ViSnow: Snow-covered Urban Roads Dataset for Computer Vision Applications

We present ViSnow: a large image dataset for snow-covered roads in an urban setting. The dataset includes an extensive collection of images from traffic surveillance cameras installed in Montreal, Quebec, Canada, during the winters of 2022 and 2023. ViSnow dataset aims to enable computer vision applications in intelligent transportation and winter road maintenance. ViSnow comprises 294,000 images describing various settings spanning day and night periods, different weather conditions (snow, rain, clear), and multiple urban areas (residential, commercial, industrial). We attach a metadata JSON file recording the timestamp and weather data to each image to provide more contextual information. ViSnow images are annotated to describe four snow cover classes: “clear surface”, “light-covered surface”, “medium-to-heavy-covered surface”, and “plowed surface”, matching possible snow removal operations.本研究提出ViSnow：一款面向城市积雪道路的大规模图像数据集。该数据集采集自加拿大魁北克省蒙特利尔市2022年与2023年冬季部署的交通监控摄像头，包含海量图像样本。ViSnow数据集旨在为智能交通与冬季道路养护领域的计算机视觉应用提供支撑。ViSnow总计包含29.4万张图像，涵盖昼夜不同时段、雪、雨、晴朗等多种天气条件，以及住宅、商业、工业等各类城市区域场景。我们为每张图像配套了元数据JSON文件，记录了拍摄时间戳与天气数据，以提供更丰富的上下文信息。ViSnow数据集的图像已针对积雪覆盖类别完成标注，涵盖四类："clear surface"（无积雪路面）、"light-covered surface"（轻度积雪路面）、"medium-to-heavy-covered surface"（中重度积雪路面）以及"plowed surface"（已清扫路面），对应实际可能的除雪作业场景。

搜集汇总

背景与挑战

背景概述

ViSnow是一个包含294,000张雪覆盖城市道路图像的大型数据集，旨在支持智能交通和道路维护的计算机视觉研究。数据集涵盖了多种天气条件和城市区域，每张图像都附有详细的元数据和雪覆盖类别标注。