RAPID PROTOTYPING OF PEAR DETECTION NEURAL NETWORK WITH YOLO ARCHITECTURE IN PHOTOGRAPHS
DOI:
https://doi.org/10.17770/etr2023vol1.7293Keywords:
artificial intelligence, deep learning, smart horticulture, yield estimationAbstract
Fruit yield estimation and forecasting are essential processes for data-based decision-making in agribusiness to optimise fruit-growing and marketing operations. The yield forecasting is based on the application of historical data, which was collected in the result of periodic yield estimation. Meanwhile, the object detection methods and regression models are applied to calculate yield per tree. The application of powerful neural network architectures for rapid prototyping is a common approach of modern artificial intelligence engineering. Meanwhile, the most popular object detection solution is YOLO architecture. Our project team collected the dataset of fruiting pear tree photographs (Pear640) and trained YOLOv5m with mAP@0.5 95% and mAP@0.5:0.95 56%. The obtained results were compared with other YOLOv5-7.0 and YOLOv7 models and similar studies.
Downloads
References
G. J. Silva, T.M. Souza, R.L. Barbieri and A.C. de Oliveira, “Origin, domestication, and dispersing of pear (Pyrus spp.),” Adv. Agricult., 2014. Available: https://doi.org/10.1155/2014/541097
A. Zarei, J. Erfani-Moghadam and H. Jalilian, “Assessment of variability within and among four Pyrus species using multivariate analysis,” Flora, vol. 250, pp. 27-36, 2019. Available: https://doi.org/10.1016/j.flora.2018.11.016
FAOSTAT, Food and agriculture data. [Online] Available: http://www.fao.org/faostat/[Accessed March 21, 2023].
G. Lācis, I. Kota-Dombrovska, K. Kārkliņa, B. Lāce, “Genetic diversity and relatedness of Latvian Pyrus germplasm assessed by a set of SSR markers,” Proceedings of the Latvian Academy of Sciences. Section B, vol. 76, no. 4 (739), pp. 438–447, 2022. Available: https://doi.org/10.2478/prolas-2022-0068
H. Cheng, L. Damerow, Y. Sun and M. Blanke, “Early Yield Prediction Using Image Analysis of Apple Fruit and Tree Canopy Features with Neural Networks,” J. Imaging, vol. 3, no. 1, p. 6+, Jan. 2017. Available: https://doi.org/10.3390/jimaging3010006
F. Winter, “Modelling the biological and economic development of an apple orchard,” in Proceedings of the III International Symposium on Research and Development on Orchard and Plantation Systems, Montpellier, May 21-26, 1984, France. Place of publication: Acta Hortic, 1986. Available: https://doi.org/10.17660/ActaHortic.1986.160.40
R. Črtomir, C. Urška, T. Stanislav, S. Denis, P. Karmen, M. Pavlovič, V. Marjan, “Application of Neural Networks and Image Visualisation for Early Forecast of Apple Yield,” Erwerbs-Obstbau, vol. 54, pp. 69–76, 2012. Available: https://doi.org/10.1007/s10341-012-0162-y
J. Redmon, S. Divvala, R. Girshick, A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” in Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. Place of publication: IEEE, 2016. Available: https://doi.org/10.1109/CVPR.2016.91
A. Bochkovskiy, C.-Y. Wang, H.-Y. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” arXiv, Apr 23, 2020. [Online] Available: https://arxiv.org/pdf/2004.10934.pdf [Accessed: Mar 17, 2023]
U. Nepal, H. Eslamiat, “Comparing YOLOv3, YOLOv4 and YOLOv5 for Autonomous Landing Spot Detection in Faulty UAVs,” Sensors, vol. 22, no. 2, p. 464, Jan. 2022, Available: https://doi.org/10.3390/s22020464
P. Jiang, D. Ergu, F. Liu, Y. Cai, B. Ma, “A Review of Yolo Algorithm Developments,” Procedia Computer Science, vol. 199, pp. 1066-1073, 2022. Available: https://doi.org/10.1016/j.procs.2022.01.135
