Logo PTI Logo FedCSIS

Proceedings of the 21st Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 47

Beyond Segmentation: Outlier-Aware and Viewpoint-Aware Crop Water Stress Index Estimation in Dense Tomato Canopies

, , , , , , , , , , ,

DOI: http://dx.doi.org/10.15439/2026F8192

Citation: Laura Mas i Serra, , , , , , , , , , ,

Full text

Abstract. Precision irrigation depends on accurate crop water stress estimation, often using the Crop Water Stress Index (CWSI). Reliable CWSI estimation requires precise measurement of sunlit-leaf canopy temperature. Prior work introduced the Crop Irrigation Web Agent (CIWA) for convolutional neural network (CNN)-based sunlit-leaf segmentation and CWSI estimation in pistachio trees, focusing on sparse canopies. We extend CIWA to dense tomato canopies, where occlusion, reduced visual contrast, thermal leakage, residual RGB--thermal misregistration, and viewpoint effects make estimation more challenging. We introduce TMSL21, an annotated RGB-thermal dataset for tomato sunlit-leaf segmentation, compare CNN and Vision Transformer architectures, and propose a CWSI pipeline with Gaussian Mixture Model (GMM)-based filtering for outlier suppression. We also analyze imaging viewpoint effects, derive a tomato-specific CWSI baseline, and update CIWA for tomato imagery. Results show that reliable CWSI estimation depends on segmentation quality, thermal noise structure, and imaging geometry. Overall, the study generalizes CIWA toward a robust framework for dense canopies.

