Beamr delivered 31% file size reduction compared to baseline encodes on footage from dSPACE RTMaps. Results to be demonstrated at dSPACE User Conference, April 21-22, Novi, Michigan

Beamr Imaging Ltd. (NASDAQ: BMR), a leader in video optimization technology and solutions, and dSPACE, a leading provider of solutions for the development of connected, autonomous, and electrically powered vehicles, today announced a joint demonstration validating, for the first time, compression for autonomous vehicle (AV) video data in the dSPACE RTMaps ecosystem while preserving machine learning (ML) model accuracy. The demonstration will be presented at dSPACE user conference, held from April 21-22 in Novi, Michigan.

AV fleets generate massive volumes of multi-camera video data during test drives. A single run produces terabytes of footage, choking storage, slowing data transfer, and extending development iteration cycles. Applying compression at the data logging stage reduces the volume of video data entering downstream storage and processing pipelines, where infrastructure costs accumulate at scale. Yet many AV teams hesitate to compress, lacking confidence that file size reduction can be achieved without compromising ML model accuracy.

Marketing Technology News: MarTech Interview With Fredrik Skantze, CEO and Co-founder of Funnel

Testing on real-world sequences processed through dSPACE RTMaps showed Beamr Content-Adaptive Bitrate compression (CABR) delivered 31% file size reduction compared to baseline encodes, and 97% reduction for uncompressed data – while preserving ML model accuracy. RTMaps is a multisensor software framework for data logging and replay, software development, and real-time execution.

In previous benchmarks, CABR demonstrated ML-safe video data compression with up to 50% file size reduction for real-world and synthetic video data, across the AV pipeline. For object detection tasks, CABR showed <2% difference in mean Average Precision, well within the model’s expected variance. Testing with world foundation models showed no measurable impact on AV captioning, evaluated using two embedding models. Beamr and dSPACE plan to extend ML-safe compression testing to additional stages, including video data simulation and hardware-in-the-loop (HIL) testing.

Marketing Technology News: The Death of Third-Party Cookies Was Just the Start. Are You Ready for Consent Orchestration?

“ML-safe compression is essential for any team running AV pipelines at scale,” said Dani Megrelishvili, Beamr Chief Product Officer. “Validating Beamr’s technology inside RTMaps brings that assurance into the dSPACE ecosystem, so teams already running these workflows can reduce their data volumes without rebuilding their pipeline.”