No abstract

For autonomous vehicles to viably replace human drivers they must contend with inclement weather. Falling rain and snow introduce noise in LiDAR returns resulting in both false positive and false negative object detections. In this article we introduce the Winter Adverse Driving dataSet (WADS) collected in the snow belt region of Michigan's Upper Peninsula. WADS is the first multi-modal dataset featuring dense point-wise labeled sequential LiDAR scans collected in severe winter weather; weather that would cause an experienced driver to alter their driving behavior. We have labelled and will make available over 7 GB or 3.6 billion labelled LiDAR points out of over 26 TB of total LiDAR and camera data collected. We also present the Dynamic Statistical Outlier Removal (DSOR) filter, a statistical PCL-based filter capable or removing snow with a higher recall than the state of the art snow de-noising filter while being 28% faster. Further, the DSOR filter is shown to have a lower time complexity compared to the state of the art resulting in an improved scalability.Our labeled dataset and DSOR filter will be made available at https://bitbucket.org/autonomymtu/dsor filter.

No abstract

The availability of public datasets with annotated light detection and ranging (LiDAR) point clouds has advanced autonomous driving tasks, such as semantic and panoptic segmentation. However, there is a lack of datasets focused on inclement weather. Snow and rain degrade visibility and introduce noise in LiDAR point clouds. In this article, summarize a 3-year winter weather data collection effort and introduce the winter adverse driving dataset. It is the first multimodal dataset featuring moderate to severe winter weather-weather that would cause an experienced driver to alter their driving behavior. Our dataset features exclusively events with heavy snowfall and occasional white-out conditions. Data are collected using high-resolution LiDAR, visible as well as near infrared (IR) cameras, a long wave IR camera, forward-facing radio detection and ranging, and Global Navigation Satellite Systems/Inertial Measurement Unit units. Our dataset is unique in the range of sensors and the severity of the conditions observed. It is also one of the only data sets to focus on rural and semi-rural environments. Over 36 TB of adverse winter data have been collected over 3 years. We also provide dense point-wise labels to sequential LiDAR scans collected in severe winter weather. We have labeled and will make available around 1000 sequential LiDAR scenes, amounting to over 7 GB or 3.6 billion labeled points. This is the first point-wise semantically labeled dataset to include falling snow.