README for "Perception-Based Adaptive Traffic Management and Data Sharing" dataset. Strengthening Mobility and Revolutionizing Transportation (SMART) Program, U.S. Department of Transportation (USDOT) FAIN #: 69A3552341025 SMARTFY22N1P1G13 ---------------------------------------------------------------- LINK TO DATASET ---------------------------------------------------------------- https://data.nrel.gov/submissions/287 Dataset DOI: https://doi.org/10.21949/rdvr-jf73. Implementation Report DOI: https://doi.org/10.21949/g3r6-5954 Data Management Plan (DMP) DOI: https://doi.org/10.48321/D16F3FD7E1 ---------------------------------------------------------------- SUMMARY OF DATASET ---------------------------------------------------------------- The data set provided here was collected as a part of the US Department of Transportation (USDOT) Strengthening Mobility and Revolutionizing Transportation (SMART) project, where the City of Colorado Springs (Colorado, USA) and National Renewable Energy Laboratory (NREL) collaborated to collect object-level trajectory data from road users using multiple types of infrastructure sensors deployed at different traffic intersections. The data was collected in 2024 across multiple days at various intersections in and around the City of Colorado Springs. The goal of the data collection exercises was to learn various attributes about infrastructure sensors and to build a repository of high-resolution object-level data that can be used for research and development (such as for developing multi-sensor data fusion algorithms). Data presented here was collected from sensors either installed either on the traffic poles or hoisted on top of NREL’s Infrastructure Perception and Control (IPC) mobile trailer. The state-of-the-art IPC trailer can deploy the latest generation of perception sensors at traffic intersections and capture real-time road user data. Sensors used for data collection include Econolite’s EVO RADAR units, Ouster’s OS1 LIDAR units and Axis Camera units. The raw data received from individual sensors is processed at the edge computer device located inside the IPC mobile Lab, and the resulting object-level data is then stored and processed offline. Each data folder contains all the data collected on the day. We have transformed (rotation then translation) raw detections to ensure the data from all sensors is represented in the same cartesian coordinate system. The object list attributes impacted from the transformation are PositionX, PositionY, SpeedX, SpeedY and HeadingDeg. The rest of the data attribute remains untouched. Users should note that we do not claim that this transformation is perfect and there may be some misalignment among the different sensors. ---------------------------------------------------------------- TABLE OF CONTENTS ---------------------------------------------------------------- A. General Information B. Sharing/Access & Policies Information C. Data and Related File Overview D. Methodological Information E. Data-Specific Information for: Multi-Sensor Object Detection Data from Infrastructure Sensors Deployed at Traffic Intersections in the City of Colorado Springs, Colorado, USA F. Update Log ---------------------------------------------------------------- A. GENERAL INFORMATION ---------------------------------------------------------------- 0. Title of Dataset: Multi-Sensor Object Detection Data from Infrastructure Sensors Deployed at Traffic Intersections in the City of Colorado Springs, Colorado, USA 1. Description of Dataset: The dataset provided here was collected as a part of the US Department of Transportation (USDOT) Strengthening Mobility and Revolutionizing Transportation (SMART) project, where the City of Colorado Springs (Colorado, USA) and National Renewable Energy Laboratory (NREL) collaborated to collect object-level trajectory data from road users using multiple types of sensors deployed at different traffic intersections. The data was collected in 2024 across multiple days at various intersections in Colorado Springs. Each data folder contains all the data collected on the day. The goal of the data collection exercises was to learn various attributes about the sensor product and to build a repository of data that can be used for research and development (such as for developing multi-sensor data fusion algorithms). Data presented here was collected from sensors either installed on the traffic poles or hoisted on top of NREL’s Infrastructure Perception and Control (IPC) mobile laboratory. The state-of-the-art IPC trailer can deploy the latest generation of perception sensors at traffic intersections and capture real-time road user data. Sensors used for data collection include Econolite’s EVO RADAR units, Ouster’s OS1 LIDAR units and Axis Camera units. The object track data is sent to an edge compute device located inside the IPC mobile Lab. General notes/caveats for using the data: • Data is spread across multiple folders (names after the day it was collected) where each folder contains object-level sensor detection data in CSV format. • Detections from EVO radar units are named EVO_RADAR_#.csv, the data from OS1 lidar units is named OS1_LIDAR_#.csv, and the data from camera units is names AXS_CAMERA_#.csv. • The object list attributes provided in the CSV files are explained in the attached data_description.docx file • The raw detections are transformed (rotation then translation) to ensure the data from all sensors is represented in the same cartesian coordinate system. The object list attributes impacted from the transformation are PositionX, PositionY, SpeedX, SpeedY and HeadingDeg. The rest of the data attribute remains untouched. Users should note that we do not claim that this transformation is perfect and there may be some misalignment among the different sensors. • During the transformation we tried to ensure positive y-axis points towards the north direction through visual inspection of the plot containing the positional data from all sensors. However, we do not claim that this is numerically achieved in the published dataset. Some small rotational correction may be needed to ensure the positive y-axis exactly points towards the true north. • For data contained within a particular day spread across multiple runs, the object ID’s may be repeated