@article{ART003197441},
author={Jong-Hyun Kim},
title={RGB Image Based U-Net Learning Representation for Efficient Flame Segmentation},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2025},
volume={30},
number={4},
pages={33-40},
doi={10.9708/jksci.2025.30.04.033}
TY - JOUR
AU - Jong-Hyun Kim
TI - RGB Image Based U-Net Learning Representation for Efficient Flame Segmentation
JO - Journal of The Korea Society of Computer and Information
PY - 2025
VL - 30
IS - 4
PB - The Korean Society Of Computer And Information
SP - 33
EP - 40
SN - 1598-849X
AB - This paper proposes a method for efficiently detecting flame regions by extracting color-based features from RGB images and applying segmentation training using a U-Net architecture. The goal of the proposed approach is to accurately identify flame regions commonly observed in fire scenes. To achieve this, the fire images are preprocessed through smoke removal and color correction, followed by a reflection removal step to eliminate surrounding reflections caused by light. The segmented flame regions are then used to train a U-Net model, enabling stable flame segmentation in other fire images as well. Since the proposed method relies solely on RGB color features, it is lightweight in computation, allowing for efficient and reliable detection of flame regions. This makes it highly applicable across various device environments and market settings.
KW - Flame segmentation;U-Net;Fire detection;Flame region;Reflection removal;Fog removal;Learning representation;RGB image
DO - 10.9708/jksci.2025.30.04.033
ER -
Jong-Hyun Kim. (2025). RGB Image Based U-Net Learning Representation for Efficient Flame Segmentation. Journal of The Korea Society of Computer and Information, 30(4), 33-40.
Jong-Hyun Kim. 2025, "RGB Image Based U-Net Learning Representation for Efficient Flame Segmentation", Journal of The Korea Society of Computer and Information, vol.30, no.4 pp.33-40. Available from: doi:10.9708/jksci.2025.30.04.033
Jong-Hyun Kim "RGB Image Based U-Net Learning Representation for Efficient Flame Segmentation" Journal of The Korea Society of Computer and Information 30.4 pp.33-40 (2025) : 33.
Jong-Hyun Kim. RGB Image Based U-Net Learning Representation for Efficient Flame Segmentation. 2025; 30(4), 33-40. Available from: doi:10.9708/jksci.2025.30.04.033
Jong-Hyun Kim. "RGB Image Based U-Net Learning Representation for Efficient Flame Segmentation" Journal of The Korea Society of Computer and Information 30, no.4 (2025) : 33-40.doi: 10.9708/jksci.2025.30.04.033
Jong-Hyun Kim. RGB Image Based U-Net Learning Representation for Efficient Flame Segmentation. Journal of The Korea Society of Computer and Information, 30(4), 33-40. doi: 10.9708/jksci.2025.30.04.033
Jong-Hyun Kim. RGB Image Based U-Net Learning Representation for Efficient Flame Segmentation. Journal of The Korea Society of Computer and Information. 2025; 30(4) 33-40. doi: 10.9708/jksci.2025.30.04.033
Jong-Hyun Kim. RGB Image Based U-Net Learning Representation for Efficient Flame Segmentation. 2025; 30(4), 33-40. Available from: doi:10.9708/jksci.2025.30.04.033
Jong-Hyun Kim. "RGB Image Based U-Net Learning Representation for Efficient Flame Segmentation" Journal of The Korea Society of Computer and Information 30, no.4 (2025) : 33-40.doi: 10.9708/jksci.2025.30.04.033
