Deteksi Kecelakaan Lalu Lintas Menggunakan YOLO11 pada Citra Kamera CCTV untuk Klasifikasi Jenis Kendaraan Terlibat
Abstract
Kecelakaan lalu lintas merupakan masalah serius dengan lebih dari 1,19 juta kematian setiap tahun di dunia dan 148.307 kasus di Indonesia pada 2023. Sistem pengawasan yang ada sebagian besar masih manual sehingga belum mampu mendeteksi dan mengklasifikasikan kecelakaan secara otomatis. Topik ini penting karena keterlambatan dalam deteksi kecelakaan dapat memperburuk dampak bagi korban. Solusi otomatis dapat mempercepat respons, mengurangi kerugian, serta mendukung sistem transportasi cerdas. Saat ini terdapat kesenjangan antara kebutuhan sistem otomatis dengan keterbatasan pendekatan manual yang dominan digunakan. Penelitian ini mengembangkan model deteksi kecelakaan berbasis YOLO11 untuk mengidentifikasi insiden serta mengklasifikasikan jenis kendaraan yang terlibat, yaitu car_accident, car_motorbike_accident, dan motorbike_accident. Model dilatih menggunakan 1.483 data citra dari berbagai sumber, kemudian dievaluasi dengan metrik precision, recall, [email protected], dan [email protected]:0.95. Percobaan lain dilakukan melalui strategi fine-tuning seperti freeze layer, augmentasi data, dan penggunaan optimizer AdamW. Model baseline menghasilkan performa terbaik dengan precision 0,82, recall 0,79, dan [email protected] sebesar 0,84. Setelah fine-tuning, kinerja model menjadi lebih stabil dengan precision 0,81, recall 0,72, [email protected] sebesar 0,75, dan [email protected]:0.95 yang lebih konsisten. Hasil ini menunjukkan performa yang lebih seimbang antar kelas dan berpotensi mendukung pengawasan lalu lintas yang lebih cerdas.
References
World Health Organization, “Global status report on road safety 2023,” Geneva, 2023.
D. A. Muhammad and A. Maulana, “Sepanjang 2023 Ada 148.307 Kasus Kecelakaan di Seluruh Indonesia, Jawa Timur Mendominasi,” Kompas.com, Jakarta, Jan. 16, 2024. Accessed: Aug. 11, 2025. [Online]. Available: https://otomotif.kompas.com/read/2024/01/16/181200215/sepanjang-2023-ada-148.307-kasus-kecelakaan-di-seluruh-indonesia-jawa-timur
Z. Xi, X. Liu, Y. Liu, Y. Cai, and Y. Zheng, “Integrating Generative Adversarial Networks and Convolutional Neural Networks for Enhanced Traffic Accidents Detection and Analysis,” IEEE Transactions on Intelligent Transportation Systems, pp. 1–10, 2025, doi: 10.1109/TITS.2025.3573172.
M. C. Cruz and N. N. Ferenchak, “Emergency Response Times for Fatal Motor Vehicle Crashes, 1975–2017,” Transportation Research Record: Journal of the Transportation Research Board, vol. 2674, no. 8, pp. 504–510, Aug. 2020, doi: 10.1177/0361198120927698.
M. S. Pillai, G. Chaudhary, M. Khari, and R. G. Crespo, “Real-time image enhancement for an automatic automobile accident detection through CCTV using deep learning,” Soft comput, vol. 25, no. 18, pp. 11929–11940, Sep. 2021, doi: 10.1007/s00500-021-05576-w.
M. I. Basheer Ahmed et al., “A Real-Time Computer Vision Based Approach to Detection and Classification of Traffic Incidents,” Big Data and Cognitive Computing, vol. 7, no. 1, p. 22, Jan. 2023, doi: 10.3390/bdcc7010022.
D. T. Mane, S. Sangve, S. Kandhare, S. Mohole, S. Sonar, and S. Tupare, “Real-Time Vehicle Accident Recognition from Traffic Video Surveillance using YOLOV8 and OpenCV,” International Journal on Recent and Innovation Trends in Computing and Communication, vol. 11, no. 5s, pp. 250–258, May 2023, doi: 10.17762/ijritcc.v11i5s.6651.
M. D. Fontaine, C. S. Bhamidipati, and L. E. Dougald, “Safety Impact of Truck Lane Restrictions on Multilane Freeways,” Transportation Research Record: Journal of the Transportation Research Board, vol. 2096, no. 1, pp. 25–32, Jan. 2009, doi: 10.3141/2096-04.
