Abstract
Laborious fruit thinning is required for attaining high-quality Medjoul dates. Thinning automation can significantly reduce labor and improve efficiency. An image processing apparatus developed for robotic Medjoul thinning is presented. Instance segmentation based on Mask R-CNN was applied to identify the fruit bunch components: spikelets and rachis. Motion planning parameters were extracted using the derived masks: rachis center point (RCP), rachis orientation angle, and spikelets remaining length. RCP and rachis orientation angle were computed geometrically, spikelets remaining length was estimated with a convolutional neural network (CNN) and a deep neural network (DNN). Instance segmentation results were accurate, especially for spikelets, for low intersection over union (IoU) (0.3 IoU, fruit determined for thinning identification, spikelets: 98%, rachises: 73%). However, only 66% of the rachises were correctly matched to spikelets. The segmentation of all spikelets and rachises in the images was of medium quality for low IoU (0.3 IoU, F1, spikelets: 0.67, rachis: 0.77), where both precision and recall dropped for higher IoUs. RCP and rachis orientation angle were accurately estimated (0.3 IoU, error, RCP: 2.2 cm, rachis orientation angle: 5.0°). Spikelets remaining length estimation using CNN resulted in better performance than DNN (0.3 IoU, error, CNN: 19.7%, DNN: 24.6%). Spikelets segmentation results are suitable for thinning automation. However, rachis segmentation and matching the rachis and spikelets may still require human intervention during run-time. RCP and rachis orientation angle estimation errors are acceptable, while spikelets remaining length estimation errors are acceptable only for preliminary motion planning and mandate additional tuning during motion execution.
Similar content being viewed by others
Data availability
The data collected within the current work is available online (Shoshan & Berman, 2021).
Code availability
The algorithms developed in the current work are based on available code as detailed in the text.
Notes
Mask R-CNN pre-trained weights based on the ‘COCO’ dataset can be easily loaded into the model from https://github.com/matterport.
References
Abdulla, W. (2017). Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow. GitHub repository. Github. Retrieved September 15, 2020, from https://github.com/matterport/Mask_RCNN
Aljanobi, A. A., Al-Hamed, S. A., & Al-Suhaibani, S. A. (2010). A setup of mobile robotic unit for fruit harvesting. In 19th international workshop on robotics in Alpe-Adria-Danube Region (RAAD 2010), Budapest, 2010, pp. 105-108. https://doi.org/10.1109/RAAD.2010.5524602
Altaheri, H., Alsulaiman, M., & Muhammad, G. (2019). Date fruit classification for robotic harvesting in a natural environment using deep learning. IEEE Access, 7, 117115–117133. https://doi.org/10.1109/ACCESS.2019.2936536
Bar-Shira, O., Cohen, Y., Shoshan, T., Sadowky, A., Cohen, Y., Bechar, A., Berman, S. (2019). Learning motion parameters for a Medjoul-date thinning robot. In XXXVIII CIOSTA & CIGR section V conference.
Barth, R., IJsselmuiden, J., Hemming, J., & Van Henten, E. J. (2018). Data synthesis methods for semantic segmentation in agriculture: A Capsicum annuum dataset. Computers and Electronics in Agriculture, 144, 284–296. https://doi.org/10.1016/j.compag.2017.12.001
Bechar, A., Bloch, V., Finkelshtain, R., Levi, S., Hoffman, A., Egozi, H., & Schmilovitch, Z. (2014). Visual servoing methodology for selective tree pruning by human-robot collaborative system. In International conference of agricultural engineering (AgEng).
Bechar, A., & Vigneault, C. (2017). Agricultural robots for field operations. Part 2: Operations and systems. Biosystems Engineering, 153, 110–128. https://doi.org/10.1016/j.biosystemseng.2016.11.004
Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization. The Journal of Machine Learning Research, 13(1), 281–305.
Bolya, D., Zhou, C., Xiao, F., & Lee, Y. J. (2019). YOLACT: Real-time instance segmentation, arXiv:1904.
Chao, C. T., & Krueger, R. R. (2007). The date palm (Phoenix dactylifera L.): overview of biology, uses, and cultivation. HortScience, 42(5), 1077–1082. https://doi.org/10.21273/HORTSCI.42.5.1077
Cohen, Y., Bar-Shira, O., & Berman, S. (2020). Motion adaptation based on learning the manifold of task and dynamic movement primitive parameters. Robotica. https://doi.org/10.1017/s0263574720001186
Cohen, Y., & Glasner, B. B. (2015). Date palm status and perspective in Israel. In J. M. Al-Khayri, S. M. Jain, & D. V. Johnson (Eds.), Date palm genetic resources, cultivar assessment, cultivation practices and novel products (pp. 265–298). Dordrecht: Springer. https://doi.org/10.1007/978-94-017-9707-8_8
Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In IEEE computer society conference on computer vision and pattern recognition (CVPR 2009), 20–25 June 2009, Miami, Florida, USA https://doi.org/10.1109/CVPR.2009.5206848.
