CLAHE-Enhanced YOLOv8: Deteksi Pelanggaran Helm Real-Time pada Citra CCTV Low-Light: Penelitian

Devin Nurman Wijaya; Dedy Ariyanto; Prasetyo Bintang S.N; Levina Cecilia P; Imam Budiawan; Desmulyati Desmulyati

doi:10.31004/jerkin.v4i3.4964

Authors

Devin Nurman Wijaya Universitas Bina Sarana Informatika
Dedy Ariyanto Universitas Bina Sarana Informatika
Prasetyo Bintang S.N Universitas Bina Sarana Informatika
Levina Cecilia P Universitas Bina Sarana Informatika
Imam Budiawan Universitas Bina Sarana Informatika
Desmulyati Desmulyati Universitas Bina Sarana Informatika

DOI:

https://doi.org/10.31004/jerkin.v4i3.4964

Keywords:

YOLOv8, CLAHE, Helmet Detection, Low-Light, Computer Vision

Abstract

Low lighting conditions in CCTV images cause a decrease in the accuracy of the Electronic Traffic Law Enforcement (E-TLE) system, especially in detecting helmet use among motorcyclists. Dark images with low contrast and high noise hinder the feature extraction process, so that deep learning-based detection models often produce False Negatives. This study proposes the integration of the Contrast Limited Adaptive Histogram Equalization (CLAHE) preprocessing method with the YOLOv8 architecture to improve the performance of helmet violation detection in low-light environments. The Helmet Detection dataset is used with the addition of synthetic low-light augmentation to simulate variations in nighttime lighting intensity. Tests show that the use of CLAHE can significantly improve the quality of visual features, as evidenced by the increase in Mean Average Precision (mAP@0.5) from 72.4% in raw images to 89.1% after preprocessing. In addition, the system is still able to operate in real-time with an average speed of 35–37 FPS on a Tesla T4 GPU. These results indicate that the integration of CLAHE and YOLOv8 is effective in improving the reliability of helmet violation detection in low-light conditions and is feasible to be implemented in computer vision-based traffic surveillance systems.

References

World Health Organization, Global Status Report on Road Safety 2018. Geneva: World Health Organization, 2018.

E. Poerwandono dan G. Q. Barronzoeputra, "Implementasi Algoritma You Only Look Once (YOLOv8) untuk Mendeteksi Pelanggaran Lalu Lintas Berupa Tidak Menggunakan Helm," JIMIK: Jurnal Indonesia Manajemen Informatika dan Komunikasi, vol. 5, no. 3, hal. 3237-3247, 2024.

B. Santoso dan S. A. Nugroho, "Peningkatan Akurasi Deteksi Objek pada Citra Low-Light Menggunakan Algoritma CLAHE dan CNN," Techno.Com, vol. 19, no. 4, hal. 388-398, 2020.

S. Wardani dan A. Purnomo, "Analisis Perbaikan Kualitas Citra CCTV Malam Hari Menggunakan Metode Contrast Limited Adaptive Histogram Equalization (CLAHE)," Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), vol. 8, no. 2, hal. 245-252, 2021.

A. S. Wibowo dan T. Hidayat, "Studi Efek Ekualisasi Histogram dan CLAHE dalam Mendeteksi Fitur Wajah Manusia," Jurnal Teknik Elektro, vol. 15, no. 2, hal. 88-94, 2024.

M. W. Anggana, A. Faizon, A. Munip, dan A. A. Ahyana, "Deteksi Penggunaan Helm pada Pengendara Sepeda Motor Menggunakan Model YOLOv8 dan Streamlit," Jurnal Komputer dan Teknologi Informasi (JKTI), vol. 3, no. 2, hal. 80-83, 2024.

R. Kurnia dan A. Pratiwi, "Deteksi Pengendara Motor Tanpa Helm Menggunakan YOLOv8 dengan Notifikasi Real-Time," Kohesi: Jurnal Sains dan Teknologi, vol. 9, no. 4, hal. 61-70, 2025.

A. R. Pratama, "Komparasi Metrik Evaluasi Kinerja Machine Learning: Accuracy, Precision, Recall, dan F1-Score pada Klasifikasi Teks," Jurnal Sistem Informasi Bisnis, vol. 11, no. 2, hal. 145-152, 2021.

E. S. Wahyuni, "Analisis Performa Metode K-Nearest Neighbor Menggunakan Confusion Matrix," Jurnal Teknik Komputer AMIK BSI, vol. 6, no. 1, hal. 121-126, 2020.

T. H. Pinem dan Z. P. Putra, "Evaluasi Kinerja Algoritma Klasifikasi Deep Learning dalam Prediksi Diabetes," Jurnal Ilmiah FIFO, vol. 17, no. 1, hal. 17-28, 2025.