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
. 2023 Dec 8:14:1139666.
doi: 10.3389/fpls.2023.1139666. eCollection 2023.

An improved Deeplab V3+ network based coconut CT image segmentation method

Qianfan Liu  1 , Yu Zhang  1 , Jing Chen  2 , Chengxu Sun  3 , Mengxing Huang  4 , Mingwei Che  4 , Chun Li  4 , Shenghuang Lin  2
Affiliations

An improved Deeplab V3+ network based coconut CT image segmentation method

Qianfan Liu et al. Front Plant Sci. .

Abstract

Due to the unique structure of coconuts, their cultivation heavily relies on manual experience, making it difficult to accurately and timely observe their internal characteristics. This limitation severely hinders the optimization of coconut breeding. To address this issue, we propose a new model based on the improved architecture of Deeplab V3+. We replace the original ASPP(Atrous Spatial Pyramid Pooling) structure with a dense atrous spatial pyramid pooling module and introduce CBAM(Convolutional Block Attention Module). This approach resolves the issue of information loss due to sparse sampling and effectively captures global features. Additionally, we embed a RRM(residual refinement module) after the output level of the decoder to optimize boundary information between organs. Multiple model comparisons and ablation experiments are conducted, demonstrating that the improved segmentation algorithm achieves higher accuracy when dealing with diverse coconut organ CT(Computed Tomography) images. Our work provides a new solution for accurately segmenting internal coconut organs, which facilitates scientific decision-making for coconut researchers at different stages of growth.

Keywords: CBAM; CT images; DASPP; RRM; coconut; semantic segmentation.

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
Coconut collection area situation.
Figure 2
Figure 2
Example of coconut scan.
Figure 3
Figure 3
Example of CT image of coconut.
Figure 4
Figure 4
Example of the corresponding labeled diagram.
Figure 5
Figure 5
Diagram of the improved model structure.
Figure 6
Figure 6
Diagram of DASPP module.
Figure 7
Figure 7
The structure of CBAM attention mechanism.
Figure 8
Figure 8
Structure diagram of RRM module.
Figure 9
Figure 9
Flow chart of CT image segmentation based on improved Deeplab V3+ network.
Figure 10
Figure 10
Semantic segmentation effect of different models.
Figure 11
Figure 11
Example of single class organ extraction.
See this image and copyright information in PMC

References

    1. Arumugam T., Hatta M. A. M. (2022). Improving coconut using modern breeding technologies: Challenges and opportunities. Plants 11, 3414. doi: 10.3390/plants11243414 - DOI - PMC - PubMed
    1. Li B., Wang R., Ma J., Xu W. (2020). Research on crop water status monitoring and diagnosis by terahertz imaging. Front. Phys. 8. doi: 10.3389/fphy.2020.571628 - DOI
    1. Ni X., Li C., Jiang H., Takeda F. (2020). Deep learning image segmentation and extraction of blueberry fruit traits associated with harvestability and yield. Horticulture Res. 7, 110. doi: 10.1038/s41438-020-0323-3 - DOI - PMC - PubMed
    1. Qin X., Zhang Z., Huang C., Gao C., Dehghan M., Jagersand M. (2019). Basnet: Boundary-aware salient object detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). (Long Beach, CA, USA: ). 7479–7489. doi: 10.1109/CVPR.2019.00766 - DOI
    1. Singh N., Tewari V., Biswas P., Dhruw L., Pareek C., Singh H. D. (2022). Semantic segmentation of in-field cotton bolls from the sky using deep convolutional neural networks. Smart Agric. Technol. 2, 100045. doi: 10.1016/j.atech.2022.100045 - DOI

LinkOut - more resources