Teledyne FLIR, part of Teledyne Technologies Incorporated announced version 1.0 of its Prism™ ISP, a highly optimised image signal processing software development kit (SDK) for embedded systems designed to maximise performance in thermal and multispectral applications.
Image-enhancing functionality
Designed to run on low-power GPUs from Qualcomm and NVIDIA, Prism ISP includes image-enhancing functionality for:
- Noise reduction.
- Super-resolution.
- Electronic image stabilisation.
- Infrared (IR) and electro-optical (EO) video fusion.
- Turbulence mitigation.
- Locally adaptive tone mapping.
Prism ISP applications
Developers, data scientists, and perception engineers can utilise Prism ISP with Teledyne FLIR
The Prism ISP libraries enable integrators in the defence, commercial, and industrial markets to dramatically enhance imaging quality as part of artificial intelligence (AI) data capture at the edge, improving performance, lowering development costs, and shortening time to market.
Developers, data scientists, and perception engineers can utilise Prism ISP with Teledyne FLIR market-pioneering thermal cores, including Boson®, Tau® 2, Hadron™, and Neutrino™®.
Prism AI
In addition to Prism ISP, Teledyne FLIR has also enhanced Prism AI. This powerful, efficient perception software enables classification, object detection, and object tracking in thermal and visible light spectrums.
Prism AI provides additional high-performance models trained on the world’s largest application-specific thermal image datasets, including ground intelligence, surveillance, and reconnaissance (ISR), air-to-ground, and counter-drone applications, complementing the automotive software library announced in 2022.
Thermal-based AI system development
“Prism ISP is critical to thermal-based AI system development, offering an unprecedented performance while reducing development costs,” said Dan Walker, vice president, of product management, at Teledyne FLIR.
“Within our end-to-end, computational imaging ecosystem featuring Prism AI, Teledyne FLIR can now support a wider array of projects and custom development that utilise low-power, embedded processors at the edge.”