YOLO Tabanlı ANFIS Kontrollü İnsansız Kara Aracı ile Hastalıklı Bitkilerin Tespiti ve İlaçlanması

Abstract

Bitki hastalıkları modern tarımda önemli bir sorun olmaya devam etmektedir ve hem verimde hem de ürün kalitesinde önemli düşüşlere neden olmaktadır. Bu çalışma, bitki hastalıklarını gerçek zamanlı olarak tespit edebilen ve hedefli ilaçlama yoluyla otonom olarak müdahale edebilen bir insansız kara aracının (İKA) geliştirilmesini amaçlamaktadır. UGV'ye monte edilmiş bir kamera, ürün sıralarının sürekli görüntülerini yakalar ve hastalık tespiti, gerçek zamanlı nesne tanımadaki hızı ve doğruluğu nedeniyle seçilen YOLO (You Only Look Once) algoritması kullanılarak gerçekleştirilir. Model performansını değerlendirmek için, YOLOv7, v8 ve v9, erken ve geç yanıklık dahil olmak üzere patates yaprak hastalıklarına odaklanan veri kümeleri kullanılarak eğitildi. YOLOv8 modeli, üstün tespit doğruluğuna dayanarak bir Raspberry Pi 4B'de kullanılmak üzere seçildi. Ek olarak, kameranın kapsamını genişletmek için servo motorla geliştirilmiş bir görüş sistemi uygulandı. UGV'nin otonom sürüşü, navigasyon ve hareket planlamasını yöneten beş ultrasonik sensör ve ANFIS (Uyarlanabilir Nöro-Bulanık Çıkarım Sistemi) tabanlı bir karar verme modülünün birleşimiyle sağlanır. Araç tarlada ilerlerken, yerleşik sistem enfekte bitkileri belirler ve yalnızca etkilenen alanları tedavi etmek için bir enjektör mekanizmasını etkinleştirir. Bu entegre yaklaşım, pestisit kullanımını önemli ölçüde azaltır, çevresel zararı en aza indirir ve el ile yapılan çalışmalara bağımlılığı düşürür. Sonuçlar, hassas tarımda sürdürülebilir ve verimli hastalık yönetimi için yapay zekanın ve gömülü sistemlerin uygulamasının umut verici olduğunu göstermektedir.

Keywords

• Hastalıklı Bitki Tespiti
• YOLO
• Püskürtme
• ultrasonik sensör
• Raspberry Pi
• hareket planlama
• ANFIS

Detection and Disinfestation of Diseased Plants with YOLO Based ANFIS Controlled Unmanned Ground Vehicle

Abstract

Plant diseases remain a major challenge in modern agriculture, causing considerable reductions in both yield and crop quality. This study focuses on the development of an intelligent unmanned ground vehicle (UGV) capable of detecting plant diseases in real time and autonomously responding through targeted spraying. A camera mounted on the UGV captures continuous images of crop rows, and disease detection is carried out using the YOLO (You Only Look Once) algorithm—chosen for its speed and accuracy in real-time object recognition. To evaluate model performance, YOLOv7, v8, and v9 were trained using datasets focused on potato leaf diseases, including early and late blight. The YOLOv8 model was selected for deployment on a Raspberry Pi 4B based on its superior detection accuracy. Additionally, a servo motor-enhanced vision system was implemented to broaden the camera’s coverage. The UGV's autonomous driving is enabled by a combination of five ultrasonic sensors and an ANFIS (Adaptive Neuro-Fuzzy Inference System)-based decision-making module, which governs navigation and motion planning. As the vehicle traverses the field, the onboard system identifies infected plants and activates a localized spraying mechanism to treat only the affected areas. This integrated approach significantly reduces pesticide use, minimizes environmental harm, and lowers the dependency on manual labor. The results demonstrate a promising application of artificial intelligence and embedded systems for sustainable and efficient disease management in precision agriculture.

Keywords

• Diseased Plant Detection
• YOLO
• Spraying
• ultrasonic sensor
• Raspberry Pi
• motion planning
• ANFIS

References

1. [1] A. Shill, “Plant Disease Detection Based on YOLOv3 and YOLOv4,” in Proc. Int. Conf. on Automation, Control and Mechatronics for Industry 4.0 (ACMI), Rajshahi, Bangladesh, Jul. 8–9, 2021.
2. [2] V. Singh and A. K. Misra, “Detection of plant leaf diseases using image segmentation and soft computing techniques,” Information Processing in Agriculture, 2016.
3. [3] J. A. Soeb, F. Jubayer and I. Meftaul, “Tea leaf disease detection and identification based on YOLOv7,” Scientific Reports, [Online].
4. [4] T.Y. Mahesh, "Leaf Disease Detection in Bell Pepper Using YOLOv5," International Journal of Engineering Research & Technology (IJERT), Vol. 12, 2023.
5. [5] M.P. Reddy and A. Deeksha, "Mulberry Leaf Disease Detection Using YOLO," International Journal of Advance Research, Ideas and Innovations in Technology, Vol. 7, No. 3, 2021.
6. [6] S. Verma, D. Khare, R. Gupta and G. Singh, "Analysis of Image Segmentation Algorithms Using MATLAB," Proceedings of the Third International Conference on Trends in Information, Telecommunication and Computing, pp. 163-172, 2012.
7. [7] L. Dung, "Real-Time Tomato Leaf Disease Detection Using Single Shot Detector on Raspberry Pi 3," Unpublished.
8. [8] S. Kumar and K. Dineshraja, "Development of a Real-Time Plant Species Recognizing Rover," 13th International Conference on Computing, Communication and Networking Technologies (ICCCNT), 2021.

