-2 ↗
9. A real-time approach for automatic defect detection from PCBs based on SURF features and morphological operations10.1007/s11042-019-08097-9 ↗
10. Saberironaghi, A., Ren, J., and El-Gindy, M. (2023). Defect detection methods for industrial products using deep learning techniques: A review. Algorithms, 16.10.3390/a16020095 ↗
11. Li, J., Pan, H., and Li, J. (2023). ESD-YOLOv5: A Full-Surface Defect Detection Network for Bearing Collars. Electronics, 12.10.3390/electronics12163446 ↗
12. MOD-YOLO: Rethinking the YOLO Architecture at the Level of Feature Information and Applying It to Crack Detection10.1016/j.eswa.2023.121346 ↗
13. A comprehensive review of deep learning-based PCB defect detection10.1109/ACCESS.2023.3339561 ↗
14. Summary of insulator defect detection based on deep learning10.1016/j.epsr.2023.109688 ↗
15. Automated steel surface defect detection and classification using a new deep learning-based approach10.1007/s00521-022-08112-5 ↗
16. A deep learning model for steel surface defect detection10.1007/s40747-023-01180-7 ↗
17. Comparative assessment of common pre-trained CNNs for vision-based surface defect detection of machined components10.1016/j.eswa.2023.119623 ↗
18. Fabric defect detection in textile manufacturing: A survey of the state of the art
19. The prospect of artificial intelligence-based wood surface inspection: A review10.1109/ACCESS.2024.3412928 ↗
20. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
21. Girshick, R. (2015, January 7–13). Fast R-CNN. Proceedings of the IEEE International Conference on Computer Vision 2015, Santiago, Chile.10.1109/ICCV.2015.169 ↗
22. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
23. Leibe, B., Matas, J., Sebe, N., and Welling, M. (2016). SSD: Single Shot MultiBox Detector. Computer Vision—ECCV 2016, Springer. Lecture Notes in Computer Science.10.1007/978-3-319-46454-1 ↗
24. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You only look once: Unified, real-time object detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
25. Xu, J., Zhou, W., Fu, Z., Zhou, H., and Li, L. (2021). A survey on green deep learning. arXiv.
26. Green AI10.1145/3381831 ↗
27. Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv.
28. Jocher, G., Chaurasia, A., Qiu, J., and Stoken, N. (2024, October 02). YOLOv5 v6.0. GitHub Repository. Available online: https://github.com/ultralytics/yolov5/releases/tag/v6.0.
29. Steel surface defect detection using improved deep learning algorithm: ECA-SimSPPF-SIoU-YOLOv510.1109/ACCESS.2024.3371584 ↗
30. Detection of wheat scab fungus spores utilizing the YOLOv5-ECA-ASFF network structure10.1016/j.compag.2023.107953 ↗
31. Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2020, January 13–19). ECA-net: Efficient channel attention for deep convolutional neural networks. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01155 ↗
32. YOLO-Inspection: Defect detection method for power transmission lines based on enhanced YOLOv5s10.1007/s11554-023-01360-1 ↗
33. A lightweight and efficient one-stage detection framework10.1016/j.compeleceng.2022.108520 ↗
34. LF-YOLO: A lighter and faster YOLO for weld defect detection of X-ray image10.1109/JSEN.2023.3247006 ↗
35. Hou, W., Wen, S., Li, P., and Feng, S. (2023, January 18–20). Surface defect detection of fabric based on improved Faster R-CNN. Proceedings of the 2023 IEEE International Conference on Sensors, Electronics and Computer Engineering (ICSECE), Jinzhou, China.10.1109/ICSECE58870.2023.10263522 ↗
36. Defect transformer: An efficient hybrid transformer architecture for surface defect detection10.1016/j.measurement.2023.112614 ↗
37. Liu, X., and Gao, J. (2021, January 11–14). Surface defect detection method of hot rolling strip based on improved SSD model. Database Systems for Advanced Applications, Proceedings of the DASFAA 2021 International Workshops: GDMA, MLDLDSA, MobiSocial, and MUST, Taipei, Taiwan.10.1007/978-3-030-73216-5_15 ↗
38. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv.
