Lightweight Non-Destructive Detection of Diseased Apples Based on Structural Re-Parameterization Technique
Source abstract
Abstract
This study addresses the challenges in the non-destructive detection of diseased apples, specifically the high complexity and poor real-time performance of the classification model for detecting diseased fruits in apple grading. Research is conducted on a lightweight model for apple defect recognition, and an improved VEW-YOLOv8n method is proposed. The backbone network incorporates a lightweight, re-parameterization VanillaC2f module, reducing both complexity and the number of parameters, and it employs an extended activation function to enhance the model’s nonlinear expression capability. In the neck network, an Efficient-Neck lightweight structure, developed using the lightweight modules and augmented with a channel shuffling strategy, decreases the computational load while ensuring comprehensive feature information fusion. The model’s robustness and generalization ability are further enhanced by employing the WIoU bounding box loss function, evaluating the quality of anchor frames using outlier metrics, and incorporating a dynamically updated gradient gain assignment strategy. Experimental results indicate that the improved model surpasses the YOLOv8n model, achieving a 2.7% increase in average accuracy, a 24.3% reduction in parameters, a 28.0% decrease in computational volume, and an 8.5% improvement in inference speed. This technology offers a novel, effective method for the non-destructive detection of diseased fruits in apple grading working procedures.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Smart Agriculture and AI · Plant Disease Management Techniques · Spectroscopy and Chemometric Analyses
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Computer and Information Engineering, Xinjiang Agricultural University, Urumqi 830052, China
Engineering Research Center of Intelligent Agriculture Ministry of Education, Urumqi 830052, China
Xinjiang Agricultural Informatization Engineering Technology Research Center, Urumqi 830052, China
Funding
Natural Science Foundation of Xinjiang Uygur Autonomous Region · Xinjiang Uygur Autonomous Region Colleges and Universities Research Program Project · Special Program for Central-Guided Local Science and Technology Development “Construction of Smart Agricultural Innovation Platform”
References (38)
Show source-provided references
1. Measurement of concentration of apple production in China’s main production areas and analysis of their competitiveness
2. Current status and future development of the key technologies for apple picking robots
3. Jet tagging algorithm of graph network with Haar pooling message passing10.1103/PhysRevD.108.072007 ↗
4. Fingertip Detection Algorithm Based on Maximum Discrimination HOG Feature in Complex Background10.1109/ACCESS.2023.3234526 ↗
5. Railway track detection algorithm based on Hu invariant moment feature
6. Madake, J., Raje, A., Rajurkar, S., Rakhe, R., Bhatlawande, S., and Shilaskar, S. (2022, January 13–15). Vision-based distracted driver detection using a fusion of SIFT and ORB feature extraction. Proceedings of the International Conference on Security, Privacy and Data Analytics, Surat, India.10.1007/978-981-99-3569-7_12 ↗
7. Copy move forgery detection with SURF and MSER combination
8. Pedestrian detection combined with single and couple pedestrian DPM models in traffic scene
9. Gu, B., Wen, C., Liu, X., Hou, Y., Hu, Y., and Su, H. (2023). Improved YOLOv7-Tiny Complex Environment Citrus Detection Based on Lightweighting. Agronomy, 13.10.3390/agronomy13112667 ↗
10. Ren, R., Sun, H., Zhang, S., Wang, N., Lu, X., Jing, J., Xin, M., and Cui, T. (2023). Intelligent Detection of Lightweight “Yuluxiang” Pear in Non-Structural Environment Based on YOLO-GEW. Agronomy, 13.10.3390/agronomy13092418 ↗
11. Lyu, S., Zhao, Y., Liu, X., Li, Z., Wang, C., and Shen, J. (2023). Detection of Male and Female Litchi Flowers Using YOLO-HPFD Multi-Teacher Feature Distillation and FPGA-Embedded Platform. Agronomy, 13.10.3390/agronomy13040987 ↗
