This is an easy to deploy Intelligent Video Analytics Demo that allows you to demo GPU accelerated Intelligent Video Analytics. The container is based on the NVIDIA DeepStream container and leverages it's built-in SEnet with resnet18 backend (TRT model which is trained on the KITTI dataset).
What is the Intelligent Video Analytics Demo?
• Easy to use demo to demonstrate GPU accelerated Inference
• Based on the NGC DeepStream container (https://ngc.nvidia.com/catalog/containers/nvidia:deepstream)
• Leverages Kubernetes, Helm, NGC, DeepStream
• Best deployed via Helm to deploy the application
• Does not require a Video Management System (VMS)
• Requires an IP camera
What is DeepStream?
DeepStream SDK delivers a complete streaming analytics toolkit for real-time AI based video and image understanding and multi-sensor processing. DeepStream SDK features hardware-accelerated building blocks, called plugins that bring deep neural networks and other complex processing tasks into a stream processing pipeline. The SDK allows you to focus on building core deep learning networks and IP rather than designing end-to-end solutions from scratch.
More information on the DeepStream container here: (https://ngc.nvidia.com/catalog/containers/nvidia:deepstream)
Running the Intelligent Video Analytics Demo
Prerequisites
- Kubernetes Cluster
- Helm/Tiller
- NVIDIA GPU Operator
- VLC Media Player (required to view the output)
Run the helm chart
Execute the below command to deploy the Intelligent Video Analytics Demo.
helm install video-analytics-demo
View the infered RTSP feed
Download VLC Player from: https://www.videolan.org/vlc/ on the client machine where the user intends to view the video stream.We can view the video stream by entering the following URL in the VLC player.
rtsp://IPAddress of Node:31113/ds-test
IPAddress of the node can be viewed by executing ifconfig on the server node
License
The DeepStream SDK license is available within the container at the location /root/deepstream_sdk_v4.0.1_x86_64/LicenseAgreement.pdf. By pulling and using the DeepStream SDK (deepstream) container in NGC, you accept the terms and conditions of this license.
Suggested Reading
For more information on DeepStream documentation containing Development guide, Plug-ins manual, API reference manual, migration guide, FAQ and release notes can be found here https://docs.nvidia.com/metropolis/index.html
If you have any questions or feedback, please refer to the discussions on DeepStream SDK Forum.
For more information, including blogs and webinars, see the DeepStream SDK website.