I have created a walkthrough for using the Nvidia Jetson Nano along with Microsoft Azure to create an Intelligent Close Circuit Television system.
The full guide for reproducing this project is available @
The project uses Azure IoT Edge https://docs.microsoft.com/en-us/azure/iot-edge/about-iot-edge?WT.mc_id=nvidia-IntelligentCCTV-pdecarlo to deploy a containerized module which runs Tiny Yolo v3 using a specially tuned fork of Darknet that has been compiled to take advantage of onboard CUDA libraries for GPU acceleration. GPU acceleration is achieved within the container using the strategy detailed in this blog post https://dev.to/azure/supercharge-your-containerized-iot-workloads-with-gpu-acceleration-on-nvidia-jetson-devices-4532 This allows us to achive object detection of at around 11 FPS using the Jetson Nano with an off the shelf Logitech Webcam.
Detected objects are tracked and displayed on a dashboard using Azure Time Series Insights -https://docs.microsoft.com/en-us/azure/time-series-insights/time-series-insights-overview?WT.mc_id=nvidia-IntelligentCCTV-pdecarlo This allows us to perform some interesting queries against the data to determine things like when a car has left the driveway, or whether an animal is in the yard etc.
Let me know if you have any interest in replicating this work and I would be happy to answer any questions that you may have. It is my hope that this project can help fast track developers to creating powerful cloud-enabled solutions using Accelerated IoT devices from Nvidia.