Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Teknik Informatika (JUTIF)
Esti Suryani
Informatics, Information Technology and Science Data, Universitas Sebelas Maret, Indonesia
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Parameter-Optimized Progressive Probabilistic Hough Transform Combined with Auto-CLAHE and Dual Gamma Correction for Night-Time Lane Detection in Autonomous Driving Nina Nur Aidha; Esti Suryani; Umi Salamah
Jurnal Teknik Informatika (Jutif) Vol. 7 No. 4 (2026): JUTIF Volume 7, Number 4, August 2026
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2026.7.4.5628

Abstract

Traffic accidents are often caused by driver negligence or poor environmental conditions. Lane detection is a crucial component in autonomous vehicle technology and Advanced Driver Assistance Systems (ADAS) to improve driving safety by keeping the vehicle in its lane. However, lane detection at night often faces challenges due to low lighting and noise in the images. An accurate lane detection system is needed to address these issues so that safety features can function optimally. This research builds a night-time lane detection system by combining Automatic CLAHE with Dual Gamma Correction (ACLAHEwDGC) to improve image quality in low-light conditions and Progressive Probabilistic Hough Transform (PPHT) for lane line detection. The methodology includes preprocessing, segmentation, feature extraction, and a point-based distance evaluation. The system was evaluated using 284 frames from the Digital Image Media Lab Lane Detection Benchmark dataset and compared with previous methods using CLAHE and Standard Hough Transform (SHT). Through parameter optimization using Bayesian Optimization, the lane detection system achieved average values of 0.98 for Line Precision, 0.90 for Lane Recall, and 0.35 pixels for Distance Score, with an Overall Score of 0.96. These results show that optimizing traditional computer vision methods minimizes detection errors and provides a highly accurate results alternative to deep learning models for autonomous vehicle technology.
Co-Authors Nina Nur Aidha Umi Salamah