TY - GEN
T1 - CAROM - Vehicle Localization and Traffic Scene Reconstruction from Monocular Cameras on Road Infrastructures
AU - Lu, Duo
AU - Jammula, Varun C.
AU - Como, Steven
AU - Wishart, Jeffrey
AU - Chen, Yan
AU - Yang, Yezhou
N1 - Funding Information:
This research is sponsored by the Institute of Automated Mobility, Arizona, USA. We thank Maricopa County DOT, Niraj Vasant Altekar, Larry Head, Alex Cardona, Don Bruyere, Maria Elli, Jack Weast, Greg Leeming, and Marisa Paula Walker for their help.
Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - Traffic monitoring cameras are powerful tools for traffic management and essential components of intelligent road infrastructure systems. In this paper, we present a vehicle localization and traffic scene reconstruction framework using these cameras, dubbed as CAROM, i.e., “CARs On the Map”. CAROM processes traffic monitoring videos and converts them to anonymous data structures of vehicle type, 3D shape, position, and velocity for traffic scene reconstruction and replay. Through collaborating with a local department of transportation in the United States, we constructed a benchmarking dataset containing GPS data, roadside camera videos, and drone videos to validate the vehicle tracking results. On average, the localization error is approximately 0.8 m and 1.7 m within the range of 50 m and 120 m from the cameras, respectively.
AB - Traffic monitoring cameras are powerful tools for traffic management and essential components of intelligent road infrastructure systems. In this paper, we present a vehicle localization and traffic scene reconstruction framework using these cameras, dubbed as CAROM, i.e., “CARs On the Map”. CAROM processes traffic monitoring videos and converts them to anonymous data structures of vehicle type, 3D shape, position, and velocity for traffic scene reconstruction and replay. Through collaborating with a local department of transportation in the United States, we constructed a benchmarking dataset containing GPS data, roadside camera videos, and drone videos to validate the vehicle tracking results. On average, the localization error is approximately 0.8 m and 1.7 m within the range of 50 m and 120 m from the cameras, respectively.
UR - http://www.scopus.com/inward/record.url?scp=85125435323&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85125435323&partnerID=8YFLogxK
U2 - 10.1109/ICRA48506.2021.9561190
DO - 10.1109/ICRA48506.2021.9561190
M3 - Conference contribution
AN - SCOPUS:85125435323
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 11725
EP - 11731
BT - 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
Y2 - 30 May 2021 through 5 June 2021
ER -