Duckett, T., Pearson, S., Blackmore, S., & Grieve, B. (2018). Agricultural robotics: The future of robotic agriculture. arXiv preprint arXiv:1806.06762
Eizicovits, D., van Tuijl, B., Berman, S., & Edan, Y. (2016). Integration of perception capabilities in gripper design using graspability maps. Biosystems Engineering, 146, 98–113. https://doi.org/10.1016/j.biosystemseng.2015.12.016
Forman, G., & Scholz, M. (2010). Apples-to-apples in cross-validation studies: Pitfalls in classifier performance measurement. Acm Sigkdd Explorations Newsletter, 12(1), 49–57. https://doi.org/10.1145/1882471.1882479
Glorot, X., Bordes, A., & Bengio, Y. (2011). Deep sparse rectifier neural networks. In Proceedings of the fourteenth international conference on artificial intelligence and statistics (pp. 315–323). PMLR.
Gongal, A., Amatya, S., Karkee, M., Zhang, Q., & Lewis, K. (2015). Sensors and systems for fruit detection and localization: A review. Computers and Electronics in Agriculture, 116, 8–19. https://doi.org/10.1016/j.compag.2015.05.021
He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). Mask R-CNN. In Proceedings of the IEEE international conference on computer vision (pp. 2961–2969). New York: IEEE.
Ijspeert, A. J., Nakanishi, J., Hoffmann, H., Pastor, P., & Schaal, S. (2013). Dynamical movement primitives: Learning attractor models for motor behaviors. Neural Computation, 25(2), 328–373.
Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). A review of the use of convolutional neural networks in agriculture. The Journal of Agricultural Science, 156, 312–322. https://doi.org/10.1017/S0021859618000436
Kapach, K., Barnea, E., Mairon, R., Edan, Y., & Ben-Shahar, O. (2012). Computer vision for fruit harvesting robots—State of the art and challenges ahead. International Journal of Computational Vision and Robotics. https://doi.org/10.1504/IJCVR.2012.046419
Kestur, R., Meduri, A., & Narasipura, O. (2019). MangoNet: A deep semantic segmentation architecture for a method to detect and count mangoes in an open orchard. Engineering Applications of Artificial Intelligence, 77, 59–69. https://doi.org/10.1016/j.engappai.2018.09.011
Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
Koirala, A., Walsh, K. B., Wang, Z., & McCarthy, C. (2019). Deep learning for real-time fruit detection and orchard fruit load estimation: Benchmarking of ‘MangoYOLO.’ Precision Agriculture, 20, 1107–1135. https://doi.org/10.1007/s11119-019-09642-0
Legland, D. (2014). Feret diameter and oriented box. MATLAB Central File Exchange. Retrieved September 15, 2020, from https://www.mathworks.com/matlabcentral/fileexchange/30402-feret-diameter-and-oriented-box
Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014). Microsoft COCO: Common objects in context. In D. Fleet, T. Pajdla, B. Schiele, & T. Tuytelaars (Eds.), Computer vision—ECCV 2014. Lecture Notes in Computer Science. (Vol. 8693). Cham: Springer. https://doi.org/10.1007/978-3-319-10602-1_48
Lin, G., Tang, Y., Zou, X., Cheng, J., & Xiong, J. (2020). Fruit detection in natural environment using partial shape matching and probabilistic Hough transform. Precision Agriculture, 21, 160–177. https://doi.org/10.1007/s11119-019-09662-w
Linker, R., & Neer, O. (2014). Tree skeleton extraction by close-range laser telemetry as first step toward robotic pruning. In International conference of agricultural engineering (AgEng).
Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60, 91–110. https://doi.org/10.1023/B:VISI.0000029664.99615.94
Marani, R., Milella, A., Petitti, A., & Reina, G. (2021). Deep neural networks for grape bunch segmentation in natural images from a consumer-grade camera. Precision Agriculture, 22, 387–413. https://doi.org/10.1007/s11119-020-09736-0
Morris, J. R. (2007). Development and commercialization of a complete vineyard mechanization system. HortTechnology, 17(4), 411–420. https://doi.org/10.21273/HORTTECH.17.4.411
Mortensen, A. K., Dyrmann, M., Karstoft, H., Jørgensen, R. N., & Gislum, R. (2016). Semantic segmentation of mixed crops using deep convolutional neural network. In Proceedings of the International Conference of Agricultural Engineering (CIGR).