in the data so proper care should be taken to merge all the data from a particular day or from multiple days. 2. Dataset archive link: https://data.nrel.gov/submissions/287 3. Authorship Information: Principal Data Creator or Data Manager Contact Information Name: Rimple Sandhu ORCiD: https://orcid.org/0000-0003-4415-7694 Institution: National Renewable Energy Laboratory Address: 15013 Denver W Pkwy, Golden, CO 80401 Email: rimple.sandhu@nrel.gov Organizational Contact Information Name: National Transportation Library Data Curator Institution: National Transportation Library, Office of Information and Library Sciences, Bureau of Transportation Statistics, U.S. Department of Transportation Address: 1200 New Jersey Ave SE, Washington D.C. 20590 Email: ntldatacurator@dot.gov 4. Dates of data collection: June 24, 2024 August 21, 2024 October 30, 2024 November 22, 2024 December 20, 2024 5. Geographic location of data collection: City of Colorado Springs, CO United States of America 6. Information about funding sources that supported the collection of the data: This dataset was created through the United States Department of Transportation program "Strengthening Mobility and Revolutionizing Transportation (SMART)." The contract number for this project is: 69A3552341025. ---------------------------------------------------------------- B. SHARING/ACCESS & POLICIES INFORMATION ---------------------------------------------------------------- 0. Recommended citation for the data: U.S. Department of Transportation, National Renewable Energy Laboratory (2025). Multi-Sensor Object Detection Data from Infrastructure Sensors Deployed at Traffic Intersections in the City of Colorado Springs, Colorado, USA. https://doi.org/10.21949/rdvr-jf73 1. Licenses/restrictions placed on the data: These data are in the Public Domain. 2. Was data derived from another source?: No. 3. This dataset and its documentation was created and shared to meet the requirements enumerated in the U.S. Department of Transportation's "Plan to Increase Public Access to the Results of Federally-Funded Scientific Research" Version 1.1 << https://www.transportation.gov/sites/dot.gov/files/docs/Official%20DOT%20Public%20Access%20Plan%20ver%201.1.pdf >> and guidelines suggested by the DOT Public Access website << https://ntl.bts.gov/publicaccess/ >>, in effect and current as of April 10, 2019. ---------------------------------------------------------------- C. DATA & RELATED FILE OVERVIEW ---------------------------------------------------------------- 1. File List for the [filename].zip collection A. Filename: Dec20_2024.zip Short description: Data collected at the intersection of Stapleton Dr & Meridian Rd, El Paso County, CO, USA, using 4 EVO radars at 2 Hz and 2 Ouster lidars at 10 Hz, spanning a total duration of 94 mins B. Filename: Nov22_2024.zip Short description: Data collected at the intersection of N Nevada Ave & E Platte Ave, Colorado Springs, CO, USA, using 2 EVO radars at 10 Hz, 2 Ouster lidars at 10 Hz, and 1 Axis Camera at 10 Hz, spanning a total duration of 63 mins C. Filename: Oct30_2024.zip Short description:Data collected at the intersection of N Powers Blvd & Palmer Park Blvd, Colorado Springs, CO, USA, using 4 EVO radars at 1 Hz (85 mins) and 10 Hz (8 mins), 1 Ouster lidar at 10 Hz, and 1 Axis Camera at 10 Hz, spanning a total duration of 93 mins D. Filename: Aug21_2024.zip Short description: Data collected at the intersection of N Powers Blvd & Palmer Park Blvd, Colorado Springs, CO, USA, using 2 EVO radars at 1 Hz, 2 EVO radars at 2 Hz, 1 Ouster lidar at 10 Hz, spanning a total duration of 84 mins E. Filename: Jun24_2024.zip Short description: Data collected at the intersection of N Powers Blvd & Palmer Park Blvd, Colorado Springs, CO, USA, using 2 EVO radars at 1 Hz and 2 EVO radars at 2 Hz, spanning a total duration of 80 mins F. Filename: data_description.pdf Short description: More details on the data and the sensors ---------------------------------------------------------------- D. METHODOLOGICAL INFORMATION ---------------------------------------------------------------- 1. Description of methods used for collection/generation of data: Data presented here was collected from sensors either installed either on the traffic poles or hoisted on top of NREL’s Infrastructure Perception and Control (IPC) mobile trailer. The state-of-the-art IPC trailer can deploy the latest generation of perception sensors at traffic intersections and capture real-time road user data. Sensors used for data collection include Econolite’s EVO RADAR units, Ouster’s OS1 LIDAR units and Axis Camera units. The raw data received from individual sensors is processed at the edge computer device located inside the IPC mobile Lab, and the resulting object-level data is then stored and processed offline. Each data folder contains all the data collected on the day. We have transformed (rotation then translation) raw detections to ensure the data from all sensors is represented in the same cartesian coordinate system. The object list attributes impacted from the transformation are PositionX, PositionY, SpeedX, SpeedY and HeadingDeg. The rest of the data attribute remains untouched. Users should note that we do not claim that this transformation is perfect and there may be some misalignment among the different sensors 2. Instrument- or software-specific information needed to interpret the data: The .csv, Comma Separated Value, file is a simple format that is designed for a database table and supported by many applications. The .csv file is often used for moving tabular data between two different computer programs, due to its open format. The most common software used to open .csv files are Microsoft Excel and RecordEditor, (for more information on .csv files and software, please visit https://www.file-extensions.org/csv-file-extension). ---------------------------------------------------------------- E. DATA-SPECIFIC INFORMATION ---------------------------------------------------------------- Refer to data_description.pdf ---------------------------------------------------------------- F. UPDATE LOG ---------------------------------------------------------------- This readme file was originally created on 2025-05-12 by Daniel Sines, dan.sines@coloradosprings.gov 2025-05-12: Original file created