12. Apple Location and Classification Based on Improved SSD Convolutional Neural Network
13. VMF-SSD: A Novel V-Space based Multi-scale Feature Fusion SSD for Apple Leaf Disease Detection10.1109/TCBB.2022.3229114 ↗
14. Hu, G., Zhang, E., Zhou, J., Zhao, J., Gao, Z., Sugirbay, A., Jin, H., Zhang, S., and Chen, J. (2021). Infield apple detection and grading based on multi-feature fusion. Horticulturae, 7.10.3390/horticulturae7090276 ↗
15. Study on the stability of high and steep slopes under deep bench blasting vibration in open-pit mines10.3389/feart.2022.990012 ↗
16. Liu, Y., Liu, X., and Zhang, B. (2023). RetinaNet-vline: A flexible small target detection algorithm for efficient aggregation of information. Clust. Comput., 1–13.10.1007/s10586-023-04109-4 ↗
17. Liu, S., Fu, S., Hu, A., Ma, P., Hu, X., Tian, X., Zhang, H., and Liu, S. (2023). Research on Insect Pest Identification in Rice Canopy Based on GA-Mask R-CNN. Agronomy, 13.10.3390/agronomy13082155 ↗
18. Object detection of VisDrone by stronger feature extraction FasterRCNN
19. Real-time defects detection for apple sorting using NIR cameras with pruning-based YOLOV4 network10.1016/j.compag.2022.106715 ↗
20. Apple detection in complex orchard environment based on improved RetinaNet
21. Zhang, C., Kang, F., and Wang, Y. (2022). An improved apple object detection method based on lightweight YOLOv4 in complex backgrounds. Remote Sens., 14.10.3390/rs14174150 ↗
22. Li, H., Li, J., Wei, H., Liu, Z., Zhan, Z., and Ren, Q. (2022). Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles. arXiv.
23. Tong, Z., Chen, Y., Xu, Z., and Yu, R. (2023). Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism. arXiv.
24. Aboah, A., Wang, B., Bagci, U., and Adu-Gyamfi, Y. (2023, January 18–22). Real-time multi-class helmet violation detection using few-shot data sampling technique and yolov8. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPRW59228.2023.00564 ↗
25. Ou, J., Zhang, R., Li, X., and Lin, G. (2023). Research and Explainable Analysis of a Real-Time Passion Fruit Detection Model Based on FSOne-YOLOv7. Agronomy, 13.10.3390/agronomy13081993 ↗
26. Ge, Z., Liu, S., Wang, F., Li, Z., and Sun, J. (2021). Yolox: Exceeding yolo series in 2021. arXiv.
27. Jadon, S. (2020, January 27–29). A survey of loss functions for semantic segmentation. Proceedings of the 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), Via del Mar, Chile.10.1109/CIBCB48159.2020.9277638 ↗
28. Feng, C., Zhong, Y., Gao, Y., Scott, M.R., and Huang, W. (2021, January 11–17). Tood: Task-aligned one-stage object detection. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, BC, Canada.10.1109/ICCV48922.2021.00349 ↗
29. Anchor-free oriented proposal generator for object detection10.1109/TGRS.2022.3183022 ↗
30. Chen, H., Wang, Y., Guo, J., and Tao, D. (2023). VanillaNet: The Power of Minimalism in Deep Learning. arXiv.
31. Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., and Savarese, S. (2019, January 16–20). Generalized intersection over union: A metric and a loss for bounding box regression. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2019, Long Beach, CA, USA.10.1109/CVPR.2019.00075 ↗
32. Control Distance IoU and Control Distance IoU Loss for Better Bounding Box Regression10.1016/j.patcog.2022.109256 ↗
33. Gevorgyan, Z. (2022). SIoU loss: More powerful learning for bounding box regression. arXiv.
34. Fast and accurate detection of kiwifruit in orchard using improved YOLOv3-tiny model10.1007/s11119-020-09754-y ↗
35. Sun, Y., Zhang, D., Guo, X., and Yang, H. (2023). Lightweight Algorithm for Apple Detection Based on an Improved YOLOv5 Model. Plants, 12.10.3390/plants12173032 ↗
36. 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.
37. Ranjan Sapkota, D.A., Churuvija, M., and Karkee, M. (2023). Immature green apple detection and sizing in commercial orchards using YOLOv8 and shape fitting techniques. arXiv.10.32388/ONBTUF.2 ↗
38. (2008). Fresh Apple (Standard No. GB/T 10651-2008).