Thermal imaging is essential for operational environments where RGB sensors fail, but selecting the right thermal core for edge AI requires a deep understanding of sensor physics and algorithmic constraints.
Key parameters like Noise Equivalent Temperature Difference (NETD) determine the contrast available to the perception model, while pixel pitch dictates the physical size of the optics needed to achieve a specific detection range.
Our R&D evaluates these trade-offs, ensuring that the sensor architecture matches both the SWaP constraints of the platform and the detection requirements of the algorithm.