Recognition of Chinese wolfberry images with windy and sandy noises using improved YOLOv8

Fengque Pei, Zhi Li, Song Mei, Zhiyu Song, Zhigang Shi, Dunbing Tang, Ru Wan

Abstract


With the nature of the high wind and sand in western China, the Chinese wolfberry recognition shows a strong relationship with the sandy noise and needs a high-accuracy algorithm. To address this issue, this study aimed to develop an algorithm for accurately detecting and recognizing wolfberries. YOLOv8, an algorithm promoted by Ultralytics, supports image classification, object detection, and instance segmentation tasks. To enhance the performance of the original YOLOv8 model, a novel YOLOv8 algorithm incorporating FasterNet, RepBiFPN, and Lightweight Asymmetric Dual-Head was proposed. Firstly, thousands of Chinese wolfberry images were collected from the Ningxia Academy of Agriculture and Forestry Science, China, and random noises were added to simulate the wind and sand conditions typical of spring. Secondly, leveraging the advantages of YOLOv8n, such as its high speed and accuracy, this research innovatively integrated the FasterNet block into the C2f module of YOLOv8 to improve the effective handling of data uncertainty and noise. Additionally, an innovative RepViT+BiFPN, a new detective head, and a Lightweight Asymmetric Dual-Head were introduced to improve the training efficiency of the YOLOv8 network. Finally, to evaluate the effectiveness of improved YOLOv8 for the recognition of wolfberry, the dataset of wolfberry images was divided into a training set, a validation set, and a testing set to assess the performances of different models. Experiment results demonstrate that the YOLOv8-FasterNet+LADH+RepBiFPN model outperforms other models in terms of mAP@0.50-0.95, achieving a 4.5% improvement on the validation set compared to the original YOLOv8n. This research addresses the high-speed and accurate recognition of the Chinese wolfberry under strong winds and sand noise through algorithmic improvements and integration, which can facilitate the automation and intelligence of Chinese wolfberry harvesting and contribute to the advancement of agricultural mechanization.
Key words: image recognition; Chinese wolfberry; windy and sandy noise; YOLOv8; attention module
DOI: 10.25165/j.ijabe.20251802.9052

Citation: Pei F Q, Li Z, Mei S, Song Z Y, Shi Z G, Tang D B, et al. Recognition of Chinese wolfberry images with windy and sandy noises using improved YOLOv8. Int J Agric & Biol Eng, 2025; 18(2): 239–247.

Keywords


image recognition; Chinese wolfberry; windy and sandy noise; YOLOv8; attention module

Full Text:

PDF

References


Yang Y Y, Han Y X, Li S, Yang Y D, Zhang M, Li H. Vision based fruit recognition and positioning technology for harvesting robots. Computers and Electronics in Agriculture, 2023; 213: 108258.

Zhu X, Chen R W, Xia H K, Zhang P Y. Intelligent recognition system of fruit picking robot. Application Research of Computer, 2014; 31(9): 2711–2714. (in Chinese) doi: 10.3969/j.issn.10013695. 2014.09.035.

Shen W, Pang Q, Fan Y L. Study on strong noise image restoration based on adaptive stochastic resonance in bistable system. Computer Engineering and Applications, 2009; 45(15): 180–182. (in Chinese)

He B, Zhang Y B, Gong J L, Fu G, Zhao Y Q, Wu R D. Fast recognition of tomato fruit in greenhouse at night based on improved YOLO v5. Transactions of the CSAM, 2022; 53(5): 201–208. (in Chinese)

Zhao Z Q, Wang J, Zhao H. Research on apple recognition algorithm in complex orchard environment based on deep learning. Sensors, 2023; 23(12): 5425.

Wang X R, Xu Y, Zhou J P, Chen J R. Safflower picking recognition in complex environments based on an improved YOLOv7. Transactions of the CSAE, 2023; 39(6): 169–176. (in Chinese)

Li G L, Ji C Y, Gu B X. Recognition and location of oscillating fruit based on monocular vision and ultrasonic testing. Transactions of the CSAM, 2015; 46(11): 1–8. (in Chinese)

Yu Y, Liu Y C, Li Y J, Xu C S, Li Y W. Object detection algorithm for citrus fruits based on improved YOLOv5 Model. Agriculture, 2024; 14(10): 1798.

Li Q W, Jia W K, Sun M L, Hou S J, Zheng Y J. A novel green apple segmentation algorithm based on ensemble U-Net under complex orchard environment. Computers and Electronics in Agriculture, 2021; 180: 105900.

Yang W J, Ma X X, Hu W C, Tang P J. Lightweight blueberry fruit recognition based on multi-scale and attention fusion NCBAM. Agronomy, 2022; 12(10): 2354.

