Beamr Imaging Ltd. (NASDAQ: BMR) and Intempora, a dSPACE company, announced that Beamr's video compression technology is now available on the RTMaps AI Store, a software marketplace for autonomous vehicle development teams.

RTMaps, which stands for Real-Time Multisensor Applications, is a middleware platform used by original equipment manufacturers and Tier 1 automotive suppliers for acquiring, processing, recording, and replaying sensor data streams in real time.

Beamr's content-adaptive bitrate technology, known as CABR, reduces video file sizes by up to 50% while preserving image detail that machine learning perception and detection models rely on. The technology runs GPU-accelerated for high-throughput processing and can be applied at multiple stages of the autonomous vehicle data pipeline, including logging, cloud storage, and simulation and training datasets.

According to the companies, autonomous vehicle programs can generate video data in the tens to hundreds of petabytes, creating storage and data transfer costs. Beamr's compression is described as the first such tool available on the RTMaps AI Store.

"The RTMaps AI Store gives AV teams ready-to-use software components they can easily drop straight into their development pipelines, and compression is a capability our users have been asking for," said Nicolas Du Lac, CEO of Intempora.

"Managing the volume of data AV programs generate is a constant challenge for the teams we work with, and video is the largest part of it," said Jacob Perrin, ADAS/AD Engineering Manager at dSPACE. "In our testing, Beamr reduced that video data while preserving the detections perception models depend on."

Sharon Carmel, Beamr's CEO, said the company's Blueprint methodology provides customers an end-to-end assessment of their existing video workflows before integration.

Intempora, founded in 2000 and based in Paris, has been a subsidiary of dSPACE since 2019. The information in this article is based on a press release issued by Beamr Imaging Ltd.