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 Sep 26:15:1399872.
doi: 10.3389/fpls.2024.1399872. eCollection 2024.

Estimation of sorghum seedling number from drone image based on support vector machine and YOLO algorithms

Hongxing Chen  1   2 , Hui Chen  1   2 , Xiaoyun Huang  1   2 , Song Zhang  1   2 , Shengxi Chen  1   2 , Fulang Cen  3 , Tengbing He  1   2 , Quanzhi Zhao  3 , Zhenran Gao  1   2
Affiliations

Estimation of sorghum seedling number from drone image based on support vector machine and YOLO algorithms

Hongxing Chen et al. Front Plant Sci. .

Abstract

Accurately counting the number of sorghum seedlings from images captured by unmanned aerial vehicles (UAV) is useful for identifying sorghum varieties with high seedling emergence rates in breeding programs. The traditional method is manual counting, which is time-consuming and laborious. Recently, UAV have been widely used for crop growth monitoring because of their low cost, and their ability to collect high-resolution images and other data non-destructively. However, estimating the number of sorghum seedlings is challenging because of the complexity of field environments. The aim of this study was to test three models for counting sorghum seedlings rapidly and automatically from red-green-blue (RGB) images captured at different flight altitudes by a UAV. The three models were a machine learning approach (Support Vector Machines, SVM) and two deep learning approaches (YOLOv5 and YOLOv8). The robustness of the models was verified using RGB images collected at different heights. The R2 values of the model outputs for images captured at heights of 15 m, 30 m, and 45 m were, respectively, (SVM: 0.67, 0.57, 0.51), (YOLOv5: 0.76, 0.57, 0.56), and (YOLOv8: 0.93, 0.90, 0.71). Therefore, the YOLOv8 model was most accurate in estimating the number of sorghum seedlings. The results indicate that UAV images combined with an appropriate model can be effective for large-scale counting of sorghum seedlings. This method will be a useful tool for sorghum phenotyping.

Keywords: SVM; UAV; YOLO; seedling; sorghum.

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
Location Map of the Study Area.
Figure 2
Figure 2
YOLOv5 model structure.
Figure 3
Figure 3
YOLOv8 model structure.
Figure 4
Figure 4
Color histogram of sorghum, soil in sorghum fields: (A) EXG index segmentation, (B) EXR index segmentation, (C) EXG-EXR index segmentation, (D) Cg index segmentation, (E) GBDI index segmentation, (F) NGBDI index segmentation, (G) NGRDI index segmentation, (H) S-component color segmentation.
Figure 5
Figure 5
Otsu segmentation results under different color characteristics: (A) Threshold segmentation under EXG index, (B) Threshold segmentation under EXR index, (C) Threshold segmentation under EXG-EXR index, (D) Threshold segmentation under Cg index, (E) Threshold segmentation under GBDI index, (F) Threshold segmentation under NGBDI index, (G) Threshold segmentation under NGRDI index, (H) Threshold segmentation under EXG S-component.
Figure 6
Figure 6
SVM model detection and counting of sorghum seedlings. (A, D, G) Original images at heights of 15 m, 30 m, and 45 m. (B, E, H) The segmentation results of EXG at heights of 15 m, 30 m, and 45 m. (C, F, I) The recognition results of SVM at heights of 15 m, 30 m, and 45 m.
Figure 7
Figure 7
YOLOv5 and YOLOv8 model detection and counting of sorghum seedlings. (A, D, G) Original images at heights of 15 m, 30 m, and 45 m. (B, E, H): The recognition effect diagrams of YOLOv5 at heights of 15 m, 30 m, and 45 m. (C, F, I) The recognition effect diagrams of YOLOv8 at heights of 15 m, 30 m, and 45 m.
Figure 8
Figure 8
YOLOv5 and YOLOv8 Model results. The Epoch refers to one complete traverse of the model over the entire training dataset.
Figure 9
Figure 9
The R2 results of SVM, YOLOv5, and YOLOv8 at heights of 15 m, 30 m, and 45 m: (A) The R2 results for the three models at a height of 15 m, (B) The R2 results for the three models at a height of 30 m, (C) The R2 results for the three models at a height of 45 m.
Figure 10
Figure 10
Estimation of the number of seedlings emerging.
See this image and copyright information in PMC

References

    1. Ahmed F., Al-Mamun H. A., Bari A. H., Hossain E., Kwan P. (2012). Classification of crops and weeds from digital images: A support vector machine approach. Crop Prot. 40, 98–104. doi: 10.1016/j.cropro.2012.04.024 - DOI
    1. Asiri Y. (2023). Unmanned aerial vehicles assisted rice seedling detection using shark smell optimization with deep learning model. Phys. Commun-Amst. 59, 102079. doi: 10.1016/j.phycom.2023.102079 - DOI
    1. Bagheri N. (2017). Development of a high-resolution aerial remote-sensing system for precision agriculture. Int. J. Remote. Sens. 38, 2053–2065. doi: 10.1080/01431161.2016.1225182 - DOI
    1. Barreto A., Lottes P., Yamati F. R. I., Baumgarten S., Wolf N. A., Stachniss C., et al. . (2021). Automatic UAV-based counting of seedlings in sugar-beet field and extension to maize and strawberry. Comput. Electron. Agr. 191, 106493. doi: 10.1016/j.compag.2021.106493 - DOI
    1. Cheng H. D., Jiang X. H., Sun Y., Wang J. (2001). Color image segmentation: advances and prospects. Pattern. Recogn. 34, 2259–2281. doi: 10.1016/S0031-3203(00)00149-7 - DOI

LinkOut - more resources