Detection of Waste Plastic Bottles based on an Improved YOLOv8s Model
DOI:
https://doi.org/10.6919/ICJE.202611_12(11).0013Keywords:
Waste Plastic Bottles; YOLOv8s; Object Detection.Abstract
Waste plastic bottles are frequently compressed, deformed, and stacked during recycling. To improve their detection, an enhanced model is developed from YOLOv8s. BiFPN is introduced into the Neck to strengthen feature fusion across scales; Coordinate Attention is added to the P3/8 and P4/16 branches to emphasize bottle mouths, body contours, and edge regions; and SIoU is adopted to improve bounding-box regression. Experimental results show that the proposed model achieves a Precision of 0.927, a Recall of 0.871, and an mAP@50 of 0.913, representing improvements of 5.5, 9.9, and 6.2 percentage points over the baseline, respectively. The model reduces missed detections and localization errors and improves the detection of waste plastic bottles.
Downloads
References
[1] Wang, J. S. (2022). What does China ranking first in the world in waste plastic recycling volume mean? Resource Recycling, (8), 46–47.
[2] Xue, Z. H., Liu, P., & Gao, Y. L. (2021). Current status of waste plastic recycling and reuse. Plastics Science and Technology, 49(4), 107–110.
[3] Xue, X. C., Wang, S. L., & Ju, K. L. (2022). Review of plastic waste resource utilization. Qinghai Science and Technology, 29(1), 113–118.
[4] Xing, J. K., Liu, T. T., & Wang, B. (2023). Research progress on closed-loop recyclable plastics. Sino-Global Energy, 28(9), 92–100.
[5] Wang, Y. Y. (2023). Design of a waste plastic bottle sorting system based on vision and industrial robots [Master’s thesis]. Yancheng Institute of Technology.
[6] Li, X. Y., Gong, X., Fu, B., et al. (2026). Binocular-vision recognition and localization method for waste plastic bottles based on YOLOv5. Journal of Packaging, 18(1), 98–106.
[7] Xie, S. L., Wu, H., Mao, W. J., et al. (2024). Efficient color recognition of waste plastic bottles based on deep learning. Plastics Science and Technology, 52(11), 140–146.
[8] Luo, Q. Q., Peng, W., & Yang, G. H. (2024). Recyclable-waste recognition method and engineering application based on YOLOv8. Computer Knowledge and Technology, 20(17), 29–32.
[9] Redmon, J., Divvala, S., Girshick, R., et al. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 779–788).
[10] Terven, J., Córdova-Esparza, D. M., & Romero-González, J. A. (2023). A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction, 5(4), 1680–1716.
[11] Yaseen, M. (2024). What is YOLOv8: An in-depth exploration of the internal features of the next-generation object detector. arXiv. https://arxiv.org/abs/2408.15857
[12] Tan, M., Pang, R., & Le, Q. V. (2020). EfficientDet: Scalable and efficient object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10781–10790). IEEE.
[13] Wu, C. Y., Zhang, C. H., Kong, D. J., et al. (2025). Infrared image detection algorithm for power transmission and transformation equipment based on CA-YOLOv8. Infrared Technology, 47(9), 1128–1134.
[14] Shen, X. L., & Guo, X. (2026). Attention-based small-object detection in remote-sensing images. Opto-Electronic Engineering, 53(3), 116–132.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Core Journal of Engineering

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.




