PREDIKSI JALUR JALAN BERBASIS KALMAN FILTER PADA SISTEM ADAS (ADVANCE DRIVING ASSISTANCE SYSTEM) MENGGUNAKAN HOUGH TRANSFORM DENGAN KAMERA BERSUDUT PANDANG TERBATAS
DOI:
https://doi.org/10.52453/t.v16i1.472Keywords:
Road Lane Detection, Region of Interest, Kalman FilterAbstract
Deteksi jalur jalan (road lane detection) merupakan komponen penting dalam sistem bantuan pengemudi cerdas kendaraan otonom. Namun, tantangan muncul ketika kamera dipasang pada kaca depan bagian atas kendaraan dengan sudut pandang terbatas, terutama saat kendaraan berbelok. Keterbatasan ini menyebabkan area region of interest (ROI) menjadi sempit, bahkan jalur tidak terdeteksi sama sekali. Penelitian ini mengusulkan pendekatan kombinasi antara metode deteksi garis berbasis Hough Transform Probabilistik (HoughLinesP) dan prediksi posisi jalur menggunakan Kalman Filter. Ketika jalur hanya sebagian terdeteksi atau tidak terdeteksi karena keterbatasan sudut kamera, Kalman Filter digunakan untuk memprediksi posisi jalur berdasarkan pergerakan titik-titik sebelumnya. Hasil eksperimen menunjukkan bahwa pendekatan ini mampu mempertahankan estimasi posisi jalur secara stabil dan akurat meskipun terjadi kehilangan sebagian informasi visual akibat keterbatasan pandangan kamera. Metode ini meningkatkan keandalan sistem deteksi jalur dalam kondisi lingkungan dinamis dan sudut pandang sempit.
References
N. Gyulyev, O. Prasolenko, E. Litomin, and D.Zinchenko, “Study of the influence of road congestion on the fatigue level of a sanguine driver,” Technology audit and production reserves, vol. 6, no. 2(50), pp. 31–35, Nov. 2019, doi: 10.15587/2312-8372.2019.191275.
Z. Luo, Y. Bi, Q. Ye, Y. Li, and S. Wang, “A Novel Machine Vision-Based Collision Risk Warning Method for Unsignalized Intersections on Arterial Roads,” Electronics (Switzerland), vol. 14, no. 6, Mar. 2025, doi:10.3390/electronics14061098.
M. M. Narkhede and N. B. Chopade, “Review of advanced driver assistance systems and their applications for collision avoidance in urban driving scenario,” in Machine Learning and Big Data Analytics (Proceedings of International Conference on Machine Learning and Big Data Analytics (ICMLBDA) 2021), 2022, pp. 253–267.
Q. Cao, Z. Zhao, Q. Zeng, Z. Wang, and K. Long, “Real-Time Vehicle Trajectory Prediction for Traffic Conflict Detection at Unsignalized Intersections,” J Adv Transp, vol. 2021, 2021, doi: 10.1155/2021/8453726.
D. GHEORGHE, “The Need of Advanced Driver-Assistance System’s Development based on an Analysis of Road Accidents,” Informatica Economica, vol. 27, no. 3/2023, pp. 17–28, Sep.2023, doi: 10.24818/issn14531305/27.3.2023.02.
S. A. Useche, M. Faus, and F. Alonso, “‘Cyclist at 12 o’clock!’: a systematic review of in-vehicle advanced driver assistance systems (ADAS) for preventing car-rider crashes,” 2024, Frontiers Media SA. doi: 10.3389/fpubh.2024.1335209.
D. Cao et al., “Research on Apple Detection and Tracking Count in Complex Scenes Based on the Improved YOLOv7-Tiny-PDE,” Agriculture (Switzerland), vol. 15, no. 5, Mar. 2025, doi: 10.3390/agriculture15050483.
I. Kunina, E. I. Panfilova, O. S. Shipitko, and I.A. Kunina, “Fast Hough Transform-Based Road Markings Detection For Autonomous Vehicle.”[Online]. Available:https://www.researchgate.net/publication/345309351
Q. Huang and J. Liu, “Practical limitations of lane detection algorithm based on Hough transform in challenging scenarios,” Int J AdvRobot Syst, vol. 18, no. 2, 2021, doi:10.1177/17298814211008752.
Y. Zhang, P. Gong, S. Ji, and Q. Xu, “Real-time lane detection method based on region of interest,” in 2022 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS), 2022, pp. 1188–1192.
Y. Zhang, Q. Xiao, X. Liu, Y. Wei, and J. Xue,“Method for reconstructing safety and arming motion process by integrating Kalman filter and KCF,” Sci Rep, vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-92957-y.
A. Salhi, F. Ghozzi, and A. Fakhfakh, “Estimation for motion in tracking and detection objects with Kalman filter,” in Dynamic Data Assimilation-Beating the Uncertainties, IntechOpen, 2020.
S. A. Elsagheer Mohamed, K. A. Alshalfan, M.A. Al-Hagery, and M. T. Ben Othman, “Safe Driving Distance and Speed for Collision Avoidance in Connected Vehicles,” Sensors, vol.22, no. 18, Sep. 2022, doi: 10.3390/s22187051.
H. Wei, Y. Huang, F. Hu, B. Zhao, Z. Guo, and R. Zhang, “Motion estimation using region-level segmentation and extended kalman filter for autonomous driving,” Remote Sens (Basel), vol. 13, no. 9, May 2021, doi: 10.3390/rs13091828.
P. Shi, Z. Liu, X. Dong, and A. Yang, “CLfusionBEV: 3D object detection method with camera-LiDAR fusion in Bird’s Eye View,”Complex and Intelligent Systems, Dec. 2024, doi:10.1007/s40747-024-01567-0.
M. Jakubec, M. Cingel, E. Lieskovská, and M. Drliciak, “Integrating Neural Networks for Automated Video Analysis of Traffic Flow Routing and Composition at Intersections,”Sustainability (Switzerland), vol. 17, no. 5, Mar.2025, doi: 10.3390/su17052150.
I. C. Chang et al., “An Effective YOLO-Based Proactive Blind Spot Warning System for Motorcycles,” Electronics (Switzerland), vol. 12, no. 15, Aug. 2023, doi: 10.3390/electronics12153310.
E. Casanova, D. Guffanti, and L. Hidalgo,“Technological Advancements in Human Navigation for the Visually Impaired: A
Systematic Review,” Apr. 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/s25072213.
A. H. Pratomo, W. Kaswidjanti, and S. Mu’arifah, “IMPLEMENTASI ALGORITMA REGION OF INTEREST (ROI) UNTUK
MENINGKATKAN PERFORMA ALGORITMA DETEKSI DAN KLASIFIKASI KENDARAAN IMPLEMENTATION OF REGION OF INTEREST (ROI) ALGORITHM TO IMPROVE CAR DETECTION AND CLASSIFICATION ALGORITHM,” vol. 7, no.1, pp. 155–162, 2020, doi:10.25126/jtiik.202071718.
L. C. Sousa et al., “Obstacle Avoidance Technique for Mobile Robots at Autonomous Human-Robot Collaborative Warehouse Environments,” Sensors, vol. 25, no. 8, Apr.2025, doi: 10.3390/s2508238