Abstract
Fire blight disease causes significant losses in pear orchards. Fire blight infection is accompanied by visual symptoms that can easily be recognized by a grower or adviser, but such visual inspection is time consuming. The present work focused on the use of convolutional neural networks (CNNs) to identify one type of visual symptom (cankers on the main trunk of dormant trees) as well as autumn blooming, which in Israel plays an important role in the epidemiology of Erwinia amylovora—the bacterium responsible for fire blight. Images of dormant trees were acquired with a tripod-mounted DSLR camera while, for autumn blooming detection, the images were acquired using a small unmanned aerial vehicle flying a few meters above the trees. In both cases, several Faster R-CNNs were trained and tested with several datasets acquired at various locations and over several years. Overall, the CNNs for canker detection achieved precision and recall rates that exceeded 90% while, for autumn blooming detection, the precision and recall rates exceeded 80% in all but one case. These trained CNNs were used to analyze automatically geo-references images, hence generating infection/blooming maps. Such maps could be one of the information layers used by growers for managing the orchard, for instance to determine whether winter sanitation is needed and/or if it was carried out properly, or to decide when and where costly manual removal of autumn flowers or copper application is required.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bayar, G., Bergerman, M., Koku, A. B., & Konukseven, E. (2015). Localization and control of an autonomous orchard vehicle. Computers and Electronics in Agriculture, 115, 118–128.
Blachinsky, D., Shtienberg, D., Oppenheim, D., Zilberstaine, M., Levi, S., Zamski, E., & Shoseyov, O. (2003). The role of autumn infections in the progression of fire blight symptoms in perennial pear branches. Plant Disease, 87(9), 1077–1082.
Dafny Yelin, M., Moy, J. C., Mairesse, O., Silberstein, M., Sapir, G., & Michaeli, D. (2021a). Efficacy of fire blight management in pome fruit in northern Israel: Copper agents and their effect on yield parameters. Journal of Plant Pathology, 103(1), 151–161.
Dafny-Yelin, M., Moy, J. C., Stern, R. A., Doron, I., Silberstein, M., & Michaeli, D. (2021b). High-density ‘Spadona’ pear orchard shows reduced tree sensitivity to fire blight damage due to decreased tree vigour. Phytopathologia Mediterranea, 60(3), 421–426.
Elkins, R. B., Temple, T. N., Shaffer, C. A., Ingels, C. A., Lindow, S. B., Zoller, B. G., & Johnson, K. B. (2015). Evaluation of dormant-stage inoculum sanitation as a component of a fire blight management program for fresh-market Bartlett pear. Plant Disease, 99(8), 1147–1152.
Farjon, G., Krikeb, O., Hillel, A. B., & Alchanatis, V. (2020). Detection and counting of flowers on apple trees for better chemical thinning decisions. Precision Agriculture, 21(3), 503–521.
Fu, L., Majeed, Y., Zhang, X., Karkee, M., & Zhang, Q. (2020). Faster R-CNN–based apple detection in dense-foliage fruiting-wall trees using RGB and depth features for robotic harvesting. Biosystems Engineering, 197, 245–256.
Gao, F., Fang, W., Sun, X., Wu, Z., Zhao, G., Li, G., Li, R., Fu, L., & Zhang, Q. (2022). A novel apple fruit detection and counting methodology based on deep learning and trunk tracking in modern orchard. Computers and Electronics in Agriculture, 197, 107000.
Gao, F., Fu, L., Zhang, X., Majeed, Y., Li, R., Karkee, M., & Zhang, Q. (2020). Multi-class fruit-on-plant detection for apple in SNAP system using Faster R-CNN. Computers and Electronics in Agriculture, 176, 105634.
Jones, M. H., Bell, J., Dredge, D., Seabright, M., Scarfe, A., Duke, M., & MacDonald, B. (2019). Design and testing of a heavy-duty platform for autonomous navigation in kiwifruit orchards. Biosystems Engineering, 187, 129–146.
Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 147, 70–90.
Kang, T. H., Kim, H. J., & Noh, H. K. (2020). Convolution neural network of deep learning for detection of fire blight on pear tree. Horticultural Science and Technology, 38(6), 763–775.