9. [9] R. Sharanesh, et al., "Plant Disease Detection in Strawberry and Grape Using VGGNet16 and InceptionResNetv2 Architectures," 2019 4th International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS), 2019.
10. [10] J.O. Ahmed, et al., "Real-Time Agricultural Monitoring with Agrobot: A Raspberry Pi and YOLO Based Solution”, International Conference on Computer and Applications (ICCA), Egypt, 28-30 November 2023.
11. [11] R. Gorapudi, B.R.S.P. Rudrapaka and A.S. Valluri, "Design and Implementation of Pesticide Spraying Robot Using IoT," International Journal of Advance Research and Innovation, Vol. 8, No. 2, pp. 36-41, 2020.
12. [12] M. S. Vani, S. Girinath, V. Hemasree, L. H. Havardhan, and P. Sandhya, "Plant disease identification tracking and forecasting using machine learning," in Proc. 2023 3rd Int. Conf. Technological Advancements in Computational Sciences (ICTACS), Nov. 1–3, 2023, pp. 1428–1432, Conf. ID: 59847
13. [13] R. Hamzah, L. Ang, R. Roslan, N. H. I. Teo, K. A. Samad, and K. A. F. A. Samah, "Comparing modified YOLO v5 and Faster Regional Convolutional Neural Network performance for recycle waste classification," in Proc. 2024 IEEE Int. Conf. Automatic Control and Intelligent Systems (I2CACIS), Shah Alam, Malaysia, 29 June 2024, pp. 415–419. [14] S. Pandey, K.-F. Chen and E. B. Dam, "Comprehensive Multimodal Segmentation in Medical Imaging: Combining YOLOv8 with SAM and HQ-SAM Models," 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Paris, France, 2023, pp.2584-2590, doi: 10.1109/ICCVW60793.2023.00273.
14. [15] S. Pandey, K.-F. Chen and E. B. Dam, "Comprehensive Multimodal Segmentation in Medical Imaging: Combining YOLOv8 with SAM and HQ-SAM Models," 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Paris, France, 2023, pp.2584-2590, doi: 10.1109/ICCVW60793.2023.00273.
15. [16] P. Sajitha, A. John, V. L. Devika, S. V. Gayathri and N. Sakhir, “Leaf disease detection & correction using YOLOv7 with GPT-3 integrated,” Int. J. of Engineering Research & Technology (IJERT), vol. 12, 2023.
16. [17] H. Yi, B. Liu, B. Zhao ve E. Liu, “Small Object Detection Algorithm Based on Improved YOLOv8 for Remote Sensing,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol.17, pp. 1734–1747,  2024
17. [18] S. Yılmaz And S. B. Kilci, "Modeling and simulation of a fuzzy heat distribution controlled high-voltage DC resistive divider," MEASUREMENT & CONTROL , vol.53, pp.485-500, 2020
18. [19] S. Yılmaz Et Al. , "Erosion rate of AA6082-T6 aluminum alloy subjected to erosive wear determined by the meta-heuristic (SCA) based ANFIS method," MATERIALS TESTING , vol.66, no.2, pp.248-261, 2024
19. [20] O. Rachidi, E. Chafik and B. Bououlid, “Design of a real-time-integrated system based on stereovision and YOLOv5 to detect objects,” [Online].
20. [21] H. Guliyev and S. Yılmaz, "REAL-TIME DISEASE DETECTION USING THE YOLO ALGORITHM WITH A MODULE MOUNTED ON A ROVER," 6th International Azerbaijan Congress on Life, Engineering, Mathematical, and Applied Sciences , vol.1, no.1, Baku, Azerbaijan, pp.247-254, 2024
21. [22] H.Guliyev (Student), Postgraduate,2024, Modeling of Agricultural Unmanned Ground Vehicle and Motion Control Applications Using ANFIS Methods, M.Sc. Thesis, S. Yılmaz (Advisor), Kocaeli University Institute of Science, Kocaeli
22. [23] K. Dineshraja and S. Kumar, “Development of a real-time plant species recognizing rover,” in Proc. 13th Int. Conf. on Computing, Communication and Networking Technologies (ICCCNT), 2021.
23. [24] H. T.Abatari, and A. D. Tafti, “Using a fuzzy PID controller for the path following of a car-like mobile robot”. First RSI/ISM IEEE international conference on robotics and mechatronics (ICRoM) (pp. 189-193), February 2013.
24. [25] P. Panchal, V. C. Raman and S. Mantri, “Plant diseases detection and classification using machine learning models,” in Proc. 4th Int. Conf. on Computational Systems and Information Technology for Sustainable Solution (CSITSS), 2019.
25. [26] R. Abhiram and R. K. Megalingam, "Autonomous Fertilizer Spraying Mobile Robot," in Proceedings of the 2022 IEEE 19th India Council International Conference (INDICON), Bengaluru, India, Nov. 2022, pp. 1–6.
26. [27] A. J. Ahmed, A. Babiker, A. Elhag, and M. Drar, "Real-Time Agricultural Monitoring with Agrobot: A Raspberry Pi and YOLO Based Solution," in Proceedings of the 2023 International Conference on Computer and Applications (ICCA), Kuala Lumpur, Malaysia, Nov. 2023, pp. 1–5. [28] https://avesis.kocaeli.edu.tr/arastirma-grubu/dral