An automated system based on computer vision and heuristic rules for adaptive irrigation management in cherry tomatoes

Authors

DOI:

https://doi.org/10.70929/caui3.v2i2.0023

Keywords:

Precision agriculture, computer vision, smart irrigation, cherry tomato, machine learning

Abstract

Irrigation optimization constitutes a priority challenge in precision agriculture due to increasing water scarcity and the need to enhance the sustainability of production systems. This study aimed to develop and implement an intelligent system based on computer vision and heuristic decision rules to adaptively manage irrigation in cherry tomato (Solanum lycopersicum var. cerasiforme) crops. The research was conducted under a quantitative experimental longitudinal approach in a controlled greenhouse environment. The system integrated digital image processing using OpenCV and HSV color space segmentation to classify fruit ripeness stages and execute automated control actions. The results demonstrated effective visual discrimination, a reduction in false detections through morphological filtering, and real-time performance with latency below 100 ms per frame. Furthermore, the architecture dynamically adjusted irrigation runtime according to the detected phenological ratio, overcoming the rigidity of conventional fixed-timer schemes. It is concluded that coupling computer vision with heuristic control provides a viable and computationally efficient approach to modulate water delivery in protected agricultural environments.

Downloads

Download data is not yet available.

Author Biographies

  • Gonzalo Rodríguez-Galarza, Universidad internacional del Ecuador

    Electronics and Telecommunications Engineer who graduated with honors (Cum Laude) from the National University of Chimborazo and holds a graduate degree in Data Science and Machine Learning (with a specialization in AI) from the International University of Ecuador, with solid experience in the development of applied technology solutions, automation, programming (Python, C/C++, MicroPython), and the implementation of virtual environments (Moodle H5P), as well as in data analysis and business intelligence using Power BI. He complements his technical profile with an outstanding track record in editorial management and scientific research as an editor at Revista Esprint, a consultant on publication processes in accordance with international standards (APA, Vancouver, IEEE), and an author of projects focused on technological and educational innovation.

  • Alfonso Gunsha-Morales, Universidad Estatal de Quevedo

    Electrical Engineer with a Master’s degree in Electronic Systems Engineering. Currently a Ph.D. candidate in Renewable Energy. University professor with experience in the fields of electricity, electronics, industrial automation, renewable energy, photovoltaic systems, IoT, and control. He has engaged in teaching, research, and outreach activities at institutions of higher education, participating in projects related to energy sustainability, energy efficiency, and electricity generation from renewable sources. He is the author and co-author of scientific publications indexed in high-impact international journals and a speaker at national and international conferences. His research focuses on renewable energy, photovoltaic systems, the energy transition, energy efficiency, power quality, industrial automation, and technologies applied to sustainable development.

  • José Velastegui Almeida, Universidad Polítecnica Salesiana

    Biotechnology engineering student with experience as a co-author and researcher in the development and implementation of biotechnology and precision agriculture solutions in greenhouses (BIO J.N.), focused on optimizing water resources through computer vision and artificial intelligence applied to cherry tomato cultivation. He has actively participated in the design and field validation of intelligent systems programmed in Python, capable of segmenting and phenologically classifying the fruit’s ripening stage to autonomously regulate irrigation timing and frequency, thereby preventing water stress in early stages and epidermal collapse or cracking due to over-hydration in mature crops. His profile stands out for integrating agrobiological knowledge with advanced computational tools, promoting sustainability, input efficiency, and the direct impact of technology on the agricultural sector.

  • Noelia Velastegui-Almeida, Universidad Estatal de Guayaquil

    A dental student at the University of Guayaquil with a versatile profile focused on applied research and interdisciplinary collaboration, with experience as a co-author on projects involving technological optimization and sustainability in protected-culture environments (BIO J.N.). She actively participated in the field validation of automated systems based on computer vision and Python algorithms for the phenological monitoring of cherry tomatoes, designed to autonomously regulate irrigation cycles according to the fruit’s stage of ripeness, thereby mitigating water stress and skin cracking to reduce water waste. Her involvement in initiatives outside the conventional clinical setting demonstrates strong analytical skills, methodological rigor, and a commitment to applying technological solutions to practical and sustainable real-world problems.

