Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Apr 10:15:1375118.
doi: 10.3389/fpls.2024.1375118. eCollection 2024.

Fruits hidden by green: an improved YOLOV8n for detection of young citrus in lush citrus trees

Gao Ang  1   2 , Tian Zhiwei  2 , Ma Wei  2 , Song Yuepeng  1 , Ren Longlong  1 , Feng Yuliang  3 , Qian Jianping  4 , Xu Lijia  5
Affiliations

Fruits hidden by green: an improved YOLOV8n for detection of young citrus in lush citrus trees

Gao Ang et al. Front Plant Sci. .

Abstract

In order to address the challenges of inefficiency and insufficient accuracy in the manual identification of young citrus fruits during thinning processes, this study proposes a detection methodology using the you only look once for complex backgrounds of young citrus fruits (YCCB-YOLO) approach. The method first constructs a dataset containing images of young citrus fruits in a real orchard environment. To improve the detection accuracy while maintaining the computational efficiency, the study reconstructs the detection head and backbone network using pointwise convolution (PWonv) lightweight network, which reduces the complexity of the model without affecting the performance. In addition, the ability of the model to accurately detect young citrus fruits in complex backgrounds is enhanced by integrating the fusion attention mechanism. Meanwhile, the simplified spatial pyramid pooling fast-large kernel separated attention (SimSPPF-LSKA) feature pyramid was introduced to further enhance the multi-feature extraction capability of the model. Finally, the Adam optimization function was used to strengthen the nonlinear representation and feature extraction ability of the model. The experimental results show that the model achieves 91.79% precision (P), 92.75% recall (R), and 97.32% mean average precision (mAP)on the test set, which were improved by 1.33%, 2.24%, and 1.73%, respectively, compared with the original model, and the size of the model is only 5.4 MB. This study could meet the performance requirements for citrus fruit identification, which provides technical support for fruit thinning.

Keywords: YOLO V8; deep learning; lightweight network; target detection; young citrus fruit.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Images of young citrus fruit parts at different angles.
Figure 2
Figure 2
Structure of citrus young fruit detection model.
Figure 3
Figure 3
Schematic diagram of P-shaped Conv convolution.
Figure 4
Figure 4
Schematic diagram of P-Block module.
Figure 5
Figure 5
Schematic diagram of P-Block module fusion C2F.
Figure 6
Figure 6
Schematic diagram of the efficient multi-scale attention module of EMA.
Figure 7
Figure 7
Schematic diagram of Triplet Attention ternary attention mechanism module.
Figure 8
Figure 8
LSKA Large Separable Kernel Attention Module.
Figure 9
Figure 9
Schematic diagram of SimSPPF- LSKA feature pyramid structure.
Figure 10
Figure 10
Loss map for model training and validation.
Figure 11
Figure 11
Comparison test results of lightweight P-Block with the original model.
Figure 12
Figure 12
Comparison results of different optimization functions.
Figure 13
Figure 13
Testing of different models in the detection system.
Figure 14
Figure 14
Some test results of the outdoor inspection system.
See this image and copyright information in PMC

References

    1. Akkem Y., Biswas S. K., Varanasi A. (2023). Smart farming using artificial intelligence: A review. Eng Appl Artif Intell. 120, 105899. doi: 10.1016/j.engappai.2023.105899 - DOI
    1. Bao J., Li S., Wang G., Xiong J., Li S. (2023). Improved YOLOV8 network and application in safety helmet detection. J. Physics: Conf. Ser. 2632 (1), 012012. doi: 10.1088/1742-6596/2632/1/012012 - DOI
    1. Basha S. H. S., Dubey S. R., Pulabaigari V., Mukherjee S. (2020). Impact of fully connected layers on performance of convolutional neural networks for image classification. Neurocomputing 378, 112–119. doi: 10.1016/j.neucom.2019.10.008 - DOI
    1. Chen J., Kao S., He H., Zhuo W., Wen S., Lee C., et al. . (2023). Run, don't walk: chasing higher FLOPS for faster neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 12021–12031. doi: 10.1109/CVPR52729.2023.01157 - DOI
    1. Cubero S., Lee W. S., Aleixos N., et al. . (2016). Automated systems based on machine vision for inspecting citrus fruits from the field to postharvest—a review. Food Bioprocess Technol. 9, 1623–1639. doi: 10.1007/s11947-016-1767-1 - DOI