Ouster BlueCity’s deep learning perception model reaches training milestone, processing lidar data across 800 sites, with 4 million labeled objects – boosting detection accuracy and safety across hundreds of roadways.

Ouster, a leading global provider of high-performance lidar sensors and software solutions, announced a major software development milestone for Ouster BlueCity, its turnkey traffic management solution. As a part of the NVIDIA Metropolis ecosystem, Ouster BlueCity’s proprietary deep learning perception model has been trained on 4 million labeled objects collected from 800 sites encompassing diverse traffic patterns, intersection designs, and environmental conditions using NVIDIA TensorRT and Jetson edge AI platform.

At the core of Ouster BlueCity is Ouster’s proprietary perception software that utilizes a deep neural network (DNN) to detect, classify, and track objects and trajectory data of multimodal road users. Ouster BlueCity’s DNN runs on NVIDIA Jetson AGX Orin and NVIDIA Orin NX system-on-modules for real-time inference on the edge, bringing physical AI to smart city traffic systems around the world. The Company’s deep learning model is developed in-house and further validated against manually annotated lidar data for accuracy.

Top IntentTech News: Indico Data Launches Guidewire Claims Accelerator

With NVIDIA’s high-performance accelerated computing technology, Ouster BlueCity’s edge devices can process vast amounts of 3D lidar data in real time –delivering low-latency object detection, classification, and tracking, as well as supporting V2X communications and other intelligent transportation system (ITS) applications to improve signal timings, reduce congestion and increase safety for all road users. This approach offers significant advantages over classical algorithms, including improved generalization, greater scalability, reduced computational resources and real-time processing without the need for calibration.

Top IntentTech News: Sonata Software Secures $73M AI Deal with US TMT Company

“Ouster BlueCity is a prime example of how we are working to solve important real-world problems with physical AI,” said Ouster CEO Angus Pacala. “Powered by the NVIDIA Jetson Platform, Ouster BlueCity combines digital lidar with real-time perception to improve traffic management and road safety for all road users.

In 2024, Ouster closed deals to expand the adoption of Ouster BlueCity to over 400 sites globally, including the largest lidar-powered smart traffic network in the United States in Chattanooga, Tennessee. With millions of intersections around the world, the Company sees a massive opportunity to improve transportation safety and reduce traffic congestion with the Ouster BlueCity.

For more information on Ouster’s AI capabilities, read Ouster’s latest blog here.

Top IntentTech News: Rackspace startet OpenStack Flex für sichere Cloud

To participate in our interviews, please write to our IntentTech Media Room at sudipto@intentamplify.com

Source – Businesswire