Karouta, J. J. H., & Ribeiro, A. (2023). Autonomous platforms. In S. G. Vougioukas & Q. Zhang (Eds.), Advanced automation for tree fruit orchards and vineyards. Agriculture automation and control. Springer.
Koirala, A., Walsh, K. B., Wang, Z., & McCarthy, C. (2019a). Deep learning for real-time fruit detection and orchard fruit load estimation: Benchmarking of ‘MangoYOLO.’ Precision Agriculture, 20(6), 1107–1135.
Koirala, A., Walsh, K. B., Wang, Z., & McCarthy, C. (2019b). Deep learning–Method overview and review of use for fruit detection and yield estimation. Computers and Electronics in Agriculture, 162, 219–234.
Krikeb, O., Alchanatis, V., Crane, O., & Naor, A. (2017). Evaluation of apple flowering intensity using color image processing for tree specific chemical thinning. Advances in Animal Biosciences, 8(2), 466–470.
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C. (2016). SSD: Single shot multibox detector. European conference on computer vision (pp. 21–37). Springer.
Naor, A., Stern, R., Flaishman, M., Gal, Y., & Peres, M. (2006). Effects of post-harvest water stress on autumnal bloom and subsequent-season productivity in mid-season ‘Spadona’pear. The Journal of Horticultural Science and Biotechnology, 81(3), 365–370.
Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint http://arxiv.org/abs/1804.02767
Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 28, 91–99.
Schoofs, H., Delalieux, S., Deckers, T., & Bylemans, D. (2020). Fire blight monitoring in pear orchards by unmanned airborne vehicles (UAV) systems carrying spectral sensors. Agronomy, 10(5), 615.
Shtienberg, D., Kritzman, G., Herzog, Z., Openhaim, D., Zillberstein, M., & Blatchinsky, D. (1998). Development and evaluation of a decision support system for management of fire blight in pears. Acta Horticulturae, 489, 385–392.
Shtienberg, D., Oppenheim, D., Herzog, Z., Zilberstaine, M., & Kritzman, G. (2000). Fire blight of pears in Israel: Infection, prevalence, intensity and efficacy of management actions. Phytoparasitica, 28(4), 361–374.
Shtienberg, D., Shwartz, H., Oppenheim, D., Zilberstaine, M., Herzog, Z., Manulis, S., & Kritzman, G. (2003a). Evaluation of local and imported fire blight warning systems in Israel. Phytopathology, 93(3), 356–363.
Shtienberg, D., Zilberstaine, M., Oppenheim, D., Levi, S., Shwartz, H., & Kritzman, G. (2003b). New considerations for pruning in management of fire blight in pears. Plant Disease, 87(9), 1083–1088.
Slack, S. M., & Sundin, G. W. (2017). News on ooze, the fire blight spreader. Fruit Quarterly, 25(1), 9–12.
Smith, T. J. (1995). A risk assessment model for fire blight of apple and pear. Acta Horticulturae, 411, 97–104.
Thomson, S. V. (2000). Epidemiology of fire blight. Fire blight: The disease and its causative agent, Erwinia amylovora (pp. 9–36). CABI Publishing.
Vasconez, J. P., Delpiano, J., Vougioukas, S., & Cheein, F. A. (2020). Comparison of convolutional neural networks in fruit detection and counting: A comprehensive evaluation. Computers and Electronics in Agriculture, 173, 105348.
Wilcox, W. F. (1994). Fire blight. Tree fruit disease identification sheet No. 102GFSTF-D3 (rev.). Geneva: IPM Program, Cornell University.
Wu, D., Lv, S., Jiang, M., & Song, H. (2020). Using channel pruning-based YOLO v4 deep learning algorithm for the real-time and accurate detection of apple flowers in natural environments. Computers and Electronics in Agriculture, 178, 105742.
Funding
This study was funded by the Israel Ministry of Agriculture, Chief Scientist Fund Grant Number 14-30-0004.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
See Fig. 11.
Visualization of the canker detection results (number of pixels in the areas classified as cankers) for the four rows analyzed with the trained Faster R-CNN. The two results for each tree correspond to the images acquired with the camera facing East and West
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Linker, R., Dafny-Yalin, M. Mapping fire blight cankers and autumn blooming in pear trees using Faster R-CNN. Precision Agric 25, 396–411 (2024). https://doi.org/10.1007/s11119-023-10077-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11119-023-10077-x