- PII
- 10.31857/S2500208224010121-1
- DOI
- 10.31857/S2500208224010121
- Publication type
- Article
- Status
- Published
- Authors
- Volume/ Edition
- Volume / Issue number 1
- Pages
- 53-57
- Abstract
- The creation of smart farms and urban farms (city farm) has become one of the development trends in recent years, both in agroengineering and in urban construction. A high level of automation significantly reduces the degree of human participation in the production processes of a smart farm. As a result, the requirements for the experience and professional knowledge in the field of agriculture of the owner and staff of such a farm are reduced. The article discusses the issues of creating intelligent decision support systems for a “smart” agricultural farm, in particular, for urban, city farms. In such systems, artificial neural networks (ANN) of computer vision are used to process the results of observations and recognize situations requiring human intervention. Using the example of an urban farm for growing strawberries, a number of applied tasks are formulated (detection of fruits classified by maturity, detection and classification of diseases, detection of stolons). The results of an experimental study of computer vision systems for these tasks are presented. The research methodology included the use of pre-trained neural network models with their additional training on their own sets of images and subsequent assessment of the accuracy of detection and classification. Neural networks configured for such tasks in decision support systems are complemented by algorithms working with knowledge bases and computational and logical models. Thus, a hardware and software complex is being created that allows not only to automate the execution of current business tasks, but also to recommend solutions in case of difficult situations that normally require a lot of professional experience and knowledge from the staff. The study was conducted on the basis of the agrobiotechnical complex of Tyumen State University.
- Keywords
- городская ферма умная ферма поддержка принятия решений искусственный интеллект компьютерное зрение автоматизация детекция плодов земляника обнаружение заболеваний растений
- Date of publication
- 18.09.2025
- Year of publication
- 2025
- Number of purchasers
- 0
- Views
- 3
References
- 1. Агробиотехкомплекс будущего создан в ТюмГУ. Электронный ресурс: [сайт]. – URL: https://www.utmn.ru/x-bio/novosti/nauka-i-innovatsii/1182531/ (дата обращения: 26.10.2023).
- 2. Буторина Д.А., Ахтямов И.И. Объект городского фермерства как новое общественное пространство в современной России // Известия КГАСУ. 2022. № 4(62). С. 163–176. doi: 10.52409/20731523_2022_4_163. EDN: VTAGZC.
- 3. Глухих И.Н., Прохошин А.С., Глухих Д.И. Сравнение и отбор ситуаций в системах вывода решений на прецедентах для «умной» фермы // Информатика и автоматизация. 2023. Т. 22. № 4. С. 853–879. doi: 10.15622/ia.22.4.6.
- 4. Журавлева Л.А. Сити-фермерство как перспективное направление развития агропроизводства // Научная жизнь. 2020. Т. 15. № 4. С. 492–503. doi: 10.35679/1991-9476- 2020-15-4-492-503.
- 5. Махмудул Хасан А., Мд Ракиб Ул Ислам Р., Авинаш К. Классификация болезней листьев яблони с использованием набора данных изображений: подход многослойной сверточной нейронной сети // Информатика и автоматизация. 2022. Т. 21. № 4. C. 710–728. doi:10.15622/ia.21.4.3.
- 6. Руткин Н.М., Лагуткин О.Ю., Лагуткина Л.Ю. Урбанизированное агропроизводство (сити-фермерство) как перспективное направление развития мирового агропроизводства и способ повышения продовольственной безопасности городов//Вестник Астраханского государственного технического университета. Серия: рыбное хозяйство. 2017. Т. 2017. № 4. С. 95–108.
- 7. Aamodt A., Plaza E. Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches. AI Communications. 2001. Vol. 7. PP. 39–59. doi:10.3233/AIC-1994-7104.
- 8. Afzaal U., Bhattarai B., Pandeya Y.R., Lee J. An Instance Segmentation Model for Strawberry Diseases Based on Mask R-CNN. Sensors. 2021, 21, 6565.
- 9. Bhujel A., Kim N.-E., Arulmozhi E., Basak J.K. et al. A Lightweight Attention-Based Convolutional Neural Networks for Tomato Leaf Disease Classification. Agriculture. 2022. № 12(2). P. 228. doi:10.3390/agriculture12020228. doi:10.3390/ agriculture12020228.
- 10. Detection tasks / [Электронный ресурс] // Ультралитикс : [сайт]. – URL: https://docs.ultralytics.com/tasks/detect/ (дата обращения: 26.10.2023).
- 11. Elhariri E., El-Bendary N., Saleh S.M., Strawberry-DS: Dataset of annotated strawberry fruits images with various developmental stages. Data in Brief. 2023. Vol. 48, 109165. doi:10.1016/j.dib.2023.109165.
- 12. Hu W.-C., Chen L.-B., Huang B.-K., Lin H.-M. A Computer Vision-Based Intelligent Fish Feeding System Using Deep Learning Techniques for Aquaculture. IEEE Sensors Journal. 2022. Vol. 22. № 7. PP. 7185–7194. doi: 10.1109/JSEN.2022.3151777.
- 13. Juan Terven, Diana Cordova-Esparza. A Comprehensive Review of YOLO: From YOLOv1 and Beyond. 2023. URL: https://doi.org/10.48550/arXiv.2304.00501.
- 14. Martin M., Molin E. Environmental Assessment of an Urban Vertical Hydroponic Farming System in Sweden // Sustainability. 2019. Vol. 11(15). № 4124. doi:10.3390/su11154124.