References

  1. Food and U. N. Agriculture Organization. (2012) World agriculture towards 2030/2050: The 2012 revision. [Online]. Available: http://www. fao.org/fileadmin/user_upload/esag/docs/AT2050_revision_summary.pdf
  2. T. L. Fess, J. B. Kotcon, and V. A. Benedito, “Crop breeding for low input agriculture: a sustainable response to feed a growing world population,” Sustainability, vol. 3, no. 10, pp. 1742–1772, 2011.
  3. M. Ozdogan, Y. Yang, G. Allez, and C. Cervantes, “Remote sensing of irrigated agriculture: Opportunities and challenges,” Remote sensing, vol. 2, no. 9, pp. 2274–2304, 2010.
  4. L. Konikow. (2013) Groundwater depletion in the united states (1900 to 2008). [Online]. Available: http://pubs.usgs.gov/sir/2013/5079
  5. U. Nations. (2014) Wwdr2014. [Online]. Available: https://unesdoc. unesco.org/ark:/48223/pf0000226961
  6. J. Rockström, J. Williams, G. Daily, A. Noble, N. Matthews, L. Gordon, H. Wetterstrand, F. DeClerck, M. Shah, P. Steduto, C. de Fraiture, N. Hatibu, O. Unver, J. Bird, L. Sibanda, and J. Smith, “Sustainable intensification of agriculture for human prosperity and global sustainability.” Ambio, vol. 46(1), pp. 4–17, 2 2017.
  7. E. A. Abioye, M. S. Z. Abidin, M. S. A. Mahmud, S. Buyamin, M. H. I. Ishak, M. K. I. Abd Rahman, A. O. Otuoze, P. Onotu, and M. S. A. Ramli, “A review on monitoring and advanced control strategies for precision irrigation,” Computers and Electronics in Agriculture, vol. 173, p. 105441, 2020.
  8. R. D. Jackson, S. B. Idso, R. J. Reginato, and P. J. Pinter, “Canopy temperature as a crop water stress indicator,” Water Resources Research, vol. 17, no. 4, pp. 1133–1138, 8 1981.
  9. V. Alchanatis, A. Cohen, Y. Cohen, O. Levi, and A. Naor, “Multimodal remote sensing for enhancing detection of spatial variability in agricultural fields,” in Spatial2 Conference: Spatial Data Methods for Environmental and Ecological Processes, Foggia (IT), 1-2 September 2011. Università degli studi di Bergamo, 2011, pp. 1–4.
  10. B. Gardner, D. Nielsen, and C. Shock, “Infrared thermometry and the crop water stress index. ii. sampling procedures and interpretation,” Journal of production agriculture, vol. 5, no. 4, pp. 466–475, 1992.
  11. D. Cui, Q. Zhang, M. Li, G. L. Hartman, and Y. Zhao, “Image processing methods for quantitatively detecting soybean rust from multispectral images,” Biosystems engineering, vol. 107, no. 3, pp. 186–193, 2010.
  12. Y. Dai, R. E. Dickinson, and Y.-P. Wang, “A two-big-leaf model for canopy temperature, photosynthesis, and stomatal conductance,” Journal of climate, vol. 17, no. 12, pp. 2281–2299, 2004.
  13. Z. Wang, L. Liu, B. Wang, and X. Wang, “Aerosol increases both sunlit and shaded leaf photosynthesis rate but with different mechanisms,” in AGU Fall Meeting Abstracts, vol. 2017, 2017, pp. B51F–1879.
  14. M. Pantelidakis, A. A. Panagopoulos, K. Mykoniatis, S. Ashkan, R. C. Eravi, V. Pamula, E. C. Verduzco III, O. Babich, O. P. Panagopoulos, and G. Chalkiadakis, “Identifying sunlit leaves using convolutional neural networks: An expert system for measuring the crop water stress index of pistachio trees,” Expert Systems with Applications, vol. 209, p. 118326, 2022.
  15. S. B. Idso, R. D. Jackson, P. J. Pinter, R. J. Reginato, and J. L. Hatfield, “Normalizing the stress-degree-day parameter for environmental variability,” Agricultural Meteorology, vol. 24, pp. 45–55, 1981.
  16. S. B. Idso, “Non-water-stressed baselines: a key to measuring and interpreting plant water stress.” Agricultural Meteorology, vol. 27, p. 59–70, 1982.
  17. X. Wang, W. Yang, A. Wheaton, N. Cooley, and B. Moran, “Automated canopy temperature estimation via infrared thermography: A first step towards automated plant water stress monitoring,” Computers and Electronics in Agriculture, vol. 73, pp. 74–83, 07 2010.
  18. M. H. Calp and V. K. Solanki, “Classification of plant species with iris dataset using ann, knn and k-means algorithms,” in Proceedings of the Eighth International Conference on Research in Intelligent Computing in Engineering, ser. Annals of Computer Science and Information Systems, P. Kumar, M. Cardona, V. K. Solanki, T. D. Tan, and A. Wahid, Eds., vol. 38. PTI, 2023, p. 7–10. [Online]. Available: http://dx.doi.org/10.15439/2023R63
  19. M. Arsov, E. Zdravevski, P. Lameski, R. Corizzo, N. Koteli, K. Mitreski, and V. Trajkovik, “Short-term air pollution forecasting based on environmental factors and deep learning models,” in Proceedings of the 2020 Federated Conference on Computer Science and Information Systems, ser. Annals of Computer Science and Information Systems, S. Agarwal, D. N. Barrell, and V. K. Solanki, Eds., vol. 21. IEEE, 2020, pp. 15–22. [Online]. Available: http://dx.doi.org/10.15439/2020KM211
  20. Flir. (2022) Flir ax8 datasheet. [Online]. Available: https://support.flir. com/DsDownload/Assets/71201-0101-en-US.html
  21. A. dos Santos Ferreira, D. M. Freitas, G. G. da Silva, H. Pistori, and M. T. Folhes, “Weed detection in soybean crops using convnets. computers and electronics in agriculture,” vol. 143, pp. 314–324, 2017.
  22. T. Pohlen, A. Hermans, M. Mathias, and B. Leibe, “Full-resolution residual networks for semantic segmentation in street scenes,” in Computer Vision and Pattern Recognition (CVPR), 2017 IEEE Conference on, 2017.
  23. S. Jégou, M. Drozdzal, D. Vazquez, A. Romero, and Y. Bengio, “The one hundred layers tiramisu: Fully convolutional densenets for semantic segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition workshops, 2017, pp. 11–19.
  24. E. Xie, W. Wang, Z. Yu, A. Anandkumar, J. M. Alvarez, and P. Luo, “Segformer: Simple and efficient design for semantic segmentation with transformers,” arXiv preprint https://arxiv.org/abs/2105.15203, 2021.
  25. B. Cheng, I. Misra, A. G. Schwing, A. Kirillov, and R. Girdhar, “Masked-attention mask transformer for universal image segmentation,” 2022. [Online]. Available: https://arxiv.org/abs/2112.01527
  26. M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, “The cityscapes dataset for semantic urban scene understanding,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 3213– 3223.
  27. B. Zhou, H. Zhao, X. Puig, T. Xiao, S. Fidler, A. Barriuso, and A. Torralba, “Semantic understanding of scenes through the ade20k dataset,” 2018. [Online]. Available: https://arxiv.org/abs/1608.05442
  28. N. Carion, L. Gustafson, Y.-T. Hu, S. Debnath, R. Hu, D. Suris, C. Ryali, K. V. Alwala, H. Khedr, A. Huang, J. Lei, T. Ma, B. Guo, A. Kalla, M. Marks, J. Greer, M. Wang, P. Sun, R. Rädle, T. Afouras, E. Mavroudi, K. Xu, T.-H. Wu, Y. Zhou, L. Momeni, R. Hazra, S. Ding, S. Vaze, F. Porcher, F. Li, S. Li, A. Kamath, H. K. Cheng, P. Dollár, N. Ravi, K. Saenko, P. Zhang, and C. Feichtenhofer, “Sam 3: Segment anything with concepts,” 2025. [Online]. Available: https://arxiv.org/abs/2511.16719
  29. O. Siméoni, H. V. Vo, M. Seitzer, F. Baldassarre, M. Oquab, C. Jose, V. Khalidov, M. Szafraniec, S. Yi, M. Ramamonjisoa, F. Massa, D. Haziza, L. Wehrstedt, J. Wang, T. Darcet, T. Moutakanni, L. Sentana, C. Roberts, A. Vedaldi, J. Tolan, J. Brandt, C. Couprie, J. Mairal, H. Jégou, P. Labatut, and P. Bojanowski, “Dinov3,” 2025. [Online]. Available: https://arxiv.org/abs/2508.10104
  30. L. Prechelt, “Early stopping-but when?” in Neural Networks: Tricks of the trade. Springer, 1998, pp. 55–69.
  31. A. Leigh, J. D. Close, M. C. Ball, K. Siebke, and A. B. Nicotra, “Leaf cooling curves: measuring leaf temperature in sunlight,” Functional Plant Biology, vol. 33, no. 5, pp. 515–519, 05 2006. [Online]. Available: https://doi.org/10.1071/FP05300
  32. J. D. Muller, E. Rotenberg, F. Tatarinov, I. Vishnevetsky, T. Dingjan, A. Kribus, and D. Yakir, “‘dual-reference’ method for highprecision infrared measurement of leaf surface temperature under field conditions,” New Phytologist, vol. 232, no. 6, pp. 2535–2546, 2021. [Online]. Available: https://nph.onlinelibrary.wiley.com/doi/abs/ 10.1111/nph.17720