From a technical perspective,
the most important requirement of an video recognition system is that it processes video streams and runs neural network algorithms locally.
By performing character recognition on or near the device, eliminates the latency of sending video streams back to the cloud for analysis, minimize the network transmission costs associated with wirelessly streaming video, and reduce any security concerns related to sending information over the network.
AI on Edge
The challenge this presents is that massive computational and memory resources are required to run neural networks. This is why they are typically run in a data center, not at the edge.
TensorRT
TensorRT is a C++ library based on the CUDA parallel programming model that optimizes trained neural networks for deployment in production-ready embedded systems. It achieves this by compressing the neural net into a condensed runtime engine and adjusting the precision of floating-point and integer operations for the target GPU platform. This correlates directly to improved latency, power efficiency, and memory consumption in deep learning-enabled systems, all of which are of course essential in video recognition applications.
SoC with GPU
A variety of computer vision-based chipsets are available in the market but what ultimately sets Jetson products apart is a vibrant software ecosystem. For AI, this meant access to TensorRT, a programmable software platform that accelerates inferencing workloads running on NVIDIA GPUs.
Jetson Platform
TensorRT is part of the NVIDIA JetPack SDK, a software development suite that includes a Ubuntu Linux OS image, Linux kernel, bootloaders, libraries, APIs, an IDE, and other tools. The SDK is continuously updated by NVIDIA to help accelerate the AI development lifecycle.
