Neutrino LC USB/Analog VPC Kit

The USB VPC kit with an additional custom 6-foot cable with a BNC pigtail provides an additional analog video signal (NTSC-compliant).

Neutrino LC Utility Kit

Provides all output options on a single PCB. Includes a wire harness to the cooler interface. The accessory board converts video signal into a Camera-Link-compliant output via a SDR-26 receptacle.

Neutrino SX8 Accessory Board

The Utility Kit provides Camera link and HDMI video output to a single development electronics board. The kit includes a wire harness for camera and cooler power. Communication and power to the Neutrino SX8 camera electronics is provided via a USB driver to a virtual COM port. External sync input/output signals are provided with standard MCX connectors. A header connector is provided for RS-422 lens control.

Neutrino SX8 Demonstration Lens

A 30 mm fixed focal length, f/2.5 lens provides a 32° HFOV. Includes a mechanical housing for the lens and allows for focus capability via keyed lens barrel and threaded barrel/housing.

Prism™ AI

Object Detection and Tracking Software Libraries

Prism AI is a collection of software libraries that enable classification, object detection, and object tracking operating on low-power embedded processors from Qualcomm and NVIDIA. The Teledyne FLIR perception software and powerful, efficient embedded processors enable developers to bring decision support and computational imaging to the edge.

Compatible with Teledyne FLIR market-leading thermal modules, including Boson®, Hadron™, and Neutrino®, Prism AI provides high-performance models trained on the world’s largest application-specific thermal image datasets. Perception software models are available for automotive, ground ISR, air-to-ground, and counter-drone applications.

Prism™ Development Kit for Qualcomm® RB5

Prism Software and LWIR Camera Evaluation Kit

The Prism Development Kit for Qualcomm RB5 enables system engineers to evaluate Prism ISP and Prism AI with the output of Teledyne FLIR’s Hadron™ thermal imaging camera modules. Prism ISP software includes image fusion, super resolution, turbulence mitigation, electronic imaging stabilization, 16-to-8-bit tone mapping, and local contrast enhancement (LCE). Prism AI features a mature perception software that includes object classification, object detection, object tracking, and fine-grained classification trained on the world’s largest thermal image data lake with over 5 million annotation assets.

The development kit includes Teledyne FLIR’s Hadron dual visible and thermal camera module, all necessary cables, and the Qualcomm Robotics RB5 QRB5165 system on chip (SoC), the most popular and efficient mobile processor for digital imaging, bringing unprecedented capabilities to Teledyne FLIR thermal camera module integrators.

Prism™ ISP

Advanced Computational Image Processing Software

Prism ISP is a collection of image signal processing (ISP) software libraries that include super-resolution, electronic image stabilization, image fusion, turbulence mitigation, noise reduction, and more. Compiled to run on low-power embedded processors from Qualcomm and NVIDIA, enabling developers to bring computational imaging to the edge while improving performance, lowering development costs, and shortening time to market.

Prism ISP is compatible with Teledyne FLIR market-leading thermal cores including Boson®, Tau® 2, Hadron™, and Neutrino®. The ISP libraries enable integrators to leverage high-performance ISP algorithms that dramatically enhance the viewed image quality and AI capabilities of world-class infrared camera modules for defense, industrial, and commercial applications.

Prism™ SKR

Automated Target Recognition, Tracking and Homing Software

Prism SKR provides precision Automatic Target Recognition (ATR) detection, identification, and tracking for autonomously guided weapon systems including loitering munitions, air launched effects (ALE), counter UAS systems (CUAS), low-cost missiles, and smart munitions. It utilizes an advanced algorithm pipeline with target search, target identification, target state estimation, and aim point localization.

