SnowPole Detection: A Comprehensive Dataset for Detection and Localization Using LiDAR Imaging in Nordic Winter Conditions

The SnowPole Detection dataset is a comprehensive collection of labeled LiDAR images, specifically designed for snow pole detection in road environments. This dataset was collected using a high-resolution OS2-128 LiDAR sensor mounted on an autonomous vehicle research platform, covering diverse environments such as mountainous, open, and forested areas. The SnowPole Detection dataset supports applications in computer vision, with a particular focus on snow pole detection and localization. The OS2-128 LiDAR sensor initially captures point clouds, which are then converted into 360-degree images across four modalities—Near-IR, Signal, Reflectivity, and Range—using the Ouster SDK. To enhance usability, color images were generated by assigning the first three modalities (Near-IR, Signal, and Reflectivity) to the blue, green, and red channels, respectively, excluding the Range modality. Initial labeling was conducted using Roboflow, with further refinement in CVAT, resulting in high-quality annotations. The dataset comprises a total of 1,954 manually labeled images, divided into 1,367 training images, 390 validation images, and 197 test images, following a 70/20/10 split. Since the images across all modalities are pixel-aligned, the labels for the color images are also applicable to each modality individually. This structure allows researchers to directly use the dataset for snow pole detection tasks, whether focusing on color or individual LiDAR modalities.

SnowPole Detection 数据集系一套全面的标记化激光雷达图像集合，专为道路环境中的雪杆检测而设计。该数据集采用高分辨率 OS2-128 激光雷达传感器，该传感器安装在自主车辆研究平台上进行采集，覆盖了包括山地、开阔地以及森林等多样化的环境。SnowPole Detection 数据集支持计算机视觉领域中的应用，尤其专注于雪杆的检测与定位。OS2-128 激光雷达传感器首先捕捉点云数据，随后利用 Ouster SDK 将点云数据转换为包含四种模态——近红外、信号、反射率和距离——的 360 度图像。为提高易用性，通过将前三种模态（近红外、信号和反射率）分别赋值于蓝、绿、红通道，从而生成彩色图像，距离模态被排除在外。初始标记工作由 Roboflow 完成，随后在 CVAT 中进行进一步细化，以确保高质量标注的产生。该数据集包含总共 1,954 张手动标记的图像，分为 1,367 张训练图像、390 张验证图像和 197 张测试图像，按照 70/20/10 的比例划分。由于所有模态的图像均实现像素对齐，因此彩色图像的标签也适用于各个模态。这种结构使得研究人员能够直接将数据集用于雪杆检测任务，无论其关注的是彩色图像还是单个激光雷达模态。