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

TL;DR

WTEFNet is a real-time low-light object detection framework for ADAS that combines enhancement, wavelet-based feature extraction, and adaptive fusion, demonstrating state-of-the-art accuracy and real-time performance on embedded platforms.

Contribution

The paper introduces WTEFNet, a novel low-light object detection framework with integrated modules for enhancement, feature extraction, and adaptive fusion, tailored for real-time ADAS applications.

Findings

Achieves state-of-the-art accuracy under low-light conditions.

Operates in real-time on embedded platforms like NVIDIA Jetson AGX Orin.

Introduces GSN dataset for low-light nighttime scenes.

Abstract

Object detection is a cornerstone of environmental perception in advanced driver assistance systems(ADAS). However, most existing methods rely on RGB cameras, which suffer from significant performance degradation under low-light conditions due to poor image quality. To address this challenge, we proposes 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 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 on BDD100K, SHIFT, nuScenes, and GSN demonstrate that WTEFNet achieves state-of-the-art accuracy under low-light conditions. Furthermore, deployment on a embedded platform (NVIDIA Jetson AGX Orin) confirms the framework's suitability for real-time ADAS applications.