Teledyne FLIR, part of Teledyne Technologies Incorporated announced Prism AIMMGen™, its latest addition to the Teledyne FLIR Prism™ software family.
Prism AIMMGen
Prism AIMMGen is an ITAR-free AI model generation service that enables the automated creation of artificial intelligence (AI) and machine learning (ML) models using synthetically generated data.
It offers significant cost and schedule savings for system integrators developing AI/ML products for commercial, first response, and defense applications.
Synthetic data generation toolchain
Generating annotated synthetic imagery in minutes that can be used to fine-tune AI models
The manual labeling process for AI/ML products is highly intensive, and this is further exacerbated when it includes rare and arbitrary objects such as military target classes for which data collection in real-world scenarios is both costly and difficult to near impossible.
Prism AIMMGen overcomes these hurdles with a synthetic data generation toolchain capable of generating millions of ML-ready examples of arbitrary objects in various environments and weather, all in both visible light and infrared spectrums. Generating annotated synthetic imagery in minutes that can be used to fine-tune AI models significantly reduces engineering efforts and development timelines.
Smart, synthetic data
“With the pace and sophistication in which systems are developing, it is critical to leverage smart, synthetic data to train AI models so they are best-in-class,” said Dan Walker, vice president, of Teledyne FLIR.
“AIMMGen speeds developers' time to market while ensuring that their respective AI products are ready for whatever scenario they might encounter in practically any environmental condition.”
Automated AI optimisation system
Its in-house ML operations (MLOps) infrastructure ensures data safety and leverages extensive synthetic data
The automated AI optimisation system produces high-quality models without costly data collection. Its in-house ML operations (MLOps) infrastructure ensures data safety and leverages an extensive synthetic data lake and decades of expertise.
Cost-effective development enables the release of a new model in response to new task requirements, target classes, or fine-tuning within days, future-proofing the model as the mission evolves.
Key Prism AIMMGen features
- Unlimited synthetic images – Access to a large ITAR-free data lake for multiple object detection use cases.
- Application-specific AI training datasets – Ability to produce millions of automatically labeled synthetic image sets to meet specific application requirements ensuring efficient, focused learning, including an interactive search tool.
- Automated on-premise model training, validation, and optimisation – Short-lead generation of a high-performing AI/ML solution at a fraction of the traditional engineering effort on private MLOps cloud infrastructure to achieve secure data and model handling.
