CHERRY FRUITLET DETECTION USING YOLOV5 OR YOLOV8?

Authors

  • Ilmars Apeinans Institute of Engineering, Rezekne Academy of Technologies (LV)
  • Marks Sondors Institute of Engineering, Rezekne Academy of Technologies (LV)
  • Lienīte Litavniece Research Institute for Business and Social Processes, Rezekne Academy of Technologies (LV)
  • Sergejs Kodors Institute of Engineering, Rezekne Academy of Technologies (LV)
  • Imants Zarembo Institute of Engineering, Rezekne Academy of Technologies (LV)
  • Daina Feldmane Institute of Horticulture (LatHort) (LV)

DOI:

https://doi.org/10.17770/etr2024vol2.8013

Keywords:

Agriculture 5.0, artificial intelligence, deep learning, yield estimation

Abstract

Agriculture 5.0 incorporates autonomous decision-making systems in order to make agriculture more productive. Our study is related to the development of the autonomous orchard monitoring system using unnamed aerial vehicles for automatic fruiting assessment and yield forecasting. Respectively, artificial intelligence must be developed to count fruits in an orchard. The modern solutions are mainly data-based. Therefore, we collected and annotated cherry dataset with natural images (CherryBBCH81) for neural network training. The goal of the experiment was to select the optimal “You Look Only Once” (YOLO) model for the rapid development of fruit detection. Our experiment showed that YOLOv5m provided better results for CherryBBCH81 – mean average precision (mAP) at 0.5 0.886 in comparison with YOLOv8m mAP@0.5 0.870. However, additional tests with dataset Pear640 showed that YOLOv8m can outperform YOLOv5m: 0.951 vs 0.943 (mAP@0.5).


Supporting Agencies
Latvian Council of Science, project “Development of autonomous unmanned aerial vehicles based decision-making system for smart fruit growing”, project No. lzp-2021/1-0134.

Downloads

Download data is not yet available.

References

Fresh Cherries Market – Forecast (2023 - 2028). 2021. [Online]. Available: https://www.industryarc.com/Research/Fresh-Cherries-Market-Research-511079 [Accessed: Dec. 12, 2023]

K. Ragazou, A. Garefalakis, E. Zafeiriou and I. Passas, “Agriculture 5.0: A new strategic management mode for a cut cost and an energy efficient agriculture sector,” Energies, vol. 15, no. 9, p. 3113, Apr. 2022, https://doi.org/10.3390/en15093113.

A. Ahmad, R. Damaševičius, Agriculture 5.0 and Remote Sensing. Encyclopedia. 2023. [Online]. Available: https://encyclopedia.pub/entry/11655 [Accessed: Nov. 6, 2023]

I. Zarembo, S. Kodors, I. Apeināns, G. Lācis, D. Feldmane and E. Rubauskis, “DIGITAL TWIN: ORCHARD MANAGEMENT USING UAV”, ETR, vol. 1, pp. 247–251, Jun. 2023, https://doi.org/10.17770/etr2023vol1.7290.

V. Vijayakumar, Y. Ampatzidis and L. Costa, ‘Tree-level citrus yield prediction utilizing ground and aerial machine vision and machine learning’, Smart Agricultural Technology, vol. 3, p. 100077, Feb. 2023. https://doi.org/10.1016/j.atech.2022.100077

C. B. MacEachern, T. J. Esau, A. W. Schumann, P. J. Hennessy and Q. U. Zaman, ‘Detection of fruit maturity stage and yield estimation in wild blueberry using deep learning convolutional neural networks’, Smart Agricultural Technology, vol. 3, p. 100099, Feb. 2023. https://doi.org/10.1016/j.atech.2022.100099

P. Li, J. Zheng, P. Li, H. Long, M. Li and L. Gao, “Tomato Maturity Detection and Counting Model Based on MHSA-YOLOv8,” Sensors, vol. 23, no. 15, p. 6701, Jul. 2023, https://doi.org/10.3390/s23156701.

T. Dao, N. Nguyen and V. Nguyen, “CNN-YOLOV8 - Based Tomato Quality Inspection System - a case study in Vietnam”, SSRG International Journal of Electrical and Electronics Engineering, 10(7), 31–40, 2023, https://doi.org/10.14445/23488379/ijeee-v10i7p103

X. Yue, K. Qi, X. Na, Y. Zhang, Y. Liu and C. Liu, “Improved YOLOv8-Seg Network for Instance Segmentation of Healthy and Diseased Tomato Plants in the Growth Stage,” Agriculture, vol. 13, no. 8, p. 1643, Aug. 2023, https://doi.org/10.3390/agriculture13081643.

S. Kodors, M. Sondors, G. Lācis, E. Rubauskis, I. Apeināns and I. Zarembo, “RAPID PROTOTYPING OF PEAR DETECTION NEURAL NETWORK WITH YOLO ARCHITECTURE IN PHOTOGRAPHS”, ETR, vol. 1, pp. 81–85, Jun. 2023, https://doi.org/10.17770/etr2023vol1.7293.

G. Zhao, Y. Gao, S. Gao, Y. Xu, J. Liu, C. Sun, Y. Gao, S. Liu, Z. Chen and L. Jia, “The Phenological Growth Stages of Sapindus mukorossi According to BBCH Scale,” Forests, vol. 10, no. 6, p. 462, May 2019, https://doi.org/10.3390/f10060462.

lzp-2021/1-0134, Cfruitlets81-640, 2023. [Online]. Available: https://www.kaggle.com/datasets/projectlzp201910094/cfruitlets81-640 [Accessed: Nov 12, 2023]

lzp-2021/1-0134, Pear640, 2023. [Online]. Available: https://www.kaggle.com/datasets/projectlzp201910094/pear640[Accessed: Nov 12, 2023]

Ultralytics, YOLOv5-7.0 GitHub repository. [Online] Available: https://github.com/ultralytics/yolov5 [Accessed: Nov 15, 2023]

Ultralytics, YOLOv8 GitHub repository. [Online] Available: https://github.com/ultralytics/ultralytics [Accessed: Nov 15, 2023]

Downloads

Published

2024-06-22

Issue

Vol. 2 (2024): Environment. Technology. Resources. Proceedings of the 15th International Scientific and Practical Conference. Volume 2

Section

Information Technologies

License

Copyright (c) 2024 Ilmars Apeinans, Marks Sondors, Lienīte Litavniece, Sergejs Kodors, Imants Zarembo, Daina Feldmane

Creative Commons License

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

How to Cite

[1]
I. Apeinans, M. Sondors, L. Litavniece, S. Kodors, I. Zarembo, and D. Feldmane, “CHERRY FRUITLET DETECTION USING YOLOV5 OR YOLOV8?”, ETR, vol. 2, pp. 29–33, Jun. 2024, doi: 10.17770/etr2024vol2.8013.