Analisis Performa Haar Cascade untuk Estimasi Jarak Aman Kendaraan Berbasis Monocular Vision pada Kondisi Dinamis
DOI:
https://doi.org/10.55123/storage.v5i3.8909Keywords:
Deteksi Jarak, Haar Cascade, MSE, Jarak Aman,, Monocular VisionAbstract
Penelitian ini mengevaluasi performa Haar Cascade untuk deteksi pelat kendaraan dan estimasi jarak berbasis monocular vision pada kondisi dinamis. Pengujian dilakukan pada tiga variasi kecepatan rencana (10, 20, dan 30 km/jam) dan tiga jarak (5, 10, dan 30 meter). Sistem dilatih menggunakan 30 citra positif dan 30 citra negatif, kemudian diuji menggunakan 2.700 observasi yang berasal dari satu video berdurasi 255 detik. Hasil menunjukkan tingkat deteksi pelat berada pada rentang 18,00% - 91,67% dengan rata-rata 65,55%. Performa terbaik diperoleh pada jarak 5 meter, sedangkan pada jarak 30 meter tingkat deteksi menurun menjadi 18,00% - 70,33%. Analisis menunjukkan bahwa penyusutan ukuran pelat menjadi sekitar 20 - 25 piksel pada jarak 30 meter mengurangi informasi visual yang tersedia bagi classifier. Temuan ini menunjukkan bahwa Haar Cascade masih berpotensi sebagai pendekatan lightweight untuk deteksi jarak dekat, tetapi belum memberikan performa yang konsisten untuk mendukung estimasi jarak aman pada jarak jauh. Keterbatasan utama penelitian meliputi ukuran dataset latih yang kecil, penggunaan satu video pengujian, dan belum tersedianya ground truth jarak per frame sehingga MAE/RMSE jarak serta precision, specificity, dan F1-score penuh belum dapat dihitung secara valid.
Downloads
References
Berhanu, Y., Schröder, D., Wodajo, B.T., Alemayehu, E., 2024. Machine learning for predictions of road traffic accidents and spatial network analysis for safe routing on accident and congestion-prone road networks. Results in Engineering 23, 102737. https://doi.org/10.1016/J.RINENG.2024.102737
Chen, S.H., Chen, R.S., 2011. Vision-based distance estimation for multiple vehicles using single optical camera, in: Proceedings - 2011 2nd International Conference on Innovations in Bio-Inspired Computing and Applications, IBICA 2011. pp. 9–12. https://doi.org/10.1109/IBICA.2011.7
Donghao Qiao, 2020. Vision-based Vehicle Detection and Distance Estimation. IEEE.
Erbani, J., Portier, P.É., Egyed-Zsigmond, E., Nurbakova, D., 2024. Confusion Matrices: A Unified Theory. IEEE Access 12, 181372–181419. https://doi.org/10.1109/ACCESS.2024.3507199
Hao, Y., Zhu, Q., Ye, H., Zang, Z., Xia, A., Zheng, S., Chang-Hasnain, C., Fu, H.Y., 2026. Cost-effective frequency-chirped amplitude-modulated continuous-wave LiDAR via MZI-coupled quadratic optical frequency sweep. Opt. Laser Technol. 204, 116137. https://doi.org/10.1016/J.OPTLASTEC.2026.116137
Kumar, S., Karthika, R., Kumar, A., 2026. A monocular vision-based framework for metric distance estimation of vehicles and pedestrians using a zero-shot depth estimation model. Ain Shams Engineering Journal 17, 104246. https://doi.org/10.1016/J.ASEJ.2026.104246
Lee, S., Han, K., Park, S., Yang, X., 2022. Vehicle Distance Estimation from a Monocular Camera for Advanced Driver Assistance Systems. Symmetry (Basel). 14. https://doi.org/10.3390/sym14122657
Lv, H., Du, Y., Ma, Y., Yuan, Y., 2024. Object Detection and Monocular Stable Distance Estimation for Road Environments: A Fusion Architecture Using YOLO-RedeCa and Abnormal Jumping Change Filter. Electronics (Switzerland) 13. https://doi.org/10.3390/electronics13153058
Mehta, A.A., Padaria, A.A., Bavisi, D.J., Ukani, V., Thakkar, P., Geddam, R., Kotecha, K., Abraham, A., 2024. Securing the Future: A Comprehensive Review of Security Challenges and Solutions in Advanced Driver Assistance Systems. IEEE Access 12, 643–678. https://doi.org/10.1109/ACCESS.2023.3347200
Mohammadi, K., 2024. Prioritized Object Detection Integrating Fuzzy Logic Risk assessment and Planned Path.
Sreevidya, P., Veni, S., Rajeev, V., Krishnanugrah, P.U., 2020. Compressive Sensing-Aided Collision Avoidance System. The Cognitive Approach in Cloud Computing and Internet of Things Technologies for Surveillance Tracking Systems 121–140. https://doi.org/10.1016/B978-0-12-816385-6.00009-X
Viola, P., Jones, M., 2001. Rapid Object Detection using a Boosted Cascade of Simple Features.
Wang, Z., Zhang, K., Wu, F., Lv, H., 2025. YOLO-PEL: The Efficient and Lightweight Vehicle Detection Method Based on YOLO Algorithm. Sensors 25. https://doi.org/10.3390/s25071959
Yang, R., Yu, S., Yao, Q., Huang, J., Ya, F., 2023. Vehicle Distance Measurement Method of Two-Way Two-Lane Roads Based on Monocular Vision. Applied Sciences (Switzerland) 13. https://doi.org/10.3390/app13063468
Yao, C., Feng, S., Zhang, F., Si, H., 2017. Vehicle-Distance Measurement Based on Plate Area. Xitong Fangzhen Xuebao / Journal of System Simulation 29, 2820–2827. https://doi.org/10.16182/j.issn1004731x.joss.201711031
Zhao, D., Yu, J., Wei, Y., Huang, K., Xiang, P., Zhou, H., Asano, Y., Li, Y., Arun, P. V., 2026. Depth–area estimation-based hyperspectral video tracker for scale variation adaptation. Eng. Appl. Artif. Intell. 181, 115778. https://doi.org/10.1016/J.ENGAPPAI.2026.115778
Zhou, J., Sun, C., Seo, Y., Kim, Y., 2026. A Framework for Monocular Distance Estimation of Visually Small Objects Under Pixel-Sparse Conditions. IEEE Access 14, 90487–90500. https://doi.org/10.1109/ACCESS.2026.3703860
Downloads
Published
Issue
Section
License
Copyright (c) 2026 thiara manguma, Emil Fatra
This work is licensed under a Creative Commons Attribution 4.0 International License.