References

[1] R. Sahu and P. Tripathi, "An intelligent framework for monitoring and irrigation prediction for precision agriculture," Iran J. Comput. Sci., 2025, doi: 10.1007/s42044-025-00269-1.

[2] S. Banluesapy, M. Ketcham, and M. Rattanasiriwongwut, "AI-augmented smart irrigation system using IoT and solar power for sustainable water and energy management," Ing. Energética, vol. 122, no. 10, pp. 4261–4296, Sep. 2025.

[3] P. Thongnim, T. Inthasuth, and M. Leelaphaiboon, "Integrating LSTM-based VPD forecasting into IoT-driven smart irrigation systems in tropical orchards," Discov. Sustain., vol. 7, art. no. 173, 2026, doi: 10.1007/s43621-025-02538-2.

[4] Y. Kong, D. Llewellyn, and Y. Zheng, "High tunnels without anti-insect netting benefit organic cherry tomato production in regions with cool and short growing seasons," Can. J. Plant Sci., vol. 100, no. 4, pp. 401–414, Feb. 2020, doi: 10.1139/cjps-2019-0243.

[5] L. Roco, A. Fischer, C. Grisa, F. García, and E. Sanguinet, "A systematic review of COVID-19 effects on agri-food chains in Latin America," Rev. Fac. Agron. (LUZ), vol. 42, no. 2, art. no. e254221, 2025, doi: 10.47280/RevFacAgron(LUZ).v42.n2.V.

[6] V. Tordecilla-Acevedo, M. C. Valdelamar-Ospino, and A. S. Cantillo, "Agronegocios y tecnología: aproximación de las tendencias, proyectos e iniciativas de tecnología en los agronegocios en Latinoamérica entre 2014-2024," in Proc. 23rd LACCEI Int. Multi-Conf. Eng., Educ. Technol., Mexico City, Mexico, 2025, pp. 2–8.

[7] A. Boshnjaku, E. Plasari, and I. Fata, "Charting the digital frontier: A comprehensive bibliometric analysis of e-agriculture research," Int. J. Innov. Technol. Interdiscip. Sci., vol. 9, no. 1, pp. 51–114, Jan. 2026, doi: 10.15157/IJITIS.2026.9.1.51-114.

[8] M. A. Ikegawa-Bernabé, R. González-Perea, J. A. Rodríguez-Díaz, and J. García-Morillo, "Novel hybrid transformer-based model for mid-term hourly energy demand forecasting in large pressurized irrigation districts," Comput. Electron. Agric., vol. 246, art. no. 111611, 2026.

[9] E. Sánchez-Domínguez, M. J. Briseño-López, B. Murillo-Amador, J. R. Holguín-Peña, L. G. Hernández-Montiel, y L. Lara-Capistrán, "Efecto de bioestimulantes microbianos sobre el rendimiento y calidad de fruto de tomate cherry (Solanum lycopersicum L. var. cerasiforme)," Terra Latinoam., vol. 44, pp. 1–11, Feb. 2026, doi: 10.28940/terralatinoamericana.v44i.2418.

[10] E. Sánchez-Domínguez, M. J. Briseño-López, B. Murillo-Amador, J. R. Holguín-Peña, L. G. Hernández-Montiel, y L. Lara-Capistrán, "Efecto de Bioestimulantes Microbianos sobre el Rendimiento y Calidad de Fruto de Tomate Cherry (Solanum lycopersicum L. var. cerasiforme)," Terra Latinoamericana, vol. 44, pp. 1–11, Feb. 2026. DOI: 10.28940/terralatinoamericana.v44i.2418.

[11] D. Wang, X. Wang, Y. Chen, Y. Wu y X. Zhang, “Strawberry ripeness classification method in facility environment based on red color ratio of fruit rind,” Computers and Electronics in Agriculture, vol. 214, p. 108313, Nov. 2023, doi: 10.1016/j.compag.2023.108313.

