TY  - JOUR
AU  - Tang, Xiu
AU  - Man, Yaxin
AU  - Wang, Xiaoyan
AU  - Ji, Rendong
AU  - Zhang, Xiaojun
AU  - Xu, Yunlong
PY  - 2026
DA  - 2026/09/01
TI  - Low-Light Fire and Smoke Detection in Electric Vehicles via a Lightweight Dual-Branch Architecture with Adaptive Reflectance Enhancement
JO  - ICCK Transactions on Intelligent Systematics
T2  - ICCK Transactions on Intelligent Systematics
JF  - ICCK Transactions on Intelligent Systematics
VL  - 3
IS  - 3
SP  - 145
EP  - 161
DO  - 10.62762/TIS.2026.406065
UR  - https://www.icck.org/article/abs/TIS.2026.406065
KW  - electric vehicle safety
KW  - electric vehicles
KW  - fire detection
KW  - low-light optimization
AB  - Fire and smoke detection in electric vehicle environments is essential for safety monitoring, yet existing methods often perform poorly under low-light conditions because of weak feature representation, flame overexposure, and limited nighttime data. In addition, many detection models cannot effectively balance accuracy and real-time efficiency, which restricts their deployment in practical applications. To address these issues, this study proposes a lightweight dual-branch detection framework for low-light fire and smoke recognition in electric vehicle environments. The proposed method integrates reflectance enhancement, adaptive feature weighting, and multi-scale feature learning within a unified architecture. Specifically, the auxiliary branch enhances weak fire-related features under low illumination through the Adaptive Reflectance Enhancement Module (AREM) and the Element-wise Adaptive Weight Convolution (EAConv), while the main branch employs a Self-Adaptive Feature Convolution (SAConv) module to strengthen multi-scale representation with limited computational overhead. Moreover, a self-constructed and publicly released dataset containing 3,512 images is introduced, including 1,910 daytime and 1,602 nighttime samples, to provide a more realistic benchmark for fire detection in electric vehicle environments under diverse lighting conditions. Experimental results show that the proposed method achieves 85.3% AP50 and 52.2% AP on the full dataset, and 52.9% AP50 and 26.5% AP on the nighttime subset. Compared with YOLOv11-n, the proposed model improves AP50 by 1.2% and AP by 1.7%, while demonstrating more stable performance in challenging low-light environments. These results indicate that the proposed framework provides a practical and reliable solution for real-time fire detection in electric vehicle environments.
SN  - 3068-5079
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Tang2026LowLight,
  author = {Xiu Tang and Yaxin Man and Xiaoyan Wang and Rendong Ji and Xiaojun Zhang and Yunlong Xu},
  title = {Low-Light Fire and Smoke Detection in Electric Vehicles via a Lightweight Dual-Branch Architecture with Adaptive Reflectance Enhancement},
  journal = {ICCK Transactions on Intelligent Systematics},
  year = {2026},
  volume = {3},
  number = {3},
  pages = {145-161},
  doi = {10.62762/TIS.2026.406065},
  url = {https://www.icck.org/article/abs/TIS.2026.406065},
  abstract = {Fire and smoke detection in electric vehicle environments is essential for safety monitoring, yet existing methods often perform poorly under low-light conditions because of weak feature representation, flame overexposure, and limited nighttime data. In addition, many detection models cannot effectively balance accuracy and real-time efficiency, which restricts their deployment in practical applications. To address these issues, this study proposes a lightweight dual-branch detection framework for low-light fire and smoke recognition in electric vehicle environments. The proposed method integrates reflectance enhancement, adaptive feature weighting, and multi-scale feature learning within a unified architecture. Specifically, the auxiliary branch enhances weak fire-related features under low illumination through the Adaptive Reflectance Enhancement Module (AREM) and the Element-wise Adaptive Weight Convolution (EAConv), while the main branch employs a Self-Adaptive Feature Convolution (SAConv) module to strengthen multi-scale representation with limited computational overhead. Moreover, a self-constructed and publicly released dataset containing 3,512 images is introduced, including 1,910 daytime and 1,602 nighttime samples, to provide a more realistic benchmark for fire detection in electric vehicle environments under diverse lighting conditions. Experimental results show that the proposed method achieves 85.3\% AP50 and 52.2\% AP on the full dataset, and 52.9\% AP50 and 26.5\% AP on the nighttime subset. Compared with YOLOv11-n, the proposed model improves AP50 by 1.2\% and AP by 1.7\%, while demonstrating more stable performance in challenging low-light environments. These results indicate that the proposed framework provides a practical and reliable solution for real-time fire detection in electric vehicle environments.},
  keywords = {electric vehicle safety, electric vehicles, fire detection, low-light optimization},
  issn = {3068-5079},
  publisher = {Institute of Central Computation and Knowledge}
}