Klasifikasi Tutupan Lahan dengan YOLO dan Data Citra Udara dari Drone
DOI:
https://doi.org/10.26418/jp.v12i1.100629Keywords:
YOLOv8, Drone, Land Cover, Object Classification, Aerial ImageryAbstract
Land cover classification is an important element in spatial analysis for environmental planning and management. This study aims to evaluate the effectiveness of the YOLOv8 algorithm in classifying land cover objects using high-resolution aerial imagery data from drones. Data collection was carried out using a DJI Mavic 1 Pro drone at an altitude of 100 metres, followed by annotation with bounding boxes through the Roboflow platform, division of the dataset into training, validation, and test data, and training of the YOLOv8 model with 50 epochs to measure performance and detection accuracy. The results showed that YOLOv8 was able to detect land cover objects such as buildings, vegetation, and trees with good accuracy, especially in images with a single object. Accuracy decreased in images with two to three objects due to increased spatial complexity and overlap between objects. The bounding box-based approach is effective for detecting individual objects, but it is not yet capable of classifying the entire image area as semantic segmentation methods do. Thus, YOLOv8 has the potential to be applied in monitoring land use change and sustainable environmental management, and can be further developed through integration with segmentation models such as U-Net or Mask R-CNN to improve spatial classification accuracy.References
D. Chu, Land-Cover Classification, Singapore: Springer, 2020, pp. 181–194, doi: 10.1007/978-981-13-7580-4_9.
V. Hnatushenko, V. Kashtan, D. Chumychov, and S. L. Nikulin, “Comparative analysis of classification methods for high-resolution optical satellite images,” Kompyuterni Sistemi Ta Informatsiyni Tekhnologii, vol. 4, pp. 134–142, 2024, doi: 10.31891/csit-2024-4-16.
S. Memon, G. Cavallaro, B. Hagemeier, M. Riedel, and H. Neukirchen, “Automated analysis of remotely sensed images using the Unicore workflow management system,” in Proc. Int. Geosci. Remote Sens. Symp., 2018, pp. 1128–1131, doi: 10.1109/IGARSS.2018.8519364.
S. Patil, S. Waghule, S. Waje, P. Pawar, and S. Domb, “Efficient object detection with YOLO: A comprehensive guide,” Int. J. Adv. Res. Sci. Commun. Technol., 2024, doi: 10.48175/ijarsct-18483.
C. P. Thrupthi, K. Chitra, and M. V. M. Harilakshmi, “Object detection for autonomous vehicles using YOLO algorithm,” Int. J. Adv. Res. Sci. Commun. Technol., pp. 180–184, 2024, doi: 10.48175/ijarsct-22539.
A. S. Samyal, K. R. Akshatha, S. Hans, A. K. Karunakar, and B. SatishShenoy, “Analysis and adaptation of YOLOv4 for object detection in aerial images,” arXiv preprint, arXiv:2203.10194, 2022, doi: 10.48550/arXiv.2203.10194.
H. Hashmi, R. Dwivedi, and A. Kumar, “YOLO-RS: An efficient YOLO-based approach for remote sensing object detection,” in Proc. Smart 2023 Conf., pp. 50–56, 2023, doi: 10.1109/smart59791.2023.10428504.
B. H.-C. Liao, C.-H. Cheng, H. Esen, and A. Knoll, “EC-IoU: Orienting Safety for Object Detectors via Ego-Centric Intersection-over-Union,” arXiv.org, vol. abs/2403.15474, Mar. 2024, doi: 10.48550/arxiv.2403.15474.
A. A. Kuznetsova, “Statistical Precision – Recall curves for object detection quality assessment,” vol. 15, no. 90, pp. 42–57, Dec. 2020, doi: 10.37791/2687-0649-2020-15-6-42-57.
F. Ciaglia, F. S. Zuppichini, P. Guerrie, M. McQuade, and J. Solawetz, “Roboflow 100: A Rich, Multi-Domain Object Detection Benchmark,” arXiv.org, vol. abs/2211.13523, Nov. 2022, doi: 10.48550/arXiv.2211.13523.
P. Zhao and Y. Liu, “Oracle Bone Inscriptions Detection Based On Standard Evaluation Metric,” pp. 49–55, Oct. 2022, doi: 10.1109/ICICML57342.2022.10009736.
S. Kanaga Suba Raja, R. Kumaraperumal, P. Pazhanivelan, R. Jagadeeswaran, and P. Che, “YOLO deep learning algorithm for object detection in agriculture: a review,” Journal of agricultural engineering, vol. 55, no. 4, Dec. 2024, doi: 10.4081/jae.2024.1641.
S. Dogan, J. Walatkiewicz, S. Tout, O. Darwish, and O. Spantidi, “Experimental analysis of fine-tuned drone detection YOLO models,” in Proc. SATC 2025 Conf., pp. 1–5, 2025, doi: 10.1109/satc65530.2025.11137294.
N. TS, “Real time object detection in autonomous vehicle using YOLO V8,” Indian Sci. J. Res. Eng. Manag., vol. 9, no. 5, pp. 1–9, 2025, doi: 10.55041/ijsrem48914.
J. M. Paule et al., “Integration of AWS and Roboflow Mask R-CNN model for a fully cloud-based image segmentation platform,” 2023, doi: 10.1109/hnicem60674.2023.10589105.
B. Berlikozha, A. Serek, B. Amirgaliyev, M. Mussabek, and А. Zhumadillayeva, “Comprehensive evaluation of real-time object detection algorithm based on extended criteria,” M. Tynyšpaev Kazakh Academy Bulletin, vol. 134, no. 5, pp. 239–246, 2024, doi: 10.52167/1609-1817-2024-134-5-239-246.
A. Bhola, B. Debnath, and A. Tiwari, “A systematic study on aerial images of various domains,” pp. 1–31, 2024, doi: 10.1002/9781394175512.ch1.
S. Prakljačić, R. Grbić, M. Vranješ, and M. Herceg, “Tool for image annotation in context of modern object detection,” 2024, doi: 10.1109/zinc61849.2024.10579415.
F. Ahmed, R. Ferdows, Md. R. Islam, and A. R. M. Kamal, “DeepVis: A visual interactive system for exploring performance of deep learning models,” in Proc. Int. Conf. Innov. Eng. Technol., pp. 398–402, 2022, doi: 10.1109/ICIET55102.2022.9779032.
X. Xiang and Q. Zhou, “YOLOOC: YOLO-based open-class incremental object detection with novel class discovery,” arXiv preprint, arXiv:2404.00257, 2024, doi: 10.48550/arxiv.2404.00257.
H. Xiao et al., “YOLO-Q: Drone aerial target detection,” in Proc. PRML 2023 Conf., pp. 13–20, 2023, doi: 10.1109/prml59573.2023.10348218.
R. Apsara and S. R. Harikrishnan, “Object detection in satellite images using computer vision models,” Int. J. Adv. Res. Sci. Commun. Technol., pp. 366–372, 2024, doi: 10.48175/ijarsct-19255.
J. Lee, J. Yi, C. Shin, and S. Yoon, “BBAM: Bounding box attribution map for weakly supervised semantic and instance segmentation,” arXiv: Comput. Vis. Pattern Recognit., 2021. [Online]. Available: http://export.arxiv.org/pdf/2103.08907
