İnsansız Hava Aracı ve Görüntü İşleme Destekli Yasaklı Bitki Tespiti

Abstract

Bu çalışmada insansız hava aracı (İHA) ile tarım arazileri üzerinden alınan görüntüler ile YOLOv11 ve YOLOv26 görüntü işleme algoritmaları kullanılarak tarım arazilerinde ekilmesi yasak olan bitkilerin tespiti gerçekleştirilecektir. Çalışma yazılım kiti ve donanım kiti olmak üzere iki aşamadan oluşmaktadır. Yazılım kitinde görüntü işleme algoritmalarının veri seti, eğitimi, testi ve program ara yüzü geliştirilecektir. Kullanılacak algoritmaların aynı veri seti üzerinden eğitimleri yapılacak, performans metrikleri incelenip en iyi performansı veren algoritma yazılım kitinde kullanılacaktır. Ara yüzün geliştirilmesi ve diğer tüm yazılım bileşenleri Python dilinde yapılmıştır. Donanım kiti ise projenin tüm donanımsal öğelerini içermektedir. Tasarlanan yazılım kiti, donanım kitinde bulunan Raspberry pi içerisinde çalışacaktır. İHA ve şarj istasyonu kendisine ayrılan alan içerisinde muhafaza edilecektir. Önerilen çalışma ile tarım arazilerinde ekilmesi yasak olan bitkilerin tespiti yapılarak erken müdahale edilmesinin avantajı sağlanacaktır. Ayrıca yasak bitkilerinin ekiminin tespiti yapılarak kolluk kuvvetlerinin hem personel hem de zaman ihtiyacını minimuma indirmesi planlanmaktadır.

Keywords

• İHA
• YOLO
• Görüntü İşleme
• Python

Detection of Prohibited Plants Using Unmanned Aerial Vehicles and Image Processing

Abstract

In this study, images captured over agricultural fields using an unmanned aerial vehicle (UAV) will be analyzed using the YOLOv11 and YOLOv26 image processing algorithms to detect plants whose cultivation is prohibited in agricultural fields. The study consists of two phases: a software kit and a hardware kit. The software kit will include the data set for image processing algorithms, training, testing, and program interface development. The algorithms to be used will be trained on the same data set, performance metrics will be examined, and the algorithm with the best performance will be used in the software kit. The interface development and all other software components are written in Python. The hardware kit contains all the hardware elements of the project. The designed software kit will run on the Raspberry Pi included in the hardware kit. The UAV and charging station will be stored in their designated areas. The proposed work will provide the advantage of early intervention by detecting plants that are prohibited from being cultivated on agricultural land. Furthermore, it is planned to minimize the personnel and time requirements of law enforcement agencies by detecting the cultivation of prohibited plants.

Keywords

• UAV
• YOLO
• Image Processing
• Python

References

1. [1] M. Akkamiş and S. Çalişkan, “İnsansız Hava Araçları ve Tarımsal Uygulamalarda Kullanımı,” Türkiye İnsansız Hava Araçları Dergisi, vol. 2, no. 1, pp. 8–16, Jun. 2020.
2. [2] B. Şin and İ. Kadioğlu, “İnsansız Hava Aracı (İHA) ve Görüntü İşleme Teknikleri Kullanılarak Yabancı Ot Tespitinin Yapılması,” Turkish Journal of Weed Science, vol. 20, no. 2, pp. 211–217, Jan. 2019.
3. [3] M. U. Rehman, H. Eesaar, Z. Abbas, L. Seneviratne, I. Hussain, and K. T. Chong, “Advanced drone-based weed detection using feature-enriched deep learning approach,” Knowledge-Based Systems, vol. 305, no. 1, Dec. 2024, doi: 10.1016/j.knosys.2024.112655.
4. [4] F. Dang, D. Chen, Y. Lu, and Z. Li, “YOLOWeeds: A novel benchmark of YOLO object detectors for multi-class weed detection in cotton production systems,” Computers and Electronics in Agriculture, vol. 205, pp. 1–14, Feb. 2023, doi: 10.1016/j.compag.2023.107655.
5. [5] T. B. Shahi, S. Dahal, C. Sitaula, A. Neupane, and W. Guo, “Deep Learning-Based Weed Detection Using UAV Images: A Comparative Study,” Drones, vol. 7, no. 10, Oct. 2023, doi: 10.3390/drones7100624.
6. [6] R. Rosle et al., “Weed Detection in Rice Fields Using UAV and Multispectral Aerial Imagery,” in Chemistry Proceedings, M. Francesco, Ed., Basel: MDPI AG, Jul. 2022, p. 44. doi: 10.3390/iocag2022-12519.
7. [7] Y. Li, Z. Guo, Y. Sun, X. Chen, and Y. Cao, “Weed Detection Algorithms in Rice Fields Based on Improved YOLOv10n,” Agriculture (Switzerland), vol. 14, no. 11, Nov. 2024, doi: 10.3390/agriculture14112066.
8. [8] N. P. Caliston, C. J. G. Aliac, and J. A. E. Nogra, “UAV Weed Detection Function in a Smartphone-Based Flight Computer,” in 2024 4th International Conference on Computer Communication and Artificial Intelligence, CCAI 2024, C. Wenchi, Ed., Xi’an: Institute of Electrical and Electronics Engineers Inc., May 2024, pp. 14–19. doi: 10.1109/CCAI61966.2024.10603294.

