Method for lightweight litchi fruit detection in complex environments via improved YOLO11n-MAS

Authors

  • Jing Ling School of Artificial Intelligence, Guangzhou Maritime University, Guangzhou 510725, China
  • Yaozhong Mei School of Low-altitude Equipment and Intelligent Control, Guangzhou Maritime University, Guangzhou 510725, China
  • Zheng Zuo School of Electronics and Electrical Engineering, Ningxia University, Yinchuan 750021, China
  • Shengkang Pan School of Low-altitude Equipment and Intelligent Control, Guangzhou Maritime University, Guangzhou 510725, China

Keywords:

litchi, lightweight network, YOLO11n, complex environment, fruit

Abstract

Accurate and real-time detection of litchi fruit is crucial for the development of automated harvesting systems and the advancement of precision agriculture. This study addresses the challenge of litchi fruit detection in complex orchard environments characterized by branch occlusion, fruit overlap, and variable lighting conditions. A lightweight detection model, YOLO11n-MAS, was proposed to achieve efficient and robust fruit identification. A self-constructed Zengcheng litchi dataset was first established to provide high-quality data for training and validation, thereby improving the model’s detection performance. The YOLO11n-MAS model was built on the YOLO11n architecture, incorporating a novel C3k2-EMBC module and a Bi-Level Routing Attention (BRA) mechanism to reconstruct the backbone network, utilizing a parameter-efficient Slimneck to optimize the neck, and introducing a specialized Detect_LSDECD module into the detection head to balance performance and efficiency. Experimental results show that the YOLO11n-MAS model achieves a mean average precision (mAP50) of 0.916, outperforming other advanced lightweight models including YOLOv8n and the baseline YOLO11n. Additionally, the model’s parameter size is only 2.34 M, and its GFLOPs is 5.5, representing reductions of 9.4% and 12.7%, respectively, compared to YOLO11n, significantly lowering computational costs while maintaining high detection performance. The results demonstrate the effectiveness of the C3k2-EMBC, BRA, Slimneck, and Detect_LSDECD modules. The development of the YOLO11n-MAS model can provide an efficient and lightweight solution for litchi fruit detection in resource-constrained environments, offering strong technical support for intelligent harvesting systems.      

Key words: litchi; lightweight network; YOLO11n; complex environment; fruit detection

DOI: 10.25165/j.ijabe.20261904.10519

Citation: Ling  J,  Mei  Y  Z,  Zuo  Z,  Pan  S  K.  Method  for  lightweight  litchi  fruit  detection  in  complex  environments  via
improved YOLO11n-MAS. Int J Agric & Biol Eng, 2026; 19(4): 227–234.

References

[1] Jiang N H, Liu W, Xiao Z D, Xiang X, Zhong Y. Metabolomics unveiled the accumulation characteristics of taste compounds during the development and maturation of litchi fruit. Foods, 2025; 14(1): 144.

[2] Handel M J. Labor shortages: What is the problem. Intereconomics, 2024; 59(3): 136–142.

[3] Ling J, Heldman D R. Integration of machine learning technologies in food flavor research: Current applications, challenges, and future perspectives. Int J Agric & Biol Eng, 2025; 18(3): 1–11.

[4] Habaragamuwa H, Ogawa Y, Suzuki T, Shiigi T, Ono M, Kondo N. Detecting greenhouse strawberries (mature and immature), using deep convolutional neural network. Engineering in Agriculture, Environment and Food, 2018; 11(3): 127–138.

[5] Liu Y. An improved faster R-CNN for object detection. In: 2018 11th International Symposium on Computational Intelligence and Design (ISCID), Hangzhou: IEEE, 2018; pp.119–123. doi: 10.1109/ISCID.2018.10128.

[6] Alif M A R, Hussain M. YOLOv1 to YOLOv10: A comprehensive review of YOLO variants and their application in the agricultural domain. arXiv preprint, 2024; arXiv: 2406.10139. doi: 10.48550/arXiv.2406.10139.

[7] Li X, Pan J D, Xie F P, Zeng J P, Li Q, Huang X J, et al. Fast and accurate green pepper detection in complex backgrounds via an improved YOLOv4-tiny model. Computers and Electronics in Agriculture, 2021; 191: 106503.

[8] Gao A, Du Y H, Li Y Q, Song Y P, Ren L L. Apple flower phenotype detection method based on YOLO-FL and application of intelligent flower thinning robot. Int J Agric & Biol Eng, 2025; 18(3): 236–246.

[9] Chen D X, Liu L, Zhao L, Shi Y, Wang F, Meng D, et al. Method for lightweight tomato leaf disease recognition based on improved YOLO11s. Int J Agric & Biol Eng, 2025; 18(5): 298–305.

