TeaAppearanceLiteNet: A Lightweight and Efficient Network for Tea Leaf Appearance Inspection
Source abstract
Abstract
The inspection of the appearance quality of tea leaves is vital for market classification and value assessment within the tea industry. Nevertheless, many existing detection approaches rely on sophisticated model architectures, which hinder their practical use on devices with limited computational resources. This study proposes a lightweight object detection network, TeaAppearanceLiteNet, tailored for tea leaf appearance analysis. A novel C3k2_PartialConv module is introduced to significantly reduce computational redundancy while maintaining effective feature extraction. The CBMA_MSCA attention mechanism is incorporated to enable the multi-scale modeling of channel attention, enhancing the perception accuracy of features at various scales. By incorporating the Detect_PinwheelShapedConv head, the spatial representation power of the network is significantly improved. In addition, the MPDIoU_ShapeIoU loss is formulated to enhance the correspondence between predicted and ground-truth bounding boxes across multiple dimensions—covering spatial location, geometric shape, and scale—which contributes to a more stable regression and higher detection accuracy. Experimental results demonstrate that, compared to baseline methods, TeaAppearanceLiteNet achieves a 12.27% improvement in accuracy, reaching a mAP@0.5 of 84.06% with an inference speed of 157.81 FPS. The parameter count is only 1.83% of traditional models. The compact and high-efficiency design of TeaAppearanceLiteNet enables its deployment on mobile and edge devices, thereby supporting the digitalization and intelligent upgrading of the tea industry under the framework of smart agriculture.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Smart Agriculture and AI · Spectroscopy and Chemometric Analyses
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China
Keyi College of Zhejiang Sci-Tech University, Shaoxing 312369, China
Institute of Optical Target Simulation and Test Technology, Harbin Institute of Technology, Harbin 150001, China
Funding
National Natural Science Foundation of China · Stable Support Plan of the National Key Laboratory of Underwater Acoustic Technology
References (27)
Show source-provided references
1. Zhang, S., Yang, H., Yang, C., Yuan, W., Li, X., Wang, X., Zhang, Y., Cai, X., Sheng, Y., and Deng, X. (2023). Edge Device Detection of Tea Leaves with One Bud and Two Leaves Based on ShuffleNetv2-YOLOv5-Lite-E. Agronomy, 13.10.3390/agronomy13020577 ↗
2. Lightweight Tea Bud Recognition Network Integrating GhostNet and YOLOv510.3934/mbe.2022602 ↗
3. Shuai, L., Chen, Z., Li, Z., Li, H., Zhang, B., Wang, Y., and Mu, J. (2023). Real-Time Dense Small Object Detection Algorithm Based on Multi-Modal Tea Shoots. Front. Plant Sci., 14.10.3389/fpls.2023.1224884 ↗
4. Wang, M., Li, Y., Meng, H., Chen, Z., Gui, Z., Li, Y., and Dong, C. (2024). Small Target Tea Bud Detection Based on Improved YOLOv5 in Complex Background. Front. Plant Sci., 15.10.3389/fpls.2024.1393138 ↗
5. Meng, J., Wang, Y., Zhang, J., Tong, S., Chen, C., Zhang, C., An, Y., and Kang, F. (2023). Tea Bud and Picking Point Detection Based on Deep Learning. Forests, 14.10.3390/f14061188 ↗
6. Yang, M., Yuan, W., and Xu, G. (2024). YOLOX Target Detection Model Can Identify and Classify Several Types of Tea Buds with Similar Characteristics. Sci. Rep., 14.10.1038/s41598-024-53498-y ↗
7. Zhao, R., Liao, C., Yu, T., Chen, J., Li, Y., Lin, G., Huan, X., and Wang, Z. (2023). IMVTS: A Detection Model for Multi-Varieties of Famous Tea Sprouts Based on Deep Learning. Horticulturae, 9.10.3390/horticulturae9070819 ↗
8. Tea Buds Detection in Complex Background Based on Improved YOLOv710.1109/ACCESS.2023.3305405 ↗
9. Shi, M., Zheng, D., Wu, T., Zhang, W., Fu, R., Huang, K., and Deng, L.-J. (2024). Small Object Detection Algorithm Incorporating Swin Transformer for Tea Buds. PLoS ONE, 19.10.1371/journal.pone.0299902 ↗
10. Xie, S., and Sun, H. (2023). Tea-YOLOv8s: A Tea Bud Detection Model Based on Deep Learning and Computer Vision. Sensors, 23.10.3390/s23146576 ↗
11. Moosmann, J., Giordano, M., Vogt, C., and Magno, M. (2023, January 11–14). TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers. Proceedings of the 2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS), Hangzhou, China.10.1109/AICAS57966.2023.10168657 ↗
12. Li, J., and Ye, J. (2023). Edge-YOLO: Lightweight Infrared Object Detection Method Deployed on Edge Devices. Appl. Sci., 13.10.3390/app13074402 ↗
13. Betti, A., and Tucci, M. (2023). YOLO-S: A Lightweight and Accurate YOLO-like Network for Small Target Detection in Aerial Imagery. Sensors, 23.10.3390/s23041865 ↗
14. Reis, D., Kupec, J., Hong, J., and Daoudi, A. (2024). Real-Time Flying Object Detection with YOLOv8. arXiv.
15. Alqahtani, D.K., Cheema, A., and Toosi, A.N. (2024). Benchmarking Deep Learning Models for Object Detection on Edge Computing Devices. arXiv.10.1007/978-981-96-0805-8_11 ↗
16. LEAF-YOLO: Lightweight Edge-Real-Time Small Object Detection on Aerial Imagery
17. Chen, J., Kao, S., He, H., Zhuo, W., Wen, S., Lee, C.-H., and Gary Chan, S.-H. (2023, January 18–22). Run, Don’t Walk: Chasing Higher FLOPS for Faster Neural Networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.01157 ↗
18. Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8–14). CBAM: Convolutional Block Attention Module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_1 ↗
19. SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation
20. Yang, J., Liu, S., Wu, J., Su, X., Hai, N., and Huang, X. (February, January 27). Pinwheel-Shaped Convolution and Scale-Based Dynamic Loss for Infrared Small Target Detection. Proceedings of the AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.
21. Ma, S., and Xu, Y. (2023). MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression. arXiv.
22. Zhang, H., and Zhang, S. (2024). Shape-IoU: More Accurate Metric Considering Bounding Box Shape and Scale. arXiv.
23. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks10.1109/TPAMI.2016.2577031 ↗
24. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11–14). SSD: Single Shot Multibox Detector. Proceedings of the Computer Vision—ECCV 2016: 14th European Conference, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
25. Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv.
26. Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., and Nie, W. (2022). YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications. arXiv.
27. Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., and Ding, G. (2024). YOLOv10: Real-Time End-to-End Object Detection. arXiv.