Authors:
Md Parvez Mollah
1
;
Murugan Sankaradas
2
;
Ravi K. Rajendran
2
and
Srimat T. Chakradhar
2
Affiliations:
1
Department of Computer Science, The University of New Mexico, Albuquerque, New Mexico, U.S.A.
;
2
NEC Laboratories America, Inc., Princeton, New Jersey, U.S.A.
Keyword(s):
Roadside LiDAR, Background Subtraction, Sensor-Agnostic Compression, Cloud, Edge Systems.
Abstract:
LiDAR technology has emerged as a pivotal tool in Intelligent Transportation Systems (ITS), providing unique capabilities that have significantly transformed roadside traffic applications. However, this transformation comes with a distinct challenge: the immense volume of data generated by LiDAR sensors. These sensors produce vast amounts of data every second, which can overwhelm both private and public 5G networks that are used to connect intersections. This data volume makes it challenging to stream raw sensor data across multiple intersections effectively. This paper proposes an efficient real-time compression method for roadside LiDAR data. Our approach exploits a special characteristic of roadside LiDAR data: the background points are consistent across all frames. We detect these background points and send them to edge servers only once. For each subsequent frame, we filter out the background points and compress only the remaining data. This process achieves significant temporal
compression by eliminating redundant background data and substantial spatial compression by focusing only on the filtered points. Our method is sensor-agnostic, exceptionally fast, memory-efficient, and adaptable to varying network conditions. It offers a 2.5x increase in compression rates and improves application-level accuracy by 40% compared to current state-of-the-art methods.
(More)