Beamr Imaging Ltd. Validates ML-Safe Compression for dSPACE Data Logging

Beamr Imaging Ltd. announced a joint demonstration with dSPACE, validating ML-Safe Compression for autonomous vehicle (AV) video data within the dSPACE RTMaps ecosystem. This validation ensures machine learning (ML) model accuracy is preserved while compressing large volumes of AV data generated during test drives. Testing showed Beamr's Content-Adaptive Bitrate compression (CABR) achieved a 31% file size reduction compared to baseline encodes and a 97% reduction from uncompressed data, all while maintaining ML model accuracy. This breakthrough addresses the challenge of massive data volumes in AV development, where compression is crucial for managing storage, data transfer, and development cycles. Beamr plans to extend this testing to other stages of the AV pipeline, including simulation and hardware-in-the-loop (HIL) testing. The company's technology, backed by 53 patents and an Emmy Award, aims to optimize video workflows across various high-growth markets.