发表机构
Indian Institute of Science（印度科学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对自动驾驶车辆在恶劣天气下的感知问题，提出参考数据集对齐方法和统一天气编辑方法进行多传感器对齐，经实验验证方法有效，能提升3D目标检测模型在不同天气下的鲁棒性。
AI 中文摘要
自动驾驶车辆的感知任务需要在恶劣天气条件下良好运行。由于缺乏真实世界天气数据集，天气模拟是一种有前景 的替代方案。为确保模拟紧密反映真实世界天气数据，不同传感器间呈现相同天气特征至关重要。为此，我们提出用于雾中天气强度对齐的参考数据集对齐方法（ReDAM）以及用于雨和雪中粒子定位对齐的统一天气编辑方法（受Weather-edit启发）。我们分别使用统计和几何测试验证这两种对齐方法。发现未对齐版本的3D检测模型与对齐版本相比往往过于乐观。还通过在对齐的多传感器模拟上微调现有传感器融合模型，展示了其对3D目标检测任务实现鲁棒性的有效性。
英文摘要
Perception tasks for autonomous vehicles need to work satisfactorily in adverse weather conditions. Due to lack of real-world weather datasets, weather simulations are a promising alternative. To ensure simulations closely mirror real-world weather data, it's crucial that they represent the same weather characteristics, including severity and particle positioning, across different sensors. To achieve this, we propose the Reference Dataset Alignment Method (ReDAM) for weather intensity alignment in fog and Unified-weather-edit (inspired by Weather-edit[1]) for particle positioning alignment in rain and snow. We validate both alignment methods using statistical and geometrical tests, respectively. We find that 3D detection models for non-aligned versions tend to be overly optimistic as compared to aligned versions. We also show the aligned-multi-sensor simulation's effectiveness for achieving robustness for 3D object detection task by finetuning existing sensor fusion models on it.
