Research on Online Identification Algorithms for Discarded Circuit Board Surface-Mounted Components
DOI:
https://doi.org/10.6919/ICJE.202411_10(11).0011Keywords:
Discarded Circuit Boards; YOLOv8; Electronic Components; Knowledge Distillation.Abstract
In recent years, the rapid advancement of electronic products has significantly increased the quantity of discarded electronic products, particularly waste circuit boards, leading to issues of resource wastage and environmental pollution. Therefore, developing an efficient recycling system for circuit board surface-mounted components is crucial. However, challenges such as the wide range of component sizes, diverse types, and the similarity in characteristics of small-sized components make detection difficult. This paper uses YOLOv8 as the base network model, with YOLOv8l as the teacher model and YOLOv8n as the student model, applying the CWD knowledge distillation method to the YOLOv8n model. The study employs a combination of publicly available datasets and some self-constructed datasets as the data foundation, and conducts comparative experiments with different YOLOv8 algorithm models. The results show that the average precision of the YOLOv8 model after knowledge distillation reaches 94.8%, an improvement of 2.3% over the YOLOv8n model, with a 45.2% increase in detection speed. This indicates that the knowledge-distilled YOLOv8 model is suitable for online identification of discarded circuit board surface-mounted components in practical production environments.
Downloads
References
[1] Ren S, He K, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2016, 39(6): 1137-1149.
[2] He K, Gkioxari G, Dollár P, et al. Mask r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2017: 2961-2969.
[3] Cai Z, Vasconcelos N. Cascade r-cnn: Delving into high quality object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 6154-6162.
[4] Dai J, Li Y, He K, et al. R-fcn: Object detection via region-based fully convolutional networks[J]. Advances in neural information processing systems, 2016, 29.
[5] Mulajkar R, Yede S. YOLO Version v1 to v8 Comprehensive Review[C]//2024 International Conference on Inventive Computation Technologies (ICICT). IEEE, 2024: 472-478.
[6] Liu W, Anguelov D, Erhan D, et al. Ssd: Single shot multibox detector[C]//Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14. Springer International Publishing, 2016: 21-37.
[7] Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE international conference on computer vision. 2017: 2980-2988.
[8] Zhou X, Wang D, Krähenbühl P. Objects as points[J]. arXiv preprint arXiv:1904.07850, 2019.
[9] Tan M, Pang R, Le Q V. Efficientdet: Scalable and efficient object detection[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 10781-10790.
[10] Carion N, Massa F, Synnaeve G, et al. End-to-end object detection with transformers[C]//European conference on computer vision. Cham: Springer International Publishing, 2020: 213-229.
[11] Singh G, Stefenon S F, Yow K C. Interpretable visual transmission lines inspections using pseudo-prototypical part network[J]. Machine Vision and Applications, 2023, 34(3): 41.
[12] Ma N, Su Y, Yang L, et al. Wheat Seed Detection and Counting Method Based on Improved YOLOv8 Model[J]. Sensors, 2024, 24(5): 1654.
[13] Shu C, Liu Y, Gao J, et al. Channel-wise knowledge distillation for dense prediction[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021: 5311-5320.
[14] Information on https://universe.roboflow.com.
Downloads
- Views: 4 | Downloads: 1 PDF
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.