A Strawberry Ripeness Detection Method Based on Improved YOLOv8
Source abstract
Abstract
An enhanced YOLOv8-based network was developed to accurately and efficiently detect the ripeness of strawberries in complex environments. Firstly, a CA (channel attention) mechanism was integrated into the backbone and head of the YOLOv8 model to improve its ability to identify key features of strawberries. Secondly, the bilinear interpolation operator was replaced with DySample (dynamic sampling), which optimized data processing, reduced computational load, accelerated upsampling, and improved the model’s sensitivity to fine strawberry details. Finally, the Wise-IoU (Wise Intersection over Union) loss function optimized the IoU (Intersection over Union) through intelligent weighting and adaptive tuning, enhancing the bounding box accuracy. The experimental results show that the improved YOLOv8-CDW model has a precision of 0.969, a recall of 0.936, and a mAP@0.5 of 0.975 in complex environments, which are 8.39%, 18.63%, and 12.75% better than those of the original YOLOv8, respectively. The enhanced model demonstrates higher accuracy and faster detection of strawberry ripeness, offering valuable technical support for advancing deep learning applications in smart agriculture and automated harvesting.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Smart Agriculture and AI
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Information Engineering, Tarim University, Aral 843300, China
College of Mechanical and Electrical Engineering, Tarim University, Aral 843300, China
Key Laboratory of Tarim Oasis Agriculture, Tarim University, Ministry of Education, Aral 843300, China
References (33)
Show source-provided references
1. Current Status of Machine Vision Technology for Fruit Positioning
2. Food and Agriculture Organization of the United Nations (FAO) (2023, March 24). FAOSTAT Database. Available online: https://www.fao.org/faostat/zh/#data/QCL.
3. A method for recognizing ripe apples in natural scenes based on hybrid color space
4. Maturity detection and volume estimation of apricot using image processing technique10.1016/j.scienta.2019.03.033 ↗
5. Banana detection based on color and texture features in the natural envronment10.1016/j.compag.2019.105057 ↗
6. Improved circular Hough transform for in-field red globe grape cluster ripeness discrimination
7. Dragon fruit maturity detection based-HSV space color using naive bayes classifier method10.1088/1757-899X/771/1/012022 ↗
8. Sinanoglou, V.J., Tsiaka, T., Aouant, K., Mouka, E., Ladika, G., Kritsi, E., Konteles, S.J., Ioannou, A.-G., Zoumpoulakis, P., and Strati, I.F. (2023). Quality assessment of banana ripening stages by combining analytical methods and image analysis. Appl. Sci., 13.10.3390/app13063533 ↗
9. Jiang, W., Xu, H., Chen, G., Zhao, W., and Xu, W. (2009, January 20–23). An improved edge-adaptive image scaling algorithm. Proceedings of the IEEE 8th International Conference on ASIC, Changsha, China.10.1109/ASICON.2009.5351551 ↗
10. Mature tomato fruit detection algorithm based on improved HSV and watershed algorithm10.1016/j.ifacol.2018.08.183 ↗
11. Detecting maturity of persimmon fruit based on image processing technique10.1016/j.scienta.2014.12.037 ↗
12. Jiang, H., Hu, Y., Jiang, X., and Zhou, H. (2022). Maturity stage discrimination of Camellia oleifera fruit using visible and nearinfrared hyperspectral imaging. Molecules, 27.10.3390/molecules27196318 ↗
13. Discriminaion of maturity of Camellia oleifera fruit on-site based on generaive adversarial network and hyperspectral imaging technique10.1007/s11694-023-02145-7 ↗
14. Machine vision for the maturity classification of oil palm fresh fruit bunches based on color and texture features10.1016/j.scienta.2021.110245 ↗
15. A method for blueberry ripeness recognition based on the improved YOLOv4-Tiny model
16. Detection of fruit maturity stage and yield estimation in wid blueberry using deep learing convolutional neural networks10.1016/j.atech.2022.100099 ↗
17. Apple ripeness identification from digital images using transformers10.1007/s11042-023-15938-1 ↗
18. Apple fruit recognition in complex orchard environments based on the improved YOLOv3 model
19. Zhang, L., Hao, Q., and Cao, J. (2023). Attention-based fine-grained lightweight architecture for fuji apple maturity classification in an open-world orchard environment. Agriculture, 13.10.3390/agriculture13020228 ↗
20. Ignacio, J.S., Eisma, K.N.A., and Caya, M.V.C. (2022, January 14–16). A YOLOv5-based deep leaning model for in-situ detection and matunity grading of mango. Proceedings of the 6th Intenational Conference on Communication and Information Systems (ICCIS), Chongqing, China.10.1109/ICCIS56375.2022.9998163 ↗
21. An improved Faster R-CNN model for multi-object tomato maturity detection in complex scenarios10.1016/j.ecoinf.2022.101886 ↗
22. Yan, B., Fan, P., Lei, X., Liu, Z., and Yang, F. (2021). A real-time apple targets detection method for picking robot based on improved YOLOv5. Remote Sens., 13.10.3390/rs13091619 ↗
23. Rapid recognition of greenhouse tomatoes based on attention mechanism and improved YOLO
24. Improved YOLOv5 lightweight network for citrus detection10.54254/2755-2721/26/20230834 ↗
25. Zhang, H., Zhang, K., Zhang, J., and Tao, D. (2021, January 2–9). SCNet: Spatial and Channel-wise Attention for Semantic Segmentation. Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), Palo Alto, CA, USA.
26. Woo, S., Park, J., Lee, J.-Y., and Kweon, I.S. (2018, January 8–14). CBAM: Convolutional Block Attention Module. Proceedings of the 15th European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_1 ↗
27. Strawberry Ripeness Detection Using Improved YOLOv5 Model under Complex Backgrounds
28. Hou, Q., Zhou, D., and Feng, J. (2021, January 19–25). Coordinate Attention for Efficient Mobile Network Design. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.01350 ↗
29. Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., and Ren, D. (2020, January 7–12). Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), New York, NY, USA.10.1609/aaai.v34i07.6999 ↗
30. Tong, Z.J., Chen, Y.H., Xu, Z.W., and Yu, R. (2023). Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism. arXiv.
31. The Pascal Visual Object Classes (VOC) Challenge10.1007/s11263-009-0275-4 ↗
32. Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., and Zitnick, C.L. (2014, January 6–12). Microsoft COCO: Common Objects in Context. Proceedings of the Computer vision–ECCV 2014: 13th European Conference (ECCV), Zurich, Switzerland.10.1007/978-3-319-10602-1_48 ↗
33. Design and Experiment of a Strawberry Picking Robot with Visual Identification and Deep Learning