Adversarial Appearance Learning in Augmented Cityscapes for Pedestrian Recognition in Autonomous Driving
This addresses the problem of pedestrian recognition for autonomous vehicles, but it is incremental as it builds on existing augmentation methods with a focus on lighting realism.
The paper tackles the domain gap between synthetic and real data in autonomous driving by developing a pipeline to augment the Cityscapes dataset with virtual pedestrians, using a novel generative network for adversarial learning of lighting conditions to improve realism, and evaluates it on semantic and instance segmentation tasks.
In the autonomous driving area synthetic data is crucial for cover specific traffic scenarios which autonomous vehicle must handle. This data commonly introduces domain gap between synthetic and real domains. In this paper we deploy data augmentation to generate custom traffic scenarios with VRUs in order to improve pedestrian recognition. We provide a pipeline for augmentation of the Cityscapes dataset with virtual pedestrians. In order to improve augmentation realism of the pipeline we reveal a novel generative network architecture for adversarial learning of the data-set lighting conditions. We also evaluate our approach on the tasks of semantic and instance segmentation.