R. Khanam and M. Hussain, “YOLOv11: An Overview of the Key Architectural Enhancements,” ArXiv, Oct. 2024.
V. A. Adewopo and N. Elsayed, “Smart City Transportation: Deep Learning Ensemble Approach for Traffic Accident Detection,” IEEE Access, vol. 12, pp. 59134–59147, 2024, doi: 10.1109/ACCESS.2024.3387972.
M. Farhan, H. Eesaar, A. Ahmed, K. T. Chong, and H. Tayara, “Transforming Highway Safety With Autonomous Drones and AI: A Framework for Incident Detection and Emergency Response,” IEEE Open Journal of Vehicular Technology, vol. 6, pp. 829–845, 2025, doi: 10.1109/OJVT.2025.3549387.
A. Buntara, “Cedera Akibat Kecelakaan Lalu Lintas di Indonesia: Faktor Risiko serta Strategi Pencegahan dan Intervensi,” Jurnal Ilmiah Kesehatan Masyarakat, vol. 11, no. 3, 2019.
W. Riyadina and I. P. Subik, “Profil keparahan cedera pada korban kecelakaan sepeda motor di Instalasi Gawat Darurat RSUP Fatmawati,” Universa Medicina, vol. 28, no. 2, pp. 64–72, 2007.
Q. Wu et al., “Analysis of Injury Severity of Drivers Involved Different Types of Two-Vehicle Crashes Using Random-Parameters Logit Models with Heterogeneity in Means and Variances,” J Adv Transp, vol. 2023, pp. 1–15, Oct. 2023, doi: 10.1155/2023/3399631.
S. Conrady and L. Jouffe, “Vehicle Size, Weight, and Injury Risk: High-Dimensional Modeling and Causal Inference with Bayesian Networks,” Jun. 2013.
I. Adnan, T. Umer, A. Arsalan, M. M. Al Dabel, A. K. Bashir, and A. Ansif, “Data driven vehicular heterogeneity based intelligent collision avoidance system for Internet of Vehicles (IoV),” Digital Communications and Networks, Apr. 2025, doi: 10.1016/j.dcan.2025.03.010.
C. Carrodano, “Data-driven risk analysis of nonlinear factor interactions in road safety using Bayesian networks,” Sci Rep, vol. 14, no. 1, p. 18948, Aug. 2024, doi: 10.1038/s41598-024-69740-6.
Z. Zhou, “Traffic accident detection based on YOLOv11,” in 2024 IEEE 2nd International Conference on Electrical, Automation and Computer Engineering (ICEACE), IEEE, Dec. 2024, pp. 363–369. doi: 10.1109/ICEACE63551.2024.10898397.
M. A. R. Alif, “YOLOv11 for Vehicle Detection: Advancements, Performance, and Applications in Intelligent Transportation Systems,” Oct. 2024.
C. C. Kumar, “Accident Detection From CCTV Footage,” Kaggle. Accessed: Aug. 11, 2025. [Online]. Available: https://doi.org/10.34740/KAGGLE/DSV/1379553
Tammy, “bike_accident Dataset,” Roboflow Universe. Accessed: Aug. 11, 2025. [Online]. Available: https://universe.roboflow.com/tammy/bike_accident
DatasetV5p1, “training-4 Dataset,” Roboflow Universe. Accessed: Aug. 11, 2025. [Online]. Available: https://universe.roboflow.com/datasetv5p1/training-4
F. Shahidi, S. Mohd Daud, H. Abas, N. A. Ahmad, and N. Maarop, “Breast Cancer Classification Using Deep Learning Approaches and Histopathology Image: A Comparison Study,” IEEE Access, vol. 8, pp. 187531–187552, 2020, doi: 10.1109/ACCESS.2020.3029881.
V. R. Joseph, “Optimal ratio for data splitting,” Statistical Analysis and Data Mining: The ASA Data Science Journal, vol. 15, no. 4, pp. 531–538, Aug. 2022, doi: 10.1002/sam.11583.
M. Jeri and Z. S. Hidayat, “Penentuan ukuran batch optimal untuk pelatihan YOLOv8 dalam pendeteksian objek pada kendaraan otonom,” Jurnal Ilmiah NERO, 2024.
N. Das and S. Das, “Epoch and accuracy based empirical study for cardiac MRI segmentation using deep learning technique,” PeerJ, vol. 11, p. e14939, Mar. 2023, doi: 10.7717/peerj.14939.
Published
Versions
- 2025-11-05 (2)
- 2025-11-05 (2)
- 2025-11-05 (1)