39. Liu, Z., and Gao, J. (2021). Swin Transformer: Hierarchical vision transformer using shifted windows. arXiv.10.1109/ICCV48922.2021.00986 ↗
40. Surface defect detection and classification of steel using an efficient Swin Transformer10.1016/j.aei.2023.102061 ↗
41. ETDNet: Efficient transformer-based detection network for surface defect detection10.1109/TIM.2023.3307753 ↗
42. Defect-aware transformer network for intelligent visual surface defect detection10.1016/j.aei.2023.101882 ↗
43. Khan, A., Rauf, Z., Sohail, A., Rehman, A., Asif, H., Asif, A., and Farooq, U. (2023). A survey of the Vision Transformers and their CNN-Transformer based variants. arXiv.10.1007/s10462-023-10595-0 ↗
44. Vis. Transform. Models Mob. /Edge Devices: A Survey10.1007/s00530-024-01312-0 ↗
45. Maurício, J., Domingues, I., and Bernardino, J. (2023). Comparing vision transformers and convolutional neural networks for image classification: A literature review. Appl. Sci., 13.10.3390/app13095521 ↗
46. Low-altitude small-sized object detection using lightweight feature-enhanced convolutional neural network10.23919/JSEE.2021.000073 ↗
47. Deep learning based object detection for resource-constrained devices: Systematic review, future trends and challenges ahead10.1016/j.neucom.2023.02.006 ↗
48. A crack-segmentation algorithm fusing transformers and convolutional neural networks for complex detection scenarios10.1016/j.autcon.2023.104894 ↗
49. Taye, M.M. (2023). Theoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions. Computation, 11.10.3390/computation11030052 ↗
50. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
51. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
52. Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2017, Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
53. Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., and Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50× fewer parameters and <0.5 MB model size. arXiv.
54. Howard, G., Sandler, M., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv.
55. Zhang, X., Zhou, X., Lin, M., and Sun, J. (2018, January 18–23). ShuffleNet: An extremely efficient convolutional neural network for mobile devices. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00716 ↗
56. Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., and Xu, C. (2020, January 13–19). GhostNet: More features from cheap operations. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00165 ↗
57. Gholami, A., Kwon, K., Wu, B., Tai, Z., Yue, X., Jin, P., and Keutzer, K. (2018, January 18–22). SqueezeNext: Hardware-aware neural network design. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops 2018, Salt Lake City, UT, USA.10.1109/CVPRW.2018.00215 ↗
58. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018, January 18–23). MobileNetV2: Inverted residuals and linear bottlenecks. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00474 ↗
59. Ma, N., Zhang, X., Zheng, H.-T., and Sun, J. (2018). ShuffleNet V2: Practical guidelines for efficient CNN architecture design. arXiv.10.1007/978-3-030-01264-9_8 ↗
60. Zhang, G., Liu, S., Nie, S., and Yun, L. (2024). YOLO-RDP: Lightweight Steel Defect Detection through Improved YOLOv7-Tiny and Model Pruning. Symmetry, 16.10.3390/sym16040458 ↗
61. Surface defect detection of steel plate based on SKS-YOLO10.1109/ACCESS.2024.3422244 ↗
62. Huang, H. (2023). TLI-YOLOv5: A lightweight object detection framework for transmission line inspection by unmanned aerial vehicle. Electronics, 12.10.3390/electronics12153340 ↗
63. Sapkota, R., Meng, Z., Churuvija, M., Du, X., Ma, Z., and Karkee, M. (2024). Comprehensive performance evaluation of YOLOv10, YOLOv9 and YOLOv8 on detecting and counting fruitlet in complex orchard environments. arXiv.10.36227/techrxiv.172055410.07175469/v1 ↗
64. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2017, Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
65. Wang, C.-Y., Liao, H.-Y.M., Wu, Y.-H., Chen, P.-Y., Hsieh, J.-W., and Yeh, I.-H. (2020, January 14–19). CSPNet: A new backbone that can enhance learning capability of CNN. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.10.1109/CVPRW50498.2020.00203 ↗
