Deploying AI object detection, target tracking, and computational imaging algorithms on embedded processors

The rapid advances in deep learning AI techniques for digital vision-based perception and gains in computational imaging for image quality have converged with innovations in mobile processors and device support to bring very large computing power to the edge. This convergence is creating opportunities for electro-optical systems to become intelligent at the edge and to eliminate issues with latency, compression artifacts, datalink bandwidth, thermal management, and system complexity. We describe the state of the art in embedded processors and the integration of Teledyne FLIR’s Prism^TM thermal and multispectral image signal processing and object detector and tracking libraries into today’s most widely deployed embedded platforms.