C.-Y. Wang, I.-H. Yeh, H.-Y. M. Liao, “You only learn one representation: Unified network for multiple tasks,” arXiv, May 10, 2021. [Online] Available: https://arxiv.org/pdf/2105.04206.pdf
C.-Y. Wang, A. Bochkovskiy, H.-Y. Liao, “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,” arXiv, Jul 6, 2022. Available: https://arxiv.org/pdf/2207.02696.pdf
J. Solawetz, “What is YOLOv8? The Ultimate Guide,” Jan 11, 2023. [Online] Available: https://blog.roboflow.com/whats-new-in-yolov8/ [Accessed: Mar 17, 2023]
L. Wang, Y. Zhao, Z. Xiong, S. Wang, Y. Li, Y. Lan, “Fast and precise detection of litchi fruits for yield estimation based on the improved YOLOv5 model,” Frontiers in Plant Science, vol. 13, 2022. Available: https://doi.org/10.3389/fpls.2022.965425
S. Lyu, R. Li, Y. Zhao, Z. Li, R. Fan, S. Liu, “Green Citrus Detection and Counting in Orchards Based on YOLOv5-CS and AI Edge System,” Sensors, vol. 22, no. 2, p. 576+, 2022. Available: https://doi.org/10.3390/s22020576
L. Fu, Z. Yang, F. Wu, X. Zou, J. Lin, Y. Cao, J. Duan, “YOLO-Banana: A Lightweight Neural Network for Rapid Detection of Banana Bunches and Stalks in the Natural Environment,” Agronomy, vol. 12, no. 2, p. 391+, 2022. Available: https://doi.org/10.3390/agronomy12020391
T.T. Santos, L.L. de Souza, A.A. dos Santos, S. Avila, “Grape detection, segmentation, and tracking using deep neural networks and three-dimensional association,” Computers and Electronics in Agriculture, vol. 170, 2020. Available: https://doi.org/10.1016/j.compag.2020.105247
N. Häni, P. Roy and V. Isler, "MinneApple: A Benchmark Dataset for Apple Detection and Segmentation," in IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 852-858, April 2020. Available: https://doi.org/10.1109/LRA.2020.2965061
lzp-2021/1-0134, Pear640, 2023. [Online]. Available: https://www.kaggle.com/datasets/projectlzp201910094/pear640 [Accessed: Mar 24, 2023]
Ultralytics, YOLOv5-7.0 GitHub repository. [Online] Available: https://github.com/ultralytics/yolov5 [Accessed: Jan 30, 2023]
YOLOv7 GitHub repository. [Online] Available: https://github.com/WongKinYiu/yolov7 [Accessed: Feb 20, 2023]
T.A. Ciarfuglia, I.M. Motoi, L. Saraceni, M. Fawakherji, A. Sanfeliu, D. Nardi, “Weakly and semi-supervised detection, segmentation and tracking of table grapes with limited and noisy data, Computers and Electronics in Agriculture,” vol. 205, 2023. Available: https://doi.org/10.1016/j.compag.2023.107624
M. Sun, L. Xu, X. Chen, Z. Ji, Y. Zheng, W. Jia, “BFP Net: Balanced Feature Pyramid Network for Small Apple Detection in Complex Orchard Environment,” Plant Phenomics, vol. 2022, 2022. Available: https://doi.org/10.34133/2022/9892464
Y. Li, C. Lei, Z. Xue, Z. Zheng, Y. Long, “A Comparison of YOLO Family for Apple Detection and Counting in Orchards,” World Academy of Science, Engineering and Technology, International Journal of Computer and Systems Engineering, vol. 15, no. 5, pp. 334 – 343, 2021. Available: https://publications.waset.org/10012056/a-comparison-of-yolo-family-for-apple-detection-and-counting-in-orchards
H. Sun, B. Wang, J. Xue, “YOLO-P: An efficient method for pear fast detection in complex orchard picking environment,” Frontiers in Plant Science, vol. 13, 2023. Available: https://doi.org/10.3389/fpls.2022.1089454
Y. Li, Y. Rao, X. Jin, Z. Jiang, Y. Wang, T. Wang, F. Wang, Q. Luo, L. Liu, “YOLOv5s-FP: A Novel Method for In-Field Pear Detection Using a Transformer Encoder and Multi-Scale Collaboration Perception,” Sensors, vol. 23, no. 1, p. 30+, Dec. 2022, Available: https://doi.org/10.3390/s23010030