Original equipment manufacturers (OEMs) can integrate Prism SKR at the edge on low-power embedded systems from NVIDIA® or on the Teledyne FLIR AVP, an advanced video processor system on module (SOM) based on the Qualcomm Dragonwing™ QCS8550. Boson® and Neutrino® infrared (IR) camera modules and integrator-selected visible cameras integrate seamlessly, providing machine and target state via a Weapon Open System Architecture (WOSA) compliant interface.

The Prism software ecosystem reduces development cost and risk with out-of-the-box compatibility with Prism Supervisor, which provides autonomous mission control and platform guidance. Prism AI software models leverage Teledyne FLIR’s six million visible and thermal annotations and can be expanded quickly using Prism AIMMGen synthetic dataset and model training tool chain to incorporate custom target lists. A complete Application Programming Interface (API) and Software Development Kit (SDK) is available for further customization and performance optimization.

Prism™ Supervisor

Autonomous Mission Execution Software

Prism Supervisor advanced autonomy software enhances the capabilities of unmanned aircraft systems (UAS). It seamlessly integrates drone autopilot flight control systems and real-time artificial intelligence (AI)-based observations at the edge to improve mission safety, efficiency, and performance. Prism Supervisor simplifies the operator experience with a user-friendly interface for mission planning, real-time mission visualization, and one-click start-to-finish execution. Mission planners are empowered with a flexible programming framework and SDK, allowing the creation of advanced behaviors and dynamic responses. High-level scripting capability enables custom, intricate mission scenarios, facilitating collaborative behaviors and synchronized mission execution among multiple unmanned aerial vehicles (UAVs). Prism Supervisor adapts in real-time, dynamically generating mission segments and flight plans on the fly, minimizing operator impact, and improving mission success.

Prism™ AI - Auto

Detection and Tracking Software Framework for Automotive Perception System Development

Prism AI - Auto is a software framework that provides classification, object detection, and object tracking enabling perception engineers to quickly start integrating thermal cameras for advanced driver assistance systems (ADAS) and autonomous vehicle (AV) systems. Developers can use Prism AI as the primary perception software or as reference while taking advantage of camera calibration tools, along with visible-and-thermal fusion and advanced image processing capabilities that offer superior perception capability, especially for pedestrian and animal detection.

Compatible with Teledyne FLIR market-leading thermal cameras including Boson®, Tau® 2, and the FLIR ADK, Prism AI features camera-to-ECU authentication, a key requirement for automotive production deployment. Prism AI tools provide simplified data integration with Teledyne FLIR Conservator™ dataset development software as well as the industry’s largest thermal-and-visible training dataset. The combination of validated models with successful performance in NCAP-based automatic emergency braking (AEB) tests, AI tools, ONNX model plugins, and annotation services decreases development cost and shortens time to market for a thermal-enabled ADAS or AV systems.

Prism™ AIMMGen™

Automated Synthetic Data Generation and AI Model Training Service

AIMMGen is a dual-use AI model generation service that enables the automated creation of AI models based on ITAR-free training datasets. It reduces cost and schedule, delivering high-quality data and/or models in days, not weeks, for defense, first-responders, and commercial applications.

It leverages Teledyne’s proprietary synthetic data generation toolchain that can generate millions of machine-learning-ready examples of military and civilian objects in various environments, weather, and spectral bands. By leveraging advanced graphics capabilities, AIMMGen can generate imagery for complex scenarios for autonomous vehicles or simulate current military objects that are nearly impossible to capture in the real-world. AIMMGen generates annotated synthetic image data in minutes, replacing weeks needed for hand labeled data.

AIMMGen’s model generation capability is made possible by a first-of-its-kind fully automated AI optimization system, which produces high-quality models without costly ML engineering. Optimization is run on in-house MLOps infrastructure and automated workflows that leverage decades of AI/ML expertise to generate high-quality object detection and recognition models. The models are then automatically validated on customer-provided test case data or by leveraging an extensive synthetic data lake.

Cost-effective development enables the release of new or updated models in as little as a few days in response to new task requirements, target classes, or conditions, future proofing the model as the mission evolves.