Tea Bud Detection and Recognition Based on an Improved YOLOv8 Algorithm

Qin Huang; Gang Jiang; Wei Tang; Junmin Li

doi:10.54097/xb0hgp83

Authors

Qin Huang School of Mechanical Engineering, Xihua University, Chengdu 610039, Sichuan, China
Gang Jiang School of Mechanical Engineering, Xihua University, Chengdu 610039, Sichuan, China
Wei Tang School of Mechanical Engineering, Xihua University, Chengdu 610039, Sichuan, China
Junmin Li School of Mechanical Engineering, Xihua University, Chengdu 610039, Sichuan, China

DOI:

https://doi.org/10.54097/xb0hgp83

Keywords:

Tea bud detection; YOLOv8; attention mechanism; structural re-parameterization; Wise-IoU loss.

Abstract

In natural tea gardens, tea buds are small, mutually occluded, and surrounded by background texture that closely resembles the target, which causes both missed and false detections. To raise detection accuracy without increasing model complexity, this paper proposes YOLOv8n-HQ, an improved YOLOv8n-based detector for tea buds. The algorithm introduces a P2 high-resolution detection layer to build a four-scale feature pyramid for stronger small-object representation, embeds a convolutional block attention module (CBAM) to suppress background interference, designs a lightweight re-parameterized convolution (LRPC) module to compress the model, and adopts a Wise-IoU loss to improve bounding-box regression accuracy. On a self-built dataset of 15 000 images, the proposed algorithm attains 89.9% mAP@0.5 and 67.6% mAP@0.5:0.95, which are 4.3 and 4.1 percentage points higher than the baseline; the parameter count and computational cost are reduced to 2.05 M and 6.0 GFLOPs, decreases of 35.9% and 31.0%, so that higher accuracy and a smaller model are achieved together. On both detection accuracy and model complexity the algorithm outperforms the compared models.

Downloads

Download data is not yet available.

References

[1] Xie, S., & Sun, H. W. (2023). Tea YOLOv8s: A tea bud detection model based on deep learning and computer vision. Sensors, 23(14), 6576. https://doi.org/10.3390/s23146576. DOI: https://doi.org/10.3390/s23146576

[2] Zhang, K., Yuan, B. H., Cui, J. Y., et al. (2024). Lightweight tea bud detection method based on improved YOLOv5. Scientific Reports, 14, 30449. https://doi.org/10.1038/s41598 024 81472 1 DOI: https://doi.org/10.1038/s41598-024-82529-x

[3] Ren, S., He, K., Girshick, R., & Sun, J. (2017). Faster R CNN: Towards real time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137–1149. https://doi.org/10.1109/TPAMI.2016.2577487 DOI: https://doi.org/10.1109/TPAMI.2016.2577031

[4] Liu, W., Anguelov, D., Erhan, D., Szegedy, C., & Reed, S. (2016). SSD: Single shot multibox detector. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 21–37). Springer. DOI: https://doi.org/10.1007/978-3-319-46448-0_2

[5] Redmon, J., & Farhadi, A. (2017). YOLO9000: Better, faster, stronger. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 7263–7271). IEEE. DOI: https://doi.org/10.1109/CVPR.2017.690

[6] Woo, S., Park, J., Lee, J. Y., & Kweon, I. S. (2018). CBAM: Convolutional block attention module. In Proceedings of the European Conference on Computer Vision (ECCV) (pp. 3–19). Springer. DOI: https://doi.org/10.1007/978-3-030-01234-2_1

[7] Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., & Sun, J. (2021). RepVGG: Making VGG style ConvNets great again. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 13733–13742). IEEE. DOI: https://doi.org/10.1109/CVPR46437.2021.01352

[8] Tong, Z., Chen, Y., Xu, Z., & Yu, R. (2023). Wise IoU: Bounding box regression loss with dynamic focusing mechanism. arXiv preprint arXiv:2301.10051. https://doi.org/10.48550/arXiv.2301.10051

[9] Ultralytics. (2023). Ultralytics YOLOv8: A state of the art real time object detection model. https://github.com/ultralytics/ultralytics