[10] Xu Y K, Khan T M, Song Y, Meijering E. Edge deep learning in computer vision and medical diagnostics: A comprehensive survey. Artificial Intelligence Review, 2025; 58(3): 93.

[11] He Z L, Xiong J T, Lin R, Zou X J, Tang L Y, Yang Z G, et al. A method of green litchi recognition in natural environment based on improved LDA classifier. Computers and Electronics in Agriculture, 2017; 140: 159–167.

[12] Chen M, Jin C Q, Ni Y L, Yang T X, Xu J S. A dataset of the quality of soybean harvested by mechanization for deep-learning-based monitoring and analysis. Data in Brief, 2024; 52: 109833.

[13] Sapkota R, Karkee M. Comparing YOLO11 and YOLOv8 for instance segmentation of occluded and non-occluded immature green fruits in complex orchard environment. arXiv preprint arXiv: 2410.19869, 2024.

[14] Liu C G, Gao G S, Huang Z Y, Hu Z H, Liu Q J, Wang Y H. YOLC: You only look clusters for tiny object detection in aerial images. IEEE Transactions on Intelligent Transportation Systems, 2024; 25(10): 13863–13875.

[15] Kotthapalli M, Ravipati D, Bhatia R. YOLOv1 to YOLO11: A comprehensive survey of real-time object detection innovations and challenges. arXiv preprint, 2025; arXiv: 2508.02067.

[16] He A, Li X B, Wu X M, Su C Y, Chen J, Xu S, et al. ALSS-YOLO: An adaptive lightweight channel split and shuffling network for TIR wildlife detection in UAV imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024; 17: 12345–12356.

[17] Howard A G, Zhu M L, Chen B, Kalenichenko D, Wang W J, Weyand T, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint, 2017; arXiv: 1704.04861v1. doi: 10.48550/arXiv.1704.04861.

[18] Wu X, Chen Z, Wang W, Jadbabaie A. A non-asymptotic analysis of oversmoothing in graph neural networks. In: Proc. 40th Int. Conf. on Machine Learning, Honolulu, HI: PMLR, 2023; pp.37228–37244. doi:10.5555/3618408.3618416.

[19] Lin T Y, Dollár P, Girshick R, He K M, Hariharan B, Belongie S. Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI: IEEE, 2017; pp.936–944. doi:10.1109/CVPR.2017.106.

[20] Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint, 2020; arXiv: 2004.10934. doi: 10.48550/arXiv.2004.10934.

[21] Gu Z N, He D Q, Huang J D, Chen J Q, Wu X H, Huang B C, et al. Simultaneous detection of fruits and fruiting stems in mango using improved YOLOv8 model deployed by edge device. Computers and Electronics in Agriculture, 2024; 227: 109512.

[22] Li H L, Li J, Wei H B, Liu Z, Zhan Z F, Ren Q L. Slim-neck by GSConv: A lightweight-design for real-time detector architectures. Journal of Real-Time Image Processing, 2024; 21(3): 62.

[23] Huang D Q, Tu Y T, Zhang Z H, Ye Z K. A lightweight vehicle detection method fusing GSConv and coordinate attention mechanism. Sensors, 2024; 24(8): 2394.

[24] Chen Z X, He Z W, Lu Z M. DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention. IEEE Transactions on Image Processing, 2024; 33: 1002–1015.

[25] Wen G H, Li M, Luo Y H, Shi C S, Tan Y F. The improved YOLOv8 algorithm based on EMSPConv and SPE-head modules. Multimed Tools Applications, 2024; 83(21): 61007–61023.

[26] Badgujar C M, Poulose A, Gan H. Agricultural object detection with You Only Look Once (YOLO) algorithm: A bibliometric and systematic literature review. arXiv preprint, 2024; arXiv: 2401.10379. doi:10.48550/arXiv.2401.10379.

[27] Selvaraju R R, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: Visual explanations from deep networks via gradient-based localization. In: 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy: IEEE, 2017; pp.618–626. doi:10.1109/ICCV.2017.74.

Downloads

Published

2026-09-03

How to Cite

(1)
Ling, J.; Mei, Y.; Zuo, Z.; Pan, S. Method for Lightweight Litchi Fruit Detection in Complex Environments via Improved YOLO11n-MAS. Int J Agric & Biol Eng 2026, 19, 227-234.

Issue

Vol. 19 No. 4 (2026): IJABE

Section

Information Technology, Sensors and Control Systems

License

Copyright (c) 2026 International Journal of Agricultural and Biological Engineering

Creative Commons License

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

IJABE is an international peer reviewed, open access journal, adopting Creative Commons Copyright Notices as follows.

Authors who publish with this journal agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).