Application of YOLOv8L Deep Learning in Robotic Harvesting of Persimmon (Diospyros kaki)


Abstract views: 236 / PDF downloads: 123

Authors

  • Erhan KAHYA Tekirdağ Namık Kemal Üniversitesi, Teknik Bilimler Meslek Yüksekokulu, Elektronik ve Otomasyon Bölümü, Kontrol ve Otomasyon Teknolojisi Programı, Tekirdağ https://orcid.org/0000-0001-7768-9190
  • Fatma Funda ÖZDÜVEN Tekirdağ Namık Kemal Üniversitesi, Teknik Bilimler Meslek Yüksekokulu Bitkisel ve Hayvansal Üretim Bölümü, Seracılık Programı, Tekirdağ https://orcid.org/0000-0003-4286-8943
  • Berat Can CEYLAN Tekirdağ Namık Kemal Üniversitesi, Teknik Bilimler Meslek Yüksekokulu, Bilgisayar Teknolojileri Bölümü, Bilgisayar Programcılığı Programı, Tekirdağ https://orcid.org/0009-0005-1414-179X

DOI:

https://doi.org/10.5281/zenodo.8320097

Keywords:

Persimmon, YOLOv8, classification

Abstract

Deep learning has been a branch of science that has been used by many researchers and has gained popularity in recent years. Deep learning techniques perform better than traditional methods by providing high accuracy in analyzing and processing agricultural data. Therefore, the use of deep learning techniques in agriculture is increasing. The persimmon used in this study is a fruit tree belonging to the Ebenaceae family and is cultivated in various regions of Turkey, including the Trabzon region. The persimmon harvest is typically done during the fall season when the fruits reach optimal maturity. It is recommended to harvest the persimmon when they are hard but slightly soft to the touch. In this study, using the deep learning method, the classification was made by considering the color feature of the fruit. The aim here is to develop a method to be used in robotic harvesting systems. YOLOv8L was chosen as the method. The metric values of the model were analyzed and it was observed that the 'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5' and 'metrics/mAP_0.5:0.95' values of the model increased as the number of epochs increased. In the last epoch, precision was measured at about 71%, recall was measured at 79%, mAP_0.5 was measured at about 84% and mAP_0.5:0.95 was measured at about 76%. These values indicated that the model was able to detect and classify objects with high accuracy in the validation set. Measured value Size: 640x640, Batch: 16, Epoch: 102, Algorithm: YOLOv8L. It was concluded that YOLOv8L was the best detection model to be used in robotic persimmon harvesting to separate the persimmon from branch.

References

Afonso, M., Fonteijn, H., Fiorentin, F.S., Lensink, D., Mooij, M., Faber, N., Wehrens, R., 2020. Tomato fruit detection and counting in greenhouses using deep learning. Frontiers in Plant Science, 11: 571299.

Aktaş, H., 2022. Classification of pistachios based on outer shell color using deep learning. Niğde Ömer Halisdemir University Journal of Engineering Sciences, 11(3): 461–466.

Arserim, M.A., Usta, A., 2023. Object detection by deep learning approach using images taken from unmanned aerial vehicle. Dicle University Journal of Engineering, 14(1): 9-15.

Aydın, S., Taşyürek, M., Öztürk, C., 2021. Air pollution prediction for Central Anatolia Region and its surroundings with deep learning method. European Journal of Science and Technology, Special Issue 29: 168-173.

Bengio, Y., 2009. Learning deep architectures for AI. Foundations and Trends in Machine Learning, 2(1): 1–27.

Çetiner, H., Çetiner, I., 2022. Classification of citrus diseases with convolutional neural network based deep learning model. Bitlis Eren University Journal of Science, 11(1): 352–368.

DeLuna, R.G., Dadios, E.P., Bandala, A.A., Vicerra, R.R.P., 2019. Size classification of tomato fruit using thresholding, machine learning and deep learning techniques. Agrivita, 41(3): 586–596.

