Teledyne FLIR, part of Teledyne Technologies Incorporated, has announced a new release of Prism AI, which includes a compact AI model for simplified deployment on embedded systems. The updated software model helps perception engineers to easily integrate thermal cameras for advanced driver assistance systems (ADAS) and autonomous vehicle (AV) systems, with up to 24% improved object tracking performance compared to the previous Prism AI release. The new features aim to provide a complete ecosystem to build thermal-enabled ADAS and AV systems and help reduce pedestrian fatalities in all types of conditions.
Teledyne FLIR, a subsidiary of Teledyne Technologies, has launched a new version of its Prism AI software that enables quick integration of thermal cameras in advanced driver assistance systems (ADAS) and autonomous vehicle (AV) systems. The new release comes with a compact AI model that makes deployment on embedded systems easier. It also improves object tracking performance by up to 24% compared to the previous release. Prism AI is a collaborative ecosystem built for automotive perception system developers that provides seven object detection classes, visible-and-thermal image fusion, advanced thermal image processing capabilities, new shadow mode recording capabilities, batch data ingestion, and more.
Teledyne FLIR’s Prism AI simplifies the integration of automotive thermal sensors that provide superior pedestrian, animal, and vehicle detection, particularly at night and in poor visibility. Developers can use Prism AI as the primary perception software or as reference software during in-house development. Prism AI comes with a suite of tools that provides simplified data integration with Teledyne FLIR’s Conservator data lifecycle management software, as well as the industry’s largest thermal-and-visible training dataset. It also includes production-required features such as authentication between the thermal camera and the electronic control unit.
Teledyne FLIR’s Prism AI software is expected to help in reducing the record number of pedestrian fatalities in the United States. According to preliminary data from the Governors Highway Safety Association, there was a 17% increase in pedestrian fatalities in the first half of 2021 compared to the previous year and a 46% jump from 2011. Thermal-enhanced ADAS and AV systems can play a crucial role in driving down the unacceptable number of pedestrian traffic fatalities and will help automotive OEMs to meet upcoming regulatory testing procedures that include nighttime pedestrian front crash prevention.
Teledyne FLIR’s technical services team will provide expert support to perception engineers from academia to automotive OEMs to build thermal-enabled ADAS and AV systems. The Prism AI software also includes authentication between the thermal camera and the electronic control unit, which further simplifies development.
Teledyne FLIR’s Prism AI is a collaborative ecosystem designed to provide automotive perception system developers with the tools they need to create more effective systems with thermal capabilities. With the software, embedded system testing and development can be done with ease, empowering perception engineers to build more effective systems than ever before. The ecosystem simplifies the integration of automotive thermal sensors that provide superior pedestrian, animal, and vehicle detection, particularly at night and in poor visibility.