Qian, N. (1999). On the momentum term in gradient descent learning algorithms. Neural Networks, 12(1), 145–151. https://doi.org/10.1016/S0893-6080(98)00116-6
Razzaghi, E., Massah, J., & Vakilian, K. A. (2015). Mechanical analysis of a robotic date harvesting manipulator. Russian Agricultural Sciences, 41(1), 80–85. https://doi.org/10.3103/S1068367415010176
Redmon, J., Divvala, S., Girshick, R., Farhadi, A. (2016). You only look once: Unified, real-time object detection. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 779–788), https://doi.org/10.1109/CVPR.2016.91
Ren, S., He, K., Girshick, R., & Sun, J. (2017). Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031
Rosa, U. A., Cheetancheri, K. G., Gliever, C. J., Lee, S. H., Thompson, J., & Slaughter, D. C. (2008). An electro-mechanical limb shaker for fruit thinning. Computers and Electronics in Agriculture, 61(2), 213–221. https://doi.org/10.1016/j.compag.2007.11.008
Ruder, S. (2016). An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747.
Saleem, M. H., Potgieter, J., & Arif, K. M. (2021). Automation in agriculture by machine and deep learning techniques: A review of recent developments. Precision Agriculture. https://doi.org/10.1007/s11119-021-09806-x
Santos, T. T., de Souza, L. L., dos Santos, A. A., & Avila, S. (2020). Grape detection, segmentation, and tracking using deep neural networks and three-dimensional association. Computers and Electronics in Agriculture, 170, 105247. https://doi.org/10.1016/j.compag.2020.105247
Shapiro, A., Korkidi, E., Demri, A., Ben-Shahar, O., Riemer, R., & Edan, Y. (2009). Toward elevated agrobotics: Development of a scaled-down prototype for visually guided date palm tree sprayer. Journal of Field Robotics, 26(6–7), 572–590. https://doi.org/10.1002/rob.20299
Shin, H. C., Roth, H. R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J., Mollura, D., & Summers, R. M. (2016). Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Transactions on Medical Imaging, 35(5), 1285–1298. https://doi.org/10.1109/TMI.2016.2528162
Shoshan, T., Berman, S. (2021), Medjoul-date images—Annotated, Mendeley Data, V1, https://doi.org/10.17632/k7xk2nwgrh.1
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Tian, Y., Yang, G., Wang, Z., Li, E., & Liang, Z. (2020). Instance segmentation of apple flowers using the improved mask R-CNN model. Biosystems Engineering, 193, 264–278. https://doi.org/10.1016/j.biosystemseng.2020.03.008
Tu, S., Pang, J., Liu, H., Zhuang, N., Chen, Y., Zheng, C., Wan, H., & Xue, Y. (2020). Passion fruit detection and counting based on multiple scale faster R-CNN using RGB-D images. Precision Agriculture, 21, 1072–1091. https://doi.org/10.1007/s11119-020-09709-3
Wibisono, J. K., & Hang, H. M. (2017). RGBD image segmentation using deep edge. In 2017 international symposium on intelligent signal processing and communication systems (ISPACS) (pp. 565–569), Xiamen. https://doi.org/10.1109/ISPACS.2017.8266542
Zapotezny-Anderson, P., & Lehnert, C. (2019). Towards active robotic vision in agriculture: a deep learning approach to visual servoing in occluded and unstructured protected cropping environments. IFAC-PapersOnLine, 52(30), 120–125. https://doi.org/10.1016/j.ifacol.2019.12.508
Acknowledgements
The authors would like to thank Inbar Ben-David and Dr. Yael Salzer, Dr. Zeev Schmilovitz, and Dekel Meir from the ARO-Volcani Institute for their assistance in the data collection effort, Prof. Yossi Yovel from Tel-Aviv University for his insightful comments, Noam Peles, Nissim Abuhazera, Yossi Zahavi, and Moshe Bardea from Ben-Gurion University for their technical assistance, and the Israeli date growers for their assistance in various stages of the research.
Funding
This research is funded by the Chief Scientist of the Israeli ministry of agriculture and the Israeli Date Grower’s board in the Plant Council (Project # 20-07-0018).
Author information
Authors and Affiliations
Contributions
TS, AB and SB, conceptualized the project and the methodology. All authors contributed to the data collection effort. TS and SB developed the algorithms and performed the data analysis. YC and AS provided consultation regarding Medjoul dates and their thinning operations. TS and SB wrote the initial draft of the manuscript. All authors contributed to the review and editing of the final draft of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors have no conflict of interest to declare which are relevant to the content of this article.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Shoshan, T., Bechar, A., Cohen, Y. et al. Segmentation and motion parameter estimation for robotic Medjoul-date thinning. Precision Agric 23, 514–537 (2022). https://doi.org/10.1007/s11119-021-09847-2
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11119-021-09847-2