Intersection Safety Challenge Stage 1B Training Data
收藏资源简介：
This dataset was collected as part of the U.S. Department of Transportation (U.S. DOT) Intersection Safety Challenge (hereafter, “the Challenge”) for Stage 1B: System Assessment and Virtual Testing. Multi-sensor data was collected at a controlled test roadway intersection within the Federal Highway Administration (FHWA) Turner-Fairbank Highway Research Center (TFHRC) Smart Intersection facility in McLean, VA from October 2023 through March 2024. The data includes potential conflict-based and non-conflict-based experimental scenarios between vulnerable road users (e.g., pedestrians, bicyclists) and vehicles during both daytime and nighttime conditions. Note that no actual human vulnerable road users were put at risk of being involved in a collision during the data collection efforts. The collected data (hereafter, “the Challenge Dataset”) was intended to be used for intersection safety system algorithm training, refinement, tuning, and/or validation, but may have additional uses. The Challenge Dataset is divided into training data (unlabeled, without associated ground truth) and validation data (labeled, with associated ground truth). This particular data asset provides the training data, and is complimentary to the validation data component of the Challenge Dataset found on the ITS DataHub at: <a href="https://data.transportation.gov/j58q-ymi4/">https://data.transportation.gov/j58q-ymi4</a>. For a summary of the Stage 1B data collection effort, please see this video: <a href="https://youtu.be/csirVHFa2Cc">https://youtu.be/csirVHFa2Cc</a>. All data within the Challenge Dataset (i.e., both the training data and the validation data) includes data collected at a single, signalized four-way intersection from 20 roadside sensors and traffic control devices, including eight closed-circuit television (CCTV) visual cameras, five thermal cameras, two light detection and ranging (LiDAR) sensors, and four radar sensors. Intrinsic calibration was performed for all visual and thermal cameras. Extrinsic calibration was performed for specific pairs of roadside sensors. Additionally, the traffic signal phase and timing data and vehicle and/or pedestrian calls to the traffic signal controller (if any) are also provided. The total number of unique runs in the Challenge Dataset training data is 1,104, bringing the total size of the dataset to approximately 1 TB. A sample of 20 unique runs from the training data is provided here for download, inspection, and use. If, after inspecting this training data sample, a potential data user would like access to download the full training data, a request can be made via the form linked here: <a href="https://its.dot.gov/data/data-request">https://its.dot.gov/data/data-request</a>. For more details about the data collection, supplemental files, organization and dictionary, and sensor calibration, see the attached “U.S. DOT ISC Stage 1B ITS DataHub Metadata_v2.0.pdf” document. For more information on the background of the Intersection Safety Challenge Stage 1B, please visit: <a href="https://www.its.dot.gov/research-areas/intersection-safety/challenge/">https://www.its.dot.gov/research-areas/intersection-safety/challenge/</a>.
本数据集采集自美国运输部（U.S. Department of Transportation, U.S. DOT）主办的交叉口安全挑战赛（以下简称"本次挑战赛"）1B阶段：系统评估与虚拟测试项目。多传感器数据采集于2023年10月至2024年3月间，采集地点位于弗吉尼亚州麦克林市联邦公路管理局（Federal Highway Administration, FHWA）特纳-费尔班克公路研究中心（Turner-Fairbank Highway Research Center, TFHRC）智能交叉口设施内的受控测试道路交叉口。该数据集涵盖白天与夜间工况下，脆弱道路使用者（vulnerable road users，如行人、骑行者）与车辆之间的潜在冲突型及非冲突型实验场景。需特别说明，数据采集过程中未让真实人类脆弱道路使用者面临碰撞风险。本次采集所得数据集（以下简称"挑战赛数据集"）主要用于交叉口安全系统算法的训练、优化、调参与/或验证，同时也可适用于其他应用场景。挑战赛数据集分为训练数据（无标注，无配套真值（ground truth））与验证数据（带标注，含配套真值（ground truth））两类。本数据资产即为挑战赛数据集的训练数据子集，与ITS DataHub平台上发布的挑战赛数据集验证数据组件互为补充，对应链接为：<a href="https://data.transportation.gov/j58q-ymi4/">https://data.transportation.gov/j58q-ymi4</a>。如需了解1B阶段数据采集工作的详细概要，请参阅该视频资料：<a href="https://youtu.be/csirVHFa2Cc">https://youtu.be/csirVHFa2Cc</a>。挑战赛数据集的全部数据（涵盖训练数据与验证数据）均采集自单个信号控制十字交叉口，由20台路边传感器与交通管控设备采集得到，包括8台闭路电视（CCTV）视觉摄像机、5台热成像摄像机、2台激光雷达（LiDAR）传感器及4台雷达传感器。所有视觉与热成像摄像机均已完成内参标定，部分路边传感器对已完成外参标定。此外，数据集还包含交通信号相位与计时数据，以及车辆/行人向交通信号控制器发出的请求（若存在）。挑战赛数据集训练数据中的独立运行场次总数为1,104，数据集总规模约为1 TB。本页面提供训练数据中20个独立运行场次的样本供下载、查看与使用。若查看该训练数据样本后，潜在数据使用者需要获取完整训练数据的下载权限，可通过本页面链接的表单提交申请：<a href="https://its.dot.gov/data/data-request">https://its.dot.gov/data/data-request</a>。如需了解更多关于数据采集、补充文件、数据组织与字典及传感器标定的细节，请参阅附件"U.S. DOT ISC Stage 1B ITS DataHub Metadata_v2.0.pdf"文档。如需了解交叉口安全挑战赛1B阶段的更多背景信息，请访问：<a href="https://www.its.dot.gov/research-areas/intersection-safety/challenge/">https://www.its.dot.gov/research-areas/intersection-safety/challenge/</a>。