Li H, Tao H X, Cui L H, Liu D W, Sun J T, Zhang M. Recognition and localization method of tomato based on SOM-K-means algorithm. Transactions of the CSAM, 2021; 52(1): 23–29. (in Chinese)

Hao P F, Liu L Q, Gu R Y. YOLO-RD-Apple orchard heterogeneous image obscured fruit detection model. Journal of Graphics, 2023; 44(3): 456–464. (in Chinese)

Zhao D A, Shen T, Chen Y, Jia W K. Fast tracking and recognition of overlapping fruit for apple harvesting robot. Transactions of the CSAE, 2015; 31(2): 22–28.

Xu P H, Fang N, Liu N, Lin F S, Yang S Q, Ning J. Visual recognition of cherry tomatoes in plant factory based on improved deep instance segmentation. Computers and Electronics in Agriculture, 2022; 197: 106991.

Liu T Z, Teng G F, Yuan Y C, Liu B, Liu Z G. Winter jujube fruit recognition method based on improved YOLO v3 under natural scene. Transactions of the CSAM, 2021; 52(5): 17–25. (in Chinese)

Sun J, Wu Z Q, Jia Y L, Gong D J, Wu X H, Shen J F. Detecting grape in an orchard using improved YOLOv5s. Transactions of the CSAE, 2023; 39(18): 192–200. (in Chinese)

Wang L S, Qin M X, Lei J Y, Wang X F, Tan K Z. Blueberry maturity recognition method based on improved YOLOv4-Tiny. Transactions of the CSAE, 2021; 37(18): 170–178. (in Chinese)

Zhang X W, Xuan C Z, Hou Z F. Recognition model for coated red clover seeds using YOLOv5s optimized with an attention module. Int J Agric & Biol Eng, 2023; 16(6): 207–214.

Xu R, Yang J L, Liu J, Yan W X, Ma G F, Ma J B. Trends and effects of agro-climatic resources and main meteorological disasters during Lycium barbarum L. growing seasons in Ningxia. Chinese Journal of Eco-Agriculture, 2023; 31(10): 1645–1656. (in Chinese)

Feng J, Zeng L H, Liu G, Si Y S. Fruit recognition algorithm based on multi-source images fusion. Transactions of the CSAM, 2014; 45(2): 73–80. (in Chinese)

Li P, Zheng J S, Li P Y, Long H W, Li M, Gao L H. Tomato maturity detection and counting model based on MHSA-YOLOv8. Sensors, 2023; 23(15): 6701.

Wang X T, Lu R T, Bi H X, Li Y H. An infrared small target detection method based on attention mechanism. Sensors, 2023; 23(20): 8608.

Chen J R, Kao S-H, He H, Zhuo W P, Wen S, Lee C-H. Run, don’t walk: Chasing higher FLOPS for Faster Neural Networks. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada: IEEE, 2023; pp.12021–12031. doi: 10.1109/CVPR52729.2023.01157.

Li N N, Chen Y R, Zhao D B. Adaptive search for broad attention based vision transformers. Neurocomputing, 2025; 611: 128696.

Wang A, Chen H, Lin Z J, Han J G, Ding G G. RepViT: Revisiting mobile CNN from ViT perspective. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle: IEEE, 2024; pp.15909–15920. doi: 10.1109/CVPR52733.2024.01506.

Zhang S F, Chi C, Yao Y Q, Lei Z, Li S Z. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle: IEEE, 2020; pp.9756–9765. doi: 10.1109/CVPR42600.2020.00978.

Wen M, Li C Y, Xue Y S, Xu M, Xi Z H, Qiu W D. YOFIR: High precise infrared object detection algorithm based on YOLO and FasterNet. Infrared Physics and Technology, 2025; 144: 105627.

Gulsoy T, Kablan B E. FocalNeXt: A ConvNeXt augmented FocalNet architecture for lung cancer classification from CT-scan images. Expert Systems With Applications, 2025; 261: 125553.

Yang G Y, Lei J, Zhu Z K, Cheng S Y, Feng Z L, Liang R H. AFPN: Asymptotic Feature Pyramid Network for object detection. 2023 IEEE International Conference on Systems, Man and Cybernetics (SMC), Honolulu: IEEE, 2023; pp.2184–2189. doi: 10.1109/SMC53992.2023.10394415.

Wang K H, Chu X X, Xu X M, Huang J S, Wei X M. EfficientRep: An efficient Repvgg-style ConvNets with hardware-aware neural network design. arXiv, 2023; In press. arXiv: 2302.00386. doi: 10.48550/arXiv.2302.00386.




Copyright (c) 2025 International Journal of Agricultural and Biological Engineering

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

2023-2026 Copyright IJABE Editing and Publishing Office