Augmentation-Based Approaches for Overcoming Low Visibility in Street Object Detection
See where this sits in the topic map →Summary AI-generated
- TL;DR
- Standard machine learning models struggle with road object detection in low-visibility conditions like nighttime, fog, and rain due to limited training data.
- Problem
- Collecting comprehensive datasets that cover every possible deployment scenario is often impractical in terms of time and cost.
- Method
- The researchers used depth- and Fourier domain-based data augmentations to simulate low-visibility conditions during training.
- Results
- In rainy weather, the best-performing model trained on augmented data achieved a 3.4% improvement over a model trained on non-augmented data.
- Contributions
- This work proposes specific augmentations tailored to address low-visibility challenges by training models on subsets that complement missing conditions.
- Limitations
- In other cases, the proposed augmentations did not significantly increase the performance of the classifier.
- Takeaways
- Appropriately applied augmentations can improve model performance in certain low-visibility conditions, though their effectiveness varies.
- Applications
- Road object detection systems for autonomous vehicles or driver assistance.
- Topics
- Object Detection; Data Augmentation; Low-Visibility Conditions
- For industry
- Automotive; Transportation
- Why it matters
- Helps address the data scarcity bottleneck for robust road object detection in adverse weather and lighting.
Abstract
Road object detection in low-visibility conditions, such as nighttime, fog, and rain, is difficult for standard machine learning models, which often struggle because of limited training data. The collection of comprehensive datasets that encompass all possible scenarios encountered during deployment is often impractical in terms of time and cost. To overcome this limitation, this work proposes the use of specific augmentations tailored to address the challenges associated with low-visibility conditions. The model employed in this research was trained on sub-sets that complemented the missing low-visibility circumstances. Augmentations based on depth and Fourier domain techniques were applied to simulate such conditions during training and enhance the model's performance when faced with such a scenario. Experimental results demonstrated that appropriately applied augmentations can improve the model's performance. Specifically, in rainy weather, the best-performing model trained on augmented data achieved a 3.4% improvement over a model trained on non-augmented data. In other cases, however, the proposed augmentations did not increase significantly the per-formance of the classifier.