This is the PyTorch re-implementation of our ITSC2023 paper: The Effect of Camera Data Degradation Factors on Panoptic Segmentation for Automated Driving, link.
- In this paper, we consider 5 categories of camera data degradation models, namely light level, adverse weather, internal sensor noises, motion blur and compression artefacts.
- Based on 11 models and multiple degradation levels, we synthesize an augmented version of Cityscape, named the Degraded-Cityscapes (D-Cityscapes). Moreover, for the environmental light level, we propose a new synthetic method with generative adversarial learning and zero-reference deep curve estimation to simulate 3 degraded light levels including low light, night light with glare, and extreme light.
- To compare the effect of the implemented camera degradation factors, we run extensive tests using a panoptic segmentation network (i.e. EfficientPS), quantifying how the performance metrics vary when the data are degraded.
Here, we show examples of using the EfficeintPS for the Cityscape dataset.
If you find this code helpful in your research or wish to refer to the baseline results, please use the following BibTeX entry.
@article{wang2023effect,
title={The effect of camera data degradation factors on panoptic segmentation for automated driving},
author={Wang, Yiting and Zhao, Haonan and Debattista, Kurt and Donzella, Valentina},
year={2023},
publisher={IEEE}
}
If you use the EfficientPS for segmentation, please consider citing
@article{mohan2021efficientps,
title={Efficientps: Efficient panoptic segmentation},
author={Mohan, Rohit and Valada, Abhinav},
journal={International Journal of Computer Vision},
volume={129},
number={5},
pages={1551--1579},
year={2021},
publisher={Springer}
}