Abstract
The use of the YOLOv3 and YOLOv5 algorithms for apple detection in fruit-harvesting robots are compared. It is shown that the YOLOv5 algorithm could detect apples in orchards without additional pre- and post-processing with 97.8% Recall (fruit detection rate), and 3.5% False Positive Rate (FPR). It is much better than YOLOv3 that gives 90.8% Recall and 7.8 FPR when combined with special pre- and post-processing procedures, and then 9.1% Recall and 10.0% FPR without pre- and post-processing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bechar, A., Vigneault, C.: Agricultural robots for field operations: concepts and components. Biosyst. Eng. 149, 94–111 (2016). https://doi.org/10.1016/j.biosystemseng.2016.06.014
Sistler, F.E.: Robotics and intelligent machines in agriculture. IEEE J. Robot. Autom. 3(1), 3–6 (1987). https://doi.org/10.1109/JRA.1987.1087074
Ceres, R., Pons, J., Jiménez, A., MartÃn, J., Calderón, L.: Design and implementation of an aided fruit-harvesting robot (Agribot). Ind. Robot 25(5), 337–346 (1998). https://doi.org/10.1108/01439919810232440
Edan, Y., Han, S.F., Kondo, N.: Automation in agriculture. In: Springer Handbook of Automation, pp. 1095–1128. Springer, Berlin, Heidelberg (2009). https://doi.org/10.1007/978-3-540-78831-7_63
Grift, T., Zhang, Q., Kondo, N., Ting, K.C.: A review of automation and robotics for the bio-industry. J. BioMechatron. Eng. 1(1), 37–54 (2008). https://journal.tibm.org.tw/wp-content/uploads/2013/06/2.-automation-and-robotics-for-the-bio-industry.pdf. Accessed 10 July 2020
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: YOLOv3: an incremental improvement. In: Proceedings of the 31th IEEE Conference on Computer Vision and Pattern Recognition—CVPR 2018, pp. 1–6. Salt Lake City, UT, USA, 18–22 June 2018. https://arxiv.org/abs/1804.02767
Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition—CVPR 2020, Virtual, pp. 10781–10790. 14–19 June 2020. https://arxiv.org/abs/1901.08043
Bochkovskiy, A., Wang, Ch.-Y., Liao, H.-Yu.M.: YOLOv4: optimal speed and accuracy of object detection (2020). https://arxiv.org/abs/2004.10934. Accessed 10 July 2020
Jocher, G., Nishimura, K., Mineeva, T., Vilariño, R.: YOLOv5 (2020). https://github.com/ultralytics/yolov5. Accessed 10 July 2020
Kuznetsova, A., Maleva, T., Soloviev, V.: Using YOLOv3 algorithm with pre- and post-processing for apple detection in fruit-harvesting robot. Agronomy 10(7), 1016 (2020). https://doi.org/10.3390/agronomy10071016
Kuznetsova, A., Maleva, T., Soloviev, V.: Detecting apples in orchards using YOLOv3. In: Gervasi, O., et al. (eds.) ICCSA 2020. LNCS, vol. 12249, pp. 923–934. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58799-4_66
Mao, W.H., Ji, B.P., Zhan, J.C., Zhang, X.C., Hu, X.A.: Apple location method for the apple harvesting robot. In: Proceedings of the 2nd International Congress on Image and Signal Processing—CIPE 2009, pp. 17–19. Tianjin, China, 7–19 October 2009. https://doi.org/10.1109/CISP.2009.5305224
Bulanon, D.M., Kataoka, T.: A fruit detection system and an end effector for robotic harvesting of Fuji apples. Agric. Eng. Int. CIGR J. 12(1), 203–210 (2010). https://cigrjournal.org/index.php/Ejounral/article/view/1285/1319. Accessed 10 July 2020
Wei, X., Jia, K., Lan, J., Li, Y., Zeng, Y., Wang, C.: Automatic method of fruit object extraction under complex agricultural background for vision system of fruit picking robot. Optics 125(12), 5684–5689 (2014). https://doi.org/10.1016/j.ijleo.2014.07.001
Whittaker, A.D., Miles, G.E., Mitchell, O.R.: Fruit location in a partially occluded image. Trans. Am. Soc. Agric. Eng. 30(3), 591–596 (1987). https://doi.org/10.13031/2013.30444
Xie, Z.Y., Zhang, T.Z., Zhao, J.Y.: Ripened strawberry recognition based on Hough transform. Trans. Chin. Soc. Agric. Mach. 38(3), 106–109 (2007)
Xie, Z., Ji, C., Guo, X., Zhu, S.: An object detection method for quasi-circular fruits based on improved Hough transform. Trans. Chin. Soc. Agric. Mach. 26(7), 157–162 (2010)
Kelman, E.E., Linker, R.: Vision-based localization of mature apples in tree images using convexity. Biosyst. Eng. 118(1), 174–185 (2014). https://doi.org/10.1016/j.biosystemseng.2013.11.007
Xie, Z., Ji, C., Guo, X., Zhu, S.: Detection and location algorithm for overlapped fruits based on concave spots searching. Trans. Chin. Soc. Agric. Mach. 42(12), 191–196 (2011)
