Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.20565 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912172178669568 |
|---|---|
| author | Seferian, Mark A. Yang, Jidong J. |
| author_facet | Seferian, Mark A. Yang, Jidong J. |
| contents | Autonomous vehicles face significant challenges in navigating adverse weather, particularly rain, due to the visual impairment of camera-based systems. In this study, we leveraged contemporary deep learning techniques to mitigate these challenges, aiming to develop a vision model that processes live vehicle camera feeds to eliminate rain-induced visual hindrances, yielding visuals closely resembling clear, rain-free scenes. Using the Car Learning to Act (CARLA) simulation environment, we generated a comprehensive dataset of clear and rainy images for model training and testing. In our model, we employed a classic encoder-decoder architecture with skip connections and concatenation operations. It was trained using novel batching schemes designed to effectively distinguish high-frequency rain patterns from low-frequency scene features across successive image frames. To evaluate the model performance, we integrated it with a steering module that processes front-view images as input. The results demonstrated notable improvements in steering accuracy, underscoring the model's potential to enhance navigation safety and reliability in rainy weather conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_20565 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing autonomous vehicle safety in rain: a data-centric approach for clear vision Seferian, Mark A. Yang, Jidong J. Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing Autonomous vehicles face significant challenges in navigating adverse weather, particularly rain, due to the visual impairment of camera-based systems. In this study, we leveraged contemporary deep learning techniques to mitigate these challenges, aiming to develop a vision model that processes live vehicle camera feeds to eliminate rain-induced visual hindrances, yielding visuals closely resembling clear, rain-free scenes. Using the Car Learning to Act (CARLA) simulation environment, we generated a comprehensive dataset of clear and rainy images for model training and testing. In our model, we employed a classic encoder-decoder architecture with skip connections and concatenation operations. It was trained using novel batching schemes designed to effectively distinguish high-frequency rain patterns from low-frequency scene features across successive image frames. To evaluate the model performance, we integrated it with a steering module that processes front-view images as input. The results demonstrated notable improvements in steering accuracy, underscoring the model's potential to enhance navigation safety and reliability in rainy weather conditions. |
| title | Enhancing autonomous vehicle safety in rain: a data-centric approach for clear vision |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing |
| url | https://arxiv.org/abs/2412.20565 |