Traffic counting and multi-object tracking Metadata in non-motorised private transport

The data set contains counts of the classes person, bicycle, car from video data in predominantly non-motorized road traffic. The dataset contains video data, which are used to visualize the dataset, as well as the extracted metadata of object tracking and traffic counting. The following file is included in detail: video_example.mp4 Video sequence from an inner-city area to visualize the metadata. The underlying video is pixelated and represents the following information: - Region-of-Interest (ROI): Area where road users are counted (red polygon) - Bounding boxes of individual road users in the classes person, bicycle, car - Motion Tracks of the traffic participants MOT.csv File contains the results of object tracking of the video. The entries are described below: - frame: Image of the video (1 to 7001) - label_id: IDs of object classes: - 0: person - 1: bicycle - 2: car - label: Object classes - conf: Confidence of object class identification - object_id: Describes the tracking id that marks related objects - x: Bounding box coordinate: x position of the lower left corner in px - y: Bounding box coordinate: y-position of the lower left corner in px - width: Width of the bounding box in px - height: Height of the bounding box in px roi.csv Contains the coordinates (pixel position) of the polygon points that mark the region-of-interest (ROI). This is a polygon with four vertices defined by the following pixel positions: - Series: [560 540 600 1000] - Column: [50 700 1200 1300] count.csv Includes checked/corrected counting data. Counting method: - Viewing the lower left corner of the object bounding box. - Entry and exit in ROI. - counting when exiting ROI. Includes the following data: - frame: Image of the video (1 to 7001) - count_roi: Number of road users currently in ROI - count_total: Number of road users who left the ROI at that time (result of the census)本数据集包含源自以非机动道路交通为主的视频数据中，行人（person）、自行车（bicycle）、汽车（car）三类目标的计数统计结果。数据集除提供用于可视化展示的原始视频数据外，还包含提取得到的目标跟踪与交通计数元数据。 详细包含以下文件： video_example.mp4 用于可视化元数据的城区内视频序列。原始视频已做像素化处理，承载以下信息： - 感兴趣区域（Region-of-Interest, ROI）：用于统计道路使用者的红色多边形区域 - 行人、自行车、汽车类别的单个道路使用者边界框 - 交通参与者的运动跟踪轨迹 MOT.csv 该文件存储该视频的目标跟踪结果，各字段说明如下： - frame：视频帧序号，取值范围为1至7001 - label_id：目标类别ID： 0：行人 1：自行车 2：汽车 - label：目标类别名称 - conf：目标类别识别置信度 - object_id：用于标记关联目标的跟踪ID - x：边界框左下角的x轴像素坐标 - y：边界框左下角的y轴像素坐标 - width：边界框宽度，单位为像素 - height：边界框高度，单位为像素 roi.csv 该文件存储标记感兴趣区域（ROI）的多边形顶点像素坐标。该多边形由四个顶点定义，其像素坐标如下： - 行（Series）：[560, 540, 600, 1000] - 列（Column）：[50, 700, 1200, 1300] count.csv 包含经核查与校正后的计数数据。计数规则如下： - 以目标边界框的左下角点作为统计基准 - 依据目标在ROI内的进出状态判定计数时机 - 当目标离开ROI时完成计数操作 该文件包含以下数据字段： - frame：视频帧序号，取值范围为1至7001 - count_roi：当前处于ROI内的道路使用者数量 - count_total：当前时刻已离开ROI的道路使用者总数量（即本次普查的最终结果）