Zhao, J., Tow, J., Katupitiya, J.: On-tree fruit recognition using texture properties and color data. In: Proceeddings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 263–268. Edmonton, Canada, 2–6 August 2005. https://doi.org/10.1109/IROS.2005.1545592
Rakun, J., Stajnko, D., Zazula, D.: Detecting fruits in natural scenes by using spatial-frequency based texture analysis and multiview geometry. Comput. Electron. Agric. 76(1), 80–88 (2011). https://doi.org/10.1016/j.compag.2011.01.007
Parrish, E.A., Goksel, J.A.K.: Pictorial pattern recognition applied to fruit harvesting. Trans. Am. Soc. Agric. Eng. 20(5), 822–827 (1977). https://doi.org/10.13031/2013.35657
Sites, P.W., Delwiche, M.J.: Computer vision to locate fruit on a tree. Trans. Am. Soc. Agric. Eng. 31(1), 257–263 (1988). https://doi.org/10.13031/2013.30697v
Bulanon, D.M., Kataoka, T., Okamoto, H., Hata, S.: Development of a real-time machine vision system for apple harvesting robot. In: Proceedings of the Society of Instrument and Control Engineers Annual Conference, Sapporo, pp. 595–598. Japan, 4–6 August 2004. https://doi.org/10.11499/sicep.2004.0_108_5
Seng, W.C., Mirisaee, S.H.: A new method for fruits recognition system. In: Proceedings of the 2009 International Conference on Electrical Engineering and Informatics—ICEEI 2009, vol. 1, pp. 130–134. Selangor, Malaysia, 5–7 August 2009. https://doi.org/10.1109/ICEEI.2009.5254804
Wachs, J.P., Stern, H.I., Burks, T., Alchanatis, V.: Low and high-level visual feature-based apple detection from multi-modal images. Precis. Agric. 11, 717–735 (2010). https://doi.org/10.1007/s11119-010-9198-x
Tao, Y., Zhou, J.: Automatic apple recognition based on the fusion of color and 3D feature for robotic fruit picking. Comput. Electron. Agric. 142(A), 388–396 (2017). https://doi.org/10.1016/j.compag.2017.09.019
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems 25—NIPS 2012, pp. 1–9. Harrahs and Harveys, Lake Tahoe, Canada, 3–8 December 2012. https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf. Accessed 10 July 2020
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations—ICLR 2015, pp. 1–14. San Diego, CA, USA, 7–9 May 2015. https://arxiv.org/abs/1409.1556
Williams, H.A.M., Jones, M.H., Nejati, M., Seabright, M.J., MacDonald, B.A.: Robotic kiwifruit harvesting using machine vision, convolutional neural networks, and robotic arms. Biosyst. Eng. 181, 140–156 (2019). https://doi.org/10.1016/j.biosystemseng.2019.03.007
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition—CVPR 2016, pp. 779–788. Las Vegas, NV, USA, 26 June–1 July 2016. https://arxiv.org/abs/1506.02640
Tian, Y., Yang, G., Wang, Zh., Wang, H., Li, E., Liang, Z.: Apple detection during different growth stages in orchards using the improved YOLO-V3 model. Comput. Electron. Agric. 157, 417–426 (2019). https://doi.org/10.1016/j.compag.2019.01.012
Tian, Y., Yang, G., Wang, Zh., Li, E., Liang, Z.: Detection of Apple lesions in orchards based on deep learning methods of CycleGAN and YOLO-V3-Dense. J. Sens., Special Issue, Sensors in Precision Agriculture for the Monitoring of Plant Development and Improvement of Food Production, 1–14 (2019). https://doi.org/10.1155/2019/7630926
Huang, G., Liu, Zh., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition—CVPR 2017, pp. 1–9. Honolulu, HI, USA, 22–25 July 2017. https://arxiv.org/abs/1608.06993
Kang, H., Chen, C.: Fruit detection, segmentation and 3D visualization of environments in apple orchards. Comput. Electron. Agric. 171, 105302 (2020). https://doi.org/10.1016/j.compag.2020.105302
Kang, H., Chen, C.: Fast implementation of real-time fruit detection in apple orchards using deep learning. Comput. Electron. Agric. 168, 105108 (2020). https://doi.org/10.1016/j.compag.2019.105108
Fawcett, T.: An introduction to ROC analysis. Pattern Recogn. Lett. 27(8), 861–874 (2006). https://doi.org/10.1016/j.patrec.2005.10.010
Acknowledgements
The reported study was supported by RFBR, research project 18-00-01103.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Kuznetsova, A., Maleva, T., Soloviev, V. (2021). YOLOv5 versus YOLOv3 for Apple Detection. In: Kravets, A.G., Bolshakov, A.A., Shcherbakov, M. (eds) Cyber-Physical Systems: Modelling and Intelligent Control. Studies in Systems, Decision and Control, vol 338. Springer, Cham. https://doi.org/10.1007/978-3-030-66077-2_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-66077-2_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-66076-5
Online ISBN: 978-3-030-66077-2
eBook Packages: EngineeringEngineering (R0)