WTEFNet: Real-Time Low-Light Object Detection for Advanced Driver Assistance Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912403349831680 |
|---|---|
| author | Wu, Hao Chen, Junzhou Zhang, Ronghui Lyu, Nengchao Hu, Hongyu Guo, Yanyong Qiu, Tony Z. |
| author_facet | Wu, Hao Chen, Junzhou Zhang, Ronghui Lyu, Nengchao Hu, Hongyu Guo, Yanyong Qiu, Tony Z. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23201 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WTEFNet: Real-Time Low-Light Object Detection for Advanced Driver Assistance Systems Wu, Hao Chen, Junzhou Zhang, Ronghui Lyu, Nengchao Hu, Hongyu Guo, Yanyong Qiu, Tony Z. Computer Vision and Pattern Recognition 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. |
| title | WTEFNet: Real-Time Low-Light Object Detection for Advanced Driver Assistance Systems |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.23201 |