用虚拟行人增强城市景观数据，提升自动驾驶行人识别能力。
Adversarial Appearance Learning in Augmented Cityscapes for Pedestrian Recognition in Autonomous Driving
- 构建虚拟行人增强管道，生成带真实光照条件的合成场景
- 通过对抗学习优化光照模拟，减少真实与合成数据差距
- 在语义和实例分割任务中验证效果，适合自动驾驶视觉研究
在自动驾驶领域，合成数据对覆盖车辆需应对的特定交通场景至关重要。然而，合成数据常引入与真实数据之间的域差异。本文通过数据增强生成包含弱势道路使用者（VRUs）的定制交通场景，以提升行人识别性能。我们提出了一种对城市景观数据集进行虚拟行人增强的流程。为提高增强结果的真实性，设计了一种新型生成网络架构，用于对抗性学习数据集的光照条件。同时在语义分割和实例分割任务上评估了该方法的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。