ANALYSIS OF PLANTS’ GROWTH USING COMPUTER VISION METHODS
https://doi.org/10.35266/1999-7604-2023-1-29-35
Abstract
The study describes the development of a service for monitoring plants’ growth in an indoor greenhouse using computer vision models, visual data collection with the esp32-cam card, the OV5640 camera, and the YOLO v4 detection model for extracting individual plants from the images. The plants tracking was performed by the DeepSORT library. The study determined the age of plants according to their type in order to identify their growth rate and notify the user when the parameters achieved. The computer vision methods are implemented through the TensorFlow 2 framework, with 99 % of classification accuracy, and Random Forest coefficient of determination of 0.94 for the regression of a plant’s age.
About the Authors
A. V. Matokhina
Volgograd State Technical University, Volgograd
Russian Federation
Russian Federation
Candidate of Sciences (Engineering)
E-mail: matokhina.a.v@gmail.com
V. V. Tishchenko
Volgograd State Technical University, Volgograd
Russian Federation
Russian Federation
Master’s Degree Student
E-mail: vsevolutionlord@gmail.com
References
1. Bačić S., Tomić H., Andlar G., Roić M. Towards Integrated Land Management: The Role of Green Infra-structure. ISPRS Int J GeoInf. 2022. No. 10. P. 513. DOI 10.3390/ijgi11100513.
2. Kozai T., Niu G., Takagaki M. PFAL Business and R&D in Asia and North America: Status and Perspectives. Plant Factory: An Indoor Vertical Farming System for Efficient Quality Food Production. 2nd Ed. 2020. P. 35‒76.
3. Danyltsiv O., Khomiak A., Nazarevych O. Usage of Artificial Intelligence Systems and Working with the Neural Network in Assessing the Condition of Plants in Smart Greenhouses. 3rd International Workshop on Modern Machine Learning Technologies and Data Science, June 5, 2021, Lviv-Shatsk, Ukraine. URL: https://ceur-ws.org/Vol-2917/paper20.pdf (дата обращения: 20.01.2023).
4. Прошкин Ю. А., Смирнов А. А., Соколов А. В. и др. Оптический мониторинг овощных культур на основе цифровой обработки RGB изображений // Инновации в сельском хозяйстве. 2019. № 4. С. 266–278.
5. Kerkecha M., Hafianea A., Canalsb R. Vine Disease Detection in UAV multispectral Images Using Optimized Image Registration and Deep Learning Segmentation Approach. Computers and Electronics in Agriculture. 2020. Vol. 174. P. 105446. URL: https://hal.science/hal-03299578/document (дата обращения: 20.01.2023).
6. Harakannanavara S. S., Rudagib J. M., Purani-kmathb V. I. et. al. Plant Leaf Disease Detection Using Computer Vision and Machine Learning Algorithms. Global Transitions Proceedings. 2022. Vol. 3, No. 1. P. 305‒310. DOI 10.1016/j.gltp. 2022.03.016.
7. Al-Gunaid M. A., Shcherbakov M. V., Tishchenko V. V. et. al. The System of Intelligent Identi-fication of Harmful Objects in the Field of Agricul-ture. Creativity in Intelligent Technologies and Data Science. CIT&DS 2021. Communications in Com-puter and Information Science. 2021. Vol. 1448. P. 177–189. DOI 10.1007/978-3-030-87034-8_14.
8. Брыкин В. В., Брагинский М. Я., Тараканова И. О. и др. Анализ состояния растений с применением технологий искусственного интеллекта // Вестник кибернетики. 2022. № 4. С. 6–13.
9. TensorFlow Core. URL: https://www.tensorflow.org/ overview (дата обращения: 20.01.2023).
10. Bochkovskiy A., Wang C., Liao H. M. YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv. 2020. URL: https://arxiv.org/pdf/2004.10934.pdf (дата обращения: 20.01.2023).
11. Pereira R., Carvalho G., Garrote L., Nunes U. J. Sort and Deep-SORT Based Multi-Object Tracking for Mobile Robotics: Evaluation with New Data Association Metrics. Appl Sci. 2022. Vol. 12, No. 3. P. 1319. DOI 10.3390/app12031319.
12. Keras Applications. URL: https://keras.io/api/appli cations/ (дата обращения: 20.01.2023).
Review
For citations:
Matokhina A.V., Tishchenko V.V. ANALYSIS OF PLANTS’ GROWTH USING COMPUTER VISION METHODS. Proceedings in Cybernetics. 2023;22(1):29-35. (In Russ.) https://doi.org/10.35266/1999-7604-2023-1-29-35
Views:
156
Email this article 