66. Ma, Z., Li, M., and Wang, Y. (2019). PAN: Path integral based convolution for deep graph neural networks. arXiv.
67. In-depth review of YOLOv1 to YOLOv10 variants for enhanced photovoltaic defect detection10.3390/solar4030016 ↗
68. Sohan, M., Ram, T.S., and Reddy, C.V.R. (2024, January 18–20). A review on YOLOv8 and its advancements. Proceedings of the International Conference on Data Intelligence and Cognitive Informatics 2024, Tirunelveli, India.10.1007/978-981-99-7962-2_39 ↗
69. Alif, M.A.R., and Hussain, M. (2024). YOLOv1 to YOLOv10: A comprehensive review of YOLO variants and their application in the agricultural domain. arXiv.
70. Xu, X., Jiang, Y., Chen, W., Huang, Y., Zhang, Y., and Sun, X. (2022). Damo-YOLO: A report on real-time object detection design. arXiv.
71. Ultralytics (2024, November 05). Home. Available online: https://docs.ultralytics.com/.
72. Solawetz, J. (2024, November 05). What Is YOLOv8? A Complete Guide. Roboflow Blog. Available online: https://blog.roboflow.com/whats-new-in-yolov8/.
73. Wang, C.-Y., Yeh, I.-H., and Liao, H.-Y.M. (2024). YOLOv9: Learning what you want to learn using programmable gradient information. arXiv.10.1007/978-3-031-72751-1_1 ↗
74. Wang, A., Liu, F., Gao, S., Zhang, S., Li, C., Zhang, X., Zhang, W., Sun, W., and Ding, X. (2024). YOLOv10: Real-time end-to-end object detection. arXiv.
75. Wang, C.-Y., and Liao, H.-Y.M. (2024). YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems. arXiv.10.1561/116.20240058 ↗
76. Research on lightweight pedestrian detection based on improved YOLOv510.21595/mme.2023.23719 ↗
77. Arifando, R., Eto, S., and Wada, C. (2023). Improved YOLOv5-based lightweight object detection algorithm for people with visual impairment to detect buses. Appl. Sci., 13.10.3390/app13095802 ↗
78. Hu, J., Shen, L., and Sun, G. (2018, January 18–23). Squeeze-and-Excitation Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
79. Hou, Q., Zhou, D., and Feng, J. (2021, January 20–25). Coordinate Attention for Efficient Mobile Network Design. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021, Nashville, TN, USA.10.1109/CVPR46437.2021.01350 ↗
80. Liu, Y., Shao, Z., Teng, Y., and Hoffmann, N. (2021). NAM: Normalization-Based Attention Module. arXiv.
81. Woo, S., Park, J., Lee, J.-Y., and Kweon, I.S. (2018). CBAM: Convolutional Block Attention Module. arXiv.10.1007/978-3-030-01234-2_1 ↗
82. EBSE-YOLO: High Precision Recognition Algorithm for Small Target Foreign Object Detection10.1109/ACCESS.2023.3284062 ↗
83. Zhao, Y., Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., and Chen, J. (2024, January 16–22). DETRs beat YOLOs on real-time object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR52733.2024.01605 ↗
84. MPQ-YOLO: Ultra Low Mixed-Precision Quantization of YOLO for Edge Devices Deployment10.1016/j.neucom.2023.127210 ↗
85. A Light-Weight Object Detection Method Based on Knowledge Distillation and Model Pruning for Seam Tracking System10.1016/j.measurement.2023.113438 ↗
86. Lightweight Detection Network for Bridge Defects Based on Model Pruning and Knowledge Distillation10.1016/j.istruc.2024.106276 ↗