WTEFNet: Real-Time Low-Light Object Detection for Advanced Driver Assistance Systems

Object detection is a cornerstone of environmental perception in advanced driver assistance systems(ADAS). However, most existing methods rely on RGB cameras, which suffer significant performance degradation in low-light conditions due to poor image quality. To address this challenge, we propose WTEFNet, a real-time object detection framework specifically designed for low-light scenarios, with strong adaptability to mainstream detectors. WTEFNet comprises three core modules: a Low-Light Enhancement (LLE) module, a Wavelet-based Feature Extraction (WFE) module, and an Adaptive Feature Fusion Detection (AFFD) module. The LLE enhances dark regions while suppressing overexposed areas; the WFE applies multi-level discrete wavelet transforms to isolate high- and low-frequency components, enabling effective denoising and structural feature retention; the AFFD fuses semantic and illumination features for robust detection. To support training and evaluation, we introduce GSN, a manually annotated dataset covering both clear and rainy night-time scenes. Extensive experiments demonstrate that WTEFNet achieves state-of-the-art performance under low-light conditions, outperforming previous best methods in terms of mAP@50 by 2.9%, 2.5%, and 2.1% on BDD100K, SHIFT, and nuScenes, respectively. On the GSN dataset, it further exceeds previous methods by 2.4% and 3.0% under clear and rainy night scenarios. In addition, deployment on an embedded platform (NVIDIA Jetson AGX Orin) validates the instrument realization and real-time feasibility of the proposed framework for ADAS applications. The code and dataset are available at https://github.com/wh954/WTEFNet.