9. [9] P. Wang et al., “Weed25: A deep learning dataset for weed identification,” Frontiers in Plant Science, vol. 13, no. 1, pp. 1–14, Nov. 2022, doi: 10.3389/fpls.2022.1053329.
10. [10] O. G. Ajayi, J. Ashi, and B. Guda, “Performance evaluation of YOLO v5 model for automatic crop and weed classification on UAV images,” Smart Agricultural Technology, vol. 5, Oct. 2023, doi: 10.1016/j.atech.2023.100231.
11. [11] E. Onler, “REAL TIME PEST DETECTION USING YOLOv5,” International Journal of Agricultural and Natural Sciences E, vol. 14, no. 3, pp. 232–246, Nov. 2021.
12. [12] Z. Wu, Y. Chen, B. Zhao, X. Kang, and Y. Ding, “Review of weed detection methods based on computer vision,” Jun. 01, 2021, MDPI AG. doi: 10.3390/s21113647.
13. [13] F. López-Granados, “Weed detection for site-specific weed management: mapping and real-time approaches,” Weed Research, vol. 51, no. 1, pp. 1–11, 2011, doi: https://doi.org/10.1111/j.1365-3180.2010.00829.x.
14. [14] T. Islam, T. T. Sarker, K. R. Ahmed, and N. Lakhssassi, “Detection and Classification of Cannabis Seeds Using RetinaNet and Faster R-CNN,” Seeds, vol. 3, no. 3, pp. 456–478, 2024, doi: 10.3390/seeds3030031.
15. [15] J. F. Q. Pereira, M. F. Pimentel, J. M. Amigo, and R. S. Honorato, “Detection and identification of Cannabis sativa L. using near infrared hyperspectral imaging and machine learning methods. A feasibility study,” Spectrochimica Acta - Part A: Molecular and Biomolecular Spectroscopy, vol. 237, 2020, doi: 10.1016/j.saa.2020.118385.
16. [16] Y. Guno, M. Y. Rezaldi, F. R. Triputra, and R. Suhud, “Traitement du Signal Images Processing of Unmanned Aerial Vehicle ( UAV ) for Cannabis Identification,” vol. 41, no. 3, pp. 1473–1483, 2024, doi: https://doi.org/10.18280/ts.410335.
17. [17] Z. Zhang, W. Xia, G. Xie, and S. Xiang, “Fast Opium Poppy Detection in Unmanned Aerial Vehicle (UAV) Imagery Based on Deep Neural Network,” Drones, vol. 7, no. 9, 2023, doi: 10.3390/drones7090559.
18. [18] C. Wang, Q. Wang, H. Wu, C. Zhao, G. Teng, and J. Li, “Low-altitude remote sensing opium poppy image detection based on modified yolov3,” Remote Sensing, vol. 13, no. 11, pp. 1–17, 2021, doi: 10.3390/rs13112130.
19. [19] J. Zhou, Y. Tian, C. Yuan, K. Yin, G. Yang, and M. Wen, “Improved UAV opium poppy detection using an updated YOLOV3 model,” Sensors (Switzerland), vol. 19, no. 22, pp. 1–23, 2019, doi: 10.3390/s19224851.
20. [20] X. Liu, Y. Tian, C. Yuan, F. Zhang, and G. Yang, “Opium poppy detection using deep learning,” Remote Sensing, vol. 10, no. 12, pp. 1–21, 2018, doi: 10.3390/rs10121886.
21. [21] F. Bicakli, G. Kaplan, and A. S. Alqasemi, “Cannabis sativa L. Spectral Discrimination and Classification Using Satellite Imagery and Machine Learning,” Agriculture (Switzerland), vol. 12, no. 6, 2022, doi: 10.3390/agriculture12060842.