Real-time Steel Surface Defects Detection Appliocation based on Yolov4 Model and Transfer Learning
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Steel is one of the most fundamental components to mechanical industry. However, the quality of products are greatly impacted by the surface defects in the steel. Thus, researchers pay attention to the need for surface defects detector and the deep learning methods are the current trend of object detector. There are still limitations and rooms for improvements, for example, related works focus on developing the models but don’t take into account real-time application with practical implication on industrial settings. In this paper, a real-time application of steel surface defects detection based on YOLOv4 is proposed. Firstly, as the aim of this work to deploying model on real-time application, we studied related works on this field, particularly focusing on one-stage detector and YOLO algorithm, which is one of the most famous algorithm for real-time object detectors. Secondly, using pre-trained Yolov4-Darknet platform models and transfer learning, we trained and test on the hot rolled steel defects open-source dataset NEU-DET. In our study, we applied our application with 4 types of typical defects of a steel surface, namely patches, pitted surface, inclusion and scratches. Thirdly, we evaluated YOLOv4 trained model real-time performance to deploying our system with accuracy of 87.1 % mAP@0.5 and over 60 fps with GPU processing.
Abstract
Steel is one of the most fundamental components to mechanical industry. However, the quality of products are greatly impacted by the surface defects in the steel. Thus, researchers pay attention to the need for surface defects detector and the deep learning methods are the current trend of object detector. There are still limitations and rooms for improvements, for example, related works focus on developing the models but don’t take into account real-time application with practical implication on industrial settings. In this paper, a real-time application of steel surface defects detection based on YOLOv4 is proposed. Firstly, as the aim of this work to deploying model on real-time application, we studied related works on this field, particularly focusing on one-stage detector and YOLO algorithm, which is one of the most famous algorithm for real-time object detectors. Secondly, using pre-trained Yolov4-Darknet platform models and transfer learning, we trained and test on the hot rolled steel defects open-source dataset NEU-DET. In our study, we applied our application with 4 types of typical defects of a steel surface, namely patches, pitted surface, inclusion and scratches. Thirdly, we evaluated YOLOv4 trained model real-time performance to deploying our system with accuracy of 87.1 % mAP@0.5 and over 60 fps with GPU processing.
참고문헌 (17)
- Xing, J., "A convolutional neural network-based method for workpiece surface defect detection", Measurement, 176, pp.109185~ (2021)
- S. Ren, "Faster R-CNN : Towards Real-Time Object Detection with Region Proposal Networks", IEEE Transactions on Pattern Analysis & Machine Intelligence, 39(06), pp.1137~1149 (2017)
- Cheng, J. C., "Automated detection of sewer pipe defects in closed-circuit television images using deep learning techniques", Autom. Constr, 95, pp.155~171 (2018)
- Li, R., "Unified vision-based methodology for simultaneous concrete defect detection and geolocalization", Comput.-Aided Civ. Infrastruct. Eng, 33, pp.527~544 (2018)
- W. Liu, "SSD: Single Shot MultiBox Det", Computer Vision –ECCV 2016, pp.21~37 (2016)
- Redmon, J., "You only look once: Unified, real-time object detection", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.779~788 (2016)
- Zhang, C., "Bridge damage detection using a single-stage detector and field inspection images", arXiv 2018, arXiv:1812, ~ (2018)
- Yin, X, "A deep learning-based framework for an automated defect detection system for sewer pipes", Autom. Constr, 109, pp.102967~ (2020)
- Deng J, "Imaging-based crack detection on concrete surfaces using You Only Look Once network", Structural Health Monitoring, 20(2), pp.484~499 (2021)
- Jiaqiao Zhang, "Surface defect detection of steel strips based on classification priority YOLOv3-dense network", Ironmaking & Steelmaking, 48(5), pp.547~558 (2021)
- Lv, X., "Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network", 1562~ (2020)
- Redmon, J., "Yolov3: An incremental improvement", arXiv:1804.02767, ~ (2018)
- Joseph Redmon, "YOLO9000:Better, Faster, Stronger", CVPR2017, pp.6517~6525 (2017)
- Bochkovskiy, A., "YOLOv4: Optimal Speed and Accuracy of Object Detection", arXiv:2004.10934, ~ (2020)
- "YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet)"[URL]
- J. Li, "Real-time detection of steel strip surface defects based on improved YOLO detection network", IFACPapersOnLine, 51(21), pp.76~81 (2018)