[12] Y. N. Kuan, K. M. Goh y L. L. Lim, “Systematic review on machine learning and computer vision in precision agriculture: Applications, trends, and emerging techniques,” Engineering Applications of Artificial Intelligence, vol. 148, p. 110401, May 2025, doi: 10.1016/j.engappai.2025.110401

[13] A. Das, F. Pathan, J. R. Jim, M. M. Kabir y M. F. Mridha, “Deep learning-based classification, detection, and segmentation of tomato leaf diseases: A state-of-the-art review,” Artificial Intelligence in Agriculture, vol. 15, no. 2, pp. 192–220, Jun. 2025, doi: 10.1016/j.aiia.2025.02.006.

[14] P. Parida y N. Bhoi, “2-D Gabor filter based transition region extraction and morphological operation for image segmentation,” Computers & Electrical Engineering, vol. 62, pp. 119–134, Aug. 2017, doi: 10.1016/j.compeleceng.2016.10.019.

[15] M.-T. Tran, A. Fedeli, J. A. Piñera García, P. Pelliccione y T.-P. Nguyen, “Noise-reduction-oriented super-resolution reconstruction for precision agriculture applications,” Expert Systems with Applications, vol. 307, p. 131036, Apr. 2026, doi: 10.1016/j.eswa.2025.131036.

[16] M. Ayoubi y M. Arashpour, “Enhancing workplace safety through assistive computer vision: Real-time hazard recognition using the Workplace Hazards Dataset (WHD),” Computer Vision and Image Understanding, vol. 265, p. 104681, Mar. 2026, doi: 10.1016/j.cviu.2026.104681.

[17] S. Kulandaivel y U. C. Akuthota, “Driving the future with edge computing: A review of data offloading, enabling technologies and trends for autonomous vehicles,” Internet of Things, vol. 38, p. 101963, Jul. 2026, doi: 10.1016/j.iot.2026.101963.

[18] X. Luo, A. Jiang, Y. Dong, J. Weng, Y. Tai y W. Chen, “Blockchain and IoT integration solutions in agricultural data management: From data collection to trust verification,” Crop Design, Art. no. 100144, May 2026, doi: 10.1016/j.cropd.2026.100144.

[19] W. F. Mbasso, I. Dagal, A. Harrison, S. Chebaane, M. Khishe, P. Jangir, A. Smerat y E. F. Donfack, “Towards accelerated chaos-based encryption in embedded systems: Methodological perspectives for speed optimization in constrained hardware architectures,” Computer Standards & Interfaces, vol. 98, p. 104167, Aug. 2026, doi: 10.1016/j.csi.2026.104167.

[20] M. Moyo, F. M. Akinseye, A. van Rooyen, H. Bjornlund, K. Parry, J. Pittock, P. Ramshaw, A. Mujeyi, T. Dube y F. Dube, “Can soil moisture and nutrient monitoring tools contribute to climate-smart smallholder irrigation? A modelling approach in Zimbabwe,” Agricultural Water Management, vol. 327, p. 110272, Apr. 2026, doi: 10.1016/j.agwat.2026.110272.

[21] W. Dai, Z. Zhang, Z. Zhang y H. Zhu, “YOLOv8-GSC: An agricultural crop precision detection model integrating lightweight network and attention mechanism,” Alexandria Engineering Journal, vol. 145, pp. 63–76, May 2026, doi: 10.1016/j.aej.2026.04.027.

Downloads

Published

2026-07-31

Issue

Vol. 2 No. 2 (2026): Developments in Automation, Materials, and Contemporary Design

Section

Research Paper

Categories

License

You are free to:

  1. Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
  2. Adapt — remix, transform, and build upon the material for any purpose, even commercially.
  3. The licensor cannot revoke these freedoms as long as you follow the license terms.

How to Cite

[1]
G. Rodríguez-Galarza, A. Gunsha-Morales, J. Velastegui Almeida, and N. Velastegui-Almeida, “An automated system based on computer vision and heuristic rules for adaptive irrigation management in cherry tomatoes”, Revista Digital Científica Causalidad (caui3), vol. 2, no. 2, pp. 47–59, Jul. 2026, doi: 10.70929/caui3.v2i2.0023.