Deng, L., Yu, D., 2014. Deep learning: methods and applications. Foundations And Trends® In Signal Processing, 7(3–4): 197-387.

Eren, H.A., Okyay, S., Adar, N., 2021. Adoken: Deep learning based decision support software for MRI. Journal of Engineering Sciences and Design, 9(2): 406–413.

He, K., Zhang, X., Ren, S., Sun, J., 2016. Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Conference Proceedings Book, December, pp. 770–778.

Karasulu, B., Yücalar, F., Borandaǧ, E., 2022. A hybrid approach based on deep learning for gender recognition using human ear images. Journal of the Faculty of Engineering and Architecture of Gazi University, 37(3): 1579–1594.

Kirişoğlu, S., Kotan, B., Kotan, K., 2022. Network traffic classification analysis with multi-layer sensor. Düzce University Journal of Science Technology, 10(2): 837–846.

Kuzucu F.C., Kaynaş, K., 2004. Chemical and Physiological changes in persimmons (Diospyros kaki L.) harvested in different time periods. Bahçe, 33(1-2): 17 – 25.

Liakos, K.G., Busato, P., Moshou, D., Pearson, S., Bochtis, D., 2018. Machine learning in agriculture: A review. Sensors (Basel), 18(8):2674.

Mu, Y., Chen, T.S., Ninomiya, S., Guo, W., 2020. Intact detection of highly occluded immature tomatoes on plants using deep learning techniques. Sensors, 20(10): 2984.

Mutha, S.A., Shah, A.M., Ahmed, M.Z., 2021. Maturity detection of tomatoes using deep learning. SN Computer Science, 2(6): 441.

Onur, S., 1990. Trabzon hurması. Derim, 7(1): 4-46.

Özcan, M., 2018. The problems and future of persimmon (Diospyros Kaki L.) cultivation in Turkey. Black Sea Journal of Agriculture, 1(2): 38-43.

Özkan, H.U., Can, H.Z., 2013. Research on the quality properties of persimmon (Diospyros Kaki L.) fruits at different harvest stages. Journal of Agriculture Faculty of Ege University, 50(2): 137-144.

Sa, I., Ge, Z., Dayoub, F., Upcroft, B., Perez, T., Mccool, C., 2016. Deepfruits: A fruit detection system using deep neural networks. Sensors, 16(8).

Seo, D., Cho, B.H., Kim, K., 2012. Development of monitoring robot system for tomato fruits in hydroponic greenhouses. Agronomy, 11(11): 2211.

Simonyan, K., Zisserman, A., 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. (http://arxiv.org/abs/1409.1556).

Şentürk, T., Latifoğlu, F., 2023. Deep learning based methods for biomedical image segmentation: A review. Dicle University Journal of the Institute of Natural and Applied Science, 12(1): 161–187.

Tan, Z., Karaköse, M., 2022. Comparative analysis for autonomous path planning approaches based on deep reinforcement learning in dynamic environments. Journal of Engineering Science of Adıyaman University, 9(16): 248–262.

Tuzcu, Ö., Yıldırım, B., 2000. Trabzon hurması (Diospyros kaki) ve Yetiştiriciliği. Tübitak Tarp Yayınları, Adana.

Yaman, O., Tuncer, T., 2022. Deep feature extraction and machine learning method for leaf disease detection in plants. Fırat University Journal of Engineering Science, 34(1): 123–132.

Zhang, L., Jia, J., Gui, G., Hao, X., Gao, W., Wang, M., 2018. Deep learning based improved classification system for designing tomato harvesting robot. IEEE Access, 6: 67940-67950

Downloads

Published

2023-09-24

How to Cite

KAHYA, E. ., ÖZDÜVEN, F. F. ., & CEYLAN, B. C. . (2023). Application of YOLOv8L Deep Learning in Robotic Harvesting of Persimmon (Diospyros kaki). ISPEC Journal of Agricultural Sciences, 7(3), 587–601. https://doi.org/10.5281/zenodo.8320097

Issue

Section

Articles