Enhancing Nighttime Vehicle Detection with Day-to-Night Style Transfer and Labeling-Free Augmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917876079788032 |
|---|---|
| author | Yang, Yunxiang Zhen, Hao Huang, Yongcan Yang, Jidong J. |
| author_facet | Yang, Yunxiang Zhen, Hao Huang, Yongcan Yang, Jidong J. |
| contents | Existing deep learning-based object detection models perform well under daytime conditions but face significant challenges at night, primarily because they are predominantly trained on daytime images. Additionally, training with nighttime images presents another challenge: even human annotators struggle to accurately label objects in low-light conditions. This issue is particularly pronounced in transportation applications, such as detecting vehicles and other objects of interest on rural roads at night, where street lighting is often absent, and headlights may introduce undesirable glare. This study addresses these challenges by introducing a novel framework for labeling-free data augmentation, leveraging CARLA-generated synthetic data for day-to-night image style transfer. Specifically, the framework incorporates the Efficient Attention Generative Adversarial Network for realistic day-to-night style transfer and uses CARLA-generated synthetic nighttime images to help the model learn vehicle headlight effects. To evaluate the efficacy of the proposed framework, we fine-tuned the YOLO11 model with an augmented dataset specifically curated for rural nighttime environments, achieving significant improvements in nighttime vehicle detection. This novel approach is simple yet effective, offering a scalable solution to enhance AI-based detection systems in low-visibility environments and extend the applicability of object detection models to broader real-world contexts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_16478 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Nighttime Vehicle Detection with Day-to-Night Style Transfer and Labeling-Free Augmentation Yang, Yunxiang Zhen, Hao Huang, Yongcan Yang, Jidong J. Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Existing deep learning-based object detection models perform well under daytime conditions but face significant challenges at night, primarily because they are predominantly trained on daytime images. Additionally, training with nighttime images presents another challenge: even human annotators struggle to accurately label objects in low-light conditions. This issue is particularly pronounced in transportation applications, such as detecting vehicles and other objects of interest on rural roads at night, where street lighting is often absent, and headlights may introduce undesirable glare. This study addresses these challenges by introducing a novel framework for labeling-free data augmentation, leveraging CARLA-generated synthetic data for day-to-night image style transfer. Specifically, the framework incorporates the Efficient Attention Generative Adversarial Network for realistic day-to-night style transfer and uses CARLA-generated synthetic nighttime images to help the model learn vehicle headlight effects. To evaluate the efficacy of the proposed framework, we fine-tuned the YOLO11 model with an augmented dataset specifically curated for rural nighttime environments, achieving significant improvements in nighttime vehicle detection. This novel approach is simple yet effective, offering a scalable solution to enhance AI-based detection systems in low-visibility environments and extend the applicability of object detection models to broader real-world contexts. |
| title | Enhancing Nighttime Vehicle Detection with Day-to-Night Style Transfer and Labeling-Free Augmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2412.16478 |