CURE-TSR: Challenging Unreal and Real Environments for Traffic Sign Recognition

As one of the research directions at OLIVES Lab @ Georgia Tech, we focus on the robustness of data-driven algorithms under diverse challenging conditions where trained models can possibly be depolyed. To achieve this goal, we introduced a large-sacle (>2M images) traffic sign recognition dataset (CURE-TSR) which is among the most comprehensive datasets with controlled synthetic challenging conditions. Traffic sign images in the CURE-TSR dataset were cropped from the CURE-TSD dataset, which includes around 1.7 million real-world and simulator images with more than 2 million traffic sign instances. Real-world images were obtained from the BelgiumTS video sequences and simulated images were generated with the Unreal Engine 4 game development tool. Sign types include speed limit, goods vehicles, no overtaking, no stopping, no parking, stop, bicycle, hump, no left, no right, priority to, no entry, yield, and parking. Unreal and real sequences were processed with state-of-the-art visual effect software Adobe(c) After Effects to simulate challenging conditions, which include rain, snow, haze, shadow, darkness, brightness, blurriness, dirtiness, colorlessness, sensor and codec errors. Please refer to our GitHub page for code, papers, and more information.

作为佐治亚理工学院OLIVES实验室的研究方向之一，我们聚焦于数据驱动算法在各类模型实际部署场景下的鲁棒性研究——此类场景中训练完成的模型可能遭遇各类复杂挑战。为达成该研究目标，我们构建了大规模（超200万张图像）的交通标志识别数据集CURE-TSR，该数据集是当前具备最全面可控合成复杂场景的数据集之一。CURE-TSR数据集内的交通标志图像均裁剪自CURE-TSD数据集，后者包含约170万张真实世界与模拟器采集图像，涵盖超200万交通标志实例。其中真实图像取自BelgiumTS视频序列，模拟图像则通过虚幻引擎4（Unreal Engine 4）游戏开发工具生成。该数据集涵盖的标志类型包括限速、货运车辆、禁止超车、禁止停留、禁止停车、停车让行、自行车道、减速带、禁止左转、禁止右转、优先通行、禁止驶入、让行以及停车场标识。我们采用当前领先的视觉特效软件Adobe After Effects对模拟序列与真实序列进行处理，以模拟降雨、降雪、雾霾、阴影、明暗异常、模糊、污渍、色彩失真、传感器故障及编解码器错误等各类复杂干扰场景。如需获取代码、论文及更多相关信息，请参阅我们的GitHub页面。