Devi Fitrianah
Fakultas Ilmu Komputer, Universitas Mercu Buana

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Bulletin of Electrical Engineering and Informatics

Enhancing low-light pedestrian detection: convolutional neural network and YOLOv8 integration with automated dataset Rendi, Rendi; Fitrianah, Devi
Bulletin of Electrical Engineering and Informatics Vol 14, No 3: June 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v14i3.8903

Abstract

This research aims to enhance the you only look once (YOLO) model for pedestrian detection in environments with varying lighting conditions, particularly in low-light scenarios. The primary contribution of this work is the integration of a convolutional neural network (CNN)-based low-light enhancement model, which transforms dark images into brighter, more discernible ones. This enhanced dataset is subsequently used to train the YOLO model, allowing it to learn from both the original and transformed data distributions. Unlike traditional YOLO training approaches, this method generates more accurate data representations in challenging lighting environments, leading to improved detection outcomes. The novelty of this approach lies in its dual-stage training process, which integrates a CNNbased low-light enhancement model with YOLO’s detection capabilities. This combination not only enhances pedestrian detection but also has the potential for application in other domains, such as vehicle detection and surveillance, particularly in challenging lighting conditions. The automatic dataset collection pipeline provides an efficient way to gather diverse training data across various scenarios. The YOLOv8 model trained on the low-light enhanced dataset significantly outperformed the baseline model trained only on the original dataset, with precision increased by 9.8%, recall by 45.7%, mAP50 by 26.8%, and mAP50-95 by 41.0% when validated on dark images.
Automatic drowsiness detection system to reduce road accident risks Aprilia, Sella Joanita Nur; Fitrianah, Devi
Bulletin of Electrical Engineering and Informatics Vol 14, No 4: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v14i4.8902

Abstract

Drowsy driving poses a significant risk to road safety, often equated with impaired driving due to its detrimental effects on cognitive function. This study presents a real-time drowsiness detection system utilizing the YOLOv5 algorithm, enhanced with contrast limited adaptive histogram equalization (CLAHE) technique, to improve detection in low-light conditions. The proposed method analyzes visual cues indicative of drowsiness, such as eye closure and head nodding, leveraging advanced computer vision techniques. A dataset was augmented from 1,056 original images to 2,112 images via CLAHE, resulting in significant improvements in model performance. Experimental results indicate that the model achieves a mean average precision (mAP) of 0.959, with precision and recall values of 0.9529 and 0.9528, respectively, underscoring the effectiveness of CLAHE in enhancing image quality and overall detection performance. The application developed from this model provides timely alerts to drivers, aiming to prevent accidents and promote road safety. This research contributes to the advancement of automated safety systems in vehicles, particularly under challenging lighting conditions.