@article{ART003349265},
author={Jun-Seo Jang and Hakgyun Roh and Kwansoo Jung},
title={A study on Data Preprocessing and Augmentation for Robust Object Detection in Traffic CCTV under Environmental Variations},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2026},
volume={31},
number={6},
pages={17-27}
TY - JOUR
AU - Jun-Seo Jang
AU - Hakgyun Roh
AU - Kwansoo Jung
TI - A study on Data Preprocessing and Augmentation for Robust Object Detection in Traffic CCTV under Environmental Variations
JO - Journal of The Korea Society of Computer and Information
PY - 2026
VL - 31
IS - 6
PB - The Korean Society Of Computer And Information
SP - 17
EP - 27
SN - 1598-849X
AB - In this paper, we proposes data preprocessing and augmentation techniques to enhance object detection performance in traffic CCTV systems under various weather and illumination conditions. To overcome the limitations of existing models, which exhibit degraded recognition rates in low-light and adverse weather conditions, we introduce an optimization method for YOLOv8-based models by integrating class balancing, CLAHE(Contrast Limited Adaptive Histogram Equalization), Gaussian blur, and specialized environmental simulations. The proposed method resolves class imbalance through quality score-based downsampling and ensures dataset diversity by simulating various scenarios such as rain, fog, and nighttime conditions. Experimental results demonstrate that the proposed model achieved an F1-score of 0.8792 and an mAP@0.5 of 0.5549, representing a performance improvement of approximately 30.6% and 87.9%, respectively, compared to the baseline model. These results indicate a significant enhancement in the system stability and generalization capabilities required for real-time traffic monitoring environments. Consequently, this research is expected to provide positive contributions to the advancement of smart city infrastructures and traffic safety systems.
KW - Traffic CCTV;Object Detection;Class Rebalancing;Data Preprocessing;Data Augmentation
DO -
UR -
ER -
Jun-Seo Jang, Hakgyun Roh and Kwansoo Jung. (2026). A study on Data Preprocessing and Augmentation for Robust Object Detection in Traffic CCTV under Environmental Variations. Journal of The Korea Society of Computer and Information, 31(6), 17-27.
Jun-Seo Jang, Hakgyun Roh and Kwansoo Jung. 2026, "A study on Data Preprocessing and Augmentation for Robust Object Detection in Traffic CCTV under Environmental Variations", Journal of The Korea Society of Computer and Information, vol.31, no.6 pp.17-27.
Jun-Seo Jang, Hakgyun Roh, Kwansoo Jung "A study on Data Preprocessing and Augmentation for Robust Object Detection in Traffic CCTV under Environmental Variations" Journal of The Korea Society of Computer and Information 31.6 pp.17-27 (2026) : 17.
Jun-Seo Jang, Hakgyun Roh, Kwansoo Jung. A study on Data Preprocessing and Augmentation for Robust Object Detection in Traffic CCTV under Environmental Variations. 2026; 31(6), 17-27.
Jun-Seo Jang, Hakgyun Roh and Kwansoo Jung. "A study on Data Preprocessing and Augmentation for Robust Object Detection in Traffic CCTV under Environmental Variations" Journal of The Korea Society of Computer and Information 31, no.6 (2026) : 17-27.
Jun-Seo Jang; Hakgyun Roh; Kwansoo Jung. A study on Data Preprocessing and Augmentation for Robust Object Detection in Traffic CCTV under Environmental Variations. Journal of The Korea Society of Computer and Information, 31(6), 17-27.
Jun-Seo Jang; Hakgyun Roh; Kwansoo Jung. A study on Data Preprocessing and Augmentation for Robust Object Detection in Traffic CCTV under Environmental Variations. Journal of The Korea Society of Computer and Information. 2026; 31(6) 17-27.
Jun-Seo Jang, Hakgyun Roh, Kwansoo Jung. A study on Data Preprocessing and Augmentation for Robust Object Detection in Traffic CCTV under Environmental Variations. 2026; 31(6), 17-27.
Jun-Seo Jang, Hakgyun Roh and Kwansoo Jung. "A study on Data Preprocessing and Augmentation for Robust Object Detection in Traffic CCTV under Environmental Variations" Journal of The Korea Society of Computer and Information 31, no.6 (2026) : 17-27.
2