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
. 2021 May 31;21(11):3813.
doi: 10.3390/s21113813.

Orchard Mapping with Deep Learning Semantic Segmentation

Athanasios Anagnostis  1   2 , Aristotelis C Tagarakis  1 , Dimitrios Kateris  1 , Vasileios Moysiadis  1 , Claus Grøn Sørensen  3 , Simon Pearson  4 , Dionysis Bochtis  1   5
Affiliations

Orchard Mapping with Deep Learning Semantic Segmentation

Athanasios Anagnostis et al. Sensors (Basel). .

Abstract

This study aimed to propose an approach for orchard trees segmentation using aerial images based on a deep learning convolutional neural network variant, namely the U-net network. The purpose was the automated detection and localization of the canopy of orchard trees under various conditions (i.e., different seasons, different tree ages, different levels of weed coverage). The implemented dataset was composed of images from three different walnut orchards. The achieved variability of the dataset resulted in obtaining images that fell under seven different use cases. The best-trained model achieved 91%, 90%, and 87% accuracy for training, validation, and testing, respectively. The trained model was also tested on never-before-seen orthomosaic images or orchards based on two methods (oversampling and undersampling) in order to tackle issues with out-of-the-field boundary transparent pixels from the image. Even though the training dataset did not contain orthomosaic images, it achieved performance levels that reached up to 99%, demonstrating the robustness of the proposed approach.

Keywords: computer vision; deep learning; orchard mapping; orthomosaic; precision agriculture; semantic segmentation.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Architecture of the modified U-net network implemented in the approach.
Figure 2
Figure 2
Process flow of the proposed methodology for creating segmentation predictions. FN: false negative; FP: false positive.
Figure 3
Figure 3
Channel deconstructing of (a) RGB, (b) HSV, and (c) fused images.
Figure 4
Figure 4
Image color transformations used in the study: (a) RGB image, (b) EQ image, (c) CLAHE image, (d) HSV colorspace image, (e) 6-channel RGB and HSV fused image, and (f) 6-channel CLAHE and HSV fused image.
Figure 4
Figure 4
Image color transformations used in the study: (a) RGB image, (b) EQ image, (c) CLAHE image, (d) HSV colorspace image, (e) 6-channel RGB and HSV fused image, and (f) 6-channel CLAHE and HSV fused image.
Figure 5
Figure 5
Learning plot with training and validation accuracy.
Figure 6
Figure 6
Examples of false positive and false negative segmentation predicted by the developed system (left) as compared to the real segmentation (right).
Figure 7
Figure 7
Results of indicative RGB images covering a range of different conditions.
Figure 8
Figure 8
Undersampled orthomosaic of an orchard with large- to medium-sized canopies (left) and the segmentation predicted by the model (right).
Figure 9
Figure 9
Undersampled orthomosaic of an orchard with young trees featuring small-sized canopies (left) and the segmentation predicted by the model (right).
Figure 10
Figure 10
Undersampled orthomosaic of an orchard with small canopies, not treated for weeds (left), and the segmentation predicted by the model (right).
Figure 11
Figure 11
Complete orthomosaic of a study orchard with trees with small-sized canopies, not treated for weeds (left), and the segmentation predicted by the model (right).
See this image and copyright information in PMC

References

    1. Gemtos T., Fountas S., Tagarakis A., Liakos V. Precision Agriculture Application in Fruit Crops: Experience in Handpicked Fruits. Procedia Technol. 2013;8:324–332. doi: 10.1016/j.protcy.2013.11.043. - DOI
    1. Mulla D.J. Twenty five years of remote sensing in precision agriculture: Key advances and remaining knowledge gaps. Biosyst. Eng. 2013;114:358–371. doi: 10.1016/j.biosystemseng.2012.08.009. - DOI
    1. Berni J.A.J., Zarco-Tejada P.J., Suárez L., González-Dugo V., Fereres E. Remote sensing of vegetation from UAV platforms using lightweight multispectral and thermal imaging sensors. Int. Arch. Photogramm. Remote Sens. Spat. Inform. Sci. 2009;38:6.
    1. Maresma A., Chamberlain L., Tagarakis A., Kharel T., Godwin G., Czymmek K.J., Shields E., Ketterings Q.M. Accuracy of NDVI-derived corn yield predictions is impacted by time of sensing. Comput. Electron. Agric. 2020;169 doi: 10.1016/j.compag.2020.105236. - DOI
    1. Messina G., Modica G. Applications of UAV Thermal Imagery in Precision Agriculture: State of the Art and Future Research Outlook. Remote. Sens. 2020;12:1491. doi: 10.3390/rs12091491. - DOI

LinkOut - more resources