Helm Charts
Deepstream L4T - Intelligent Video Analytics Demo

Deepstream L4T - Intelligent Video Analytics Demo

Logo for Deepstream L4T - Intelligent Video Analytics Demo
Description
This is an easy to deploy a video analytics demo that allows you to demo GPU accelerated video analytics. The container is based on the NVIDIA DeepStream L4T container
Publisher
NVIDIA
Latest Version
0.1.3
Compressed Size
35.46 KB
Modified
June 13, 2023

What is the Intelligent Video Analytics ?

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-l4t)

Running the Video Analytics Demo

Prerequisites

  • Kubernetes Cluster
  • Helm/Tiller
  • NVIDIA GPU Operator
  • Run the helm chart

If you want to use the NGC Models in Video Analytics Demo application, follow the below steps

1. helm fetch https://helm.ngc.nvidia.com/nvidia/charts/video-analytics-demo-l4t-0.1.2.tgz --untar

2. cd into the folder video-analytics-demo-l4t and update the file values.yaml

3. Go to the ngcModel section to update the NGC Model as shown in below 

# Update the NGC Model used in Deepstream
ngcModel:
  #NGC Model Pruned URL from NGC
  getModel: ngc registry model download-version "nvidia/tao/trafficcamnet:pruned_v1.0.1"
  #NGC model name
  name: trafficcamnet
  # Model File Name that will use in Deepstream
  fileName: resnet18_trafficcamnet_pruned.etlt
  # Model Config that needs to update
  modelConfig: config_infer_primary_trafficcamnet.txt
  #Do not update the Put Model
  putModel: /opt/nvidia/deepstream/deepstream-6.0/samples/configs/tao_pretrained_models/
  
ngcConfig:
  apikey: ""
  ngcorg: "nvidian"
  ngcteam: "no-team"

Execute the below commands to deploy the Intelligent Video Analytics Demo with built-in Video and WebUI

helm fetch https://helm.ngc.nvidia.com/nvidia/charts/video-analytics-demo-l4t-0.1.2.tgz

helm install video-analytics-demo-l4t-0.1.2.tgz

If you want to use camera as input, Please follow the below steps to deploy Intelligent Video Analytics Demo.

1. helm fetch https://helm.ngc.nvidia.com/nvidia/charts/video-analytics-demo-l4t-0.1.2.tgz --untar

2. cd into the folder video-analytics-demo-l4t and update the file values.yaml

3. Go to the section Cameras in the values.yaml file and add the address of your IP camera. Read the comments section on how it can be added. Single or multiple cameras can be added as shown below
cameras:
 camera1: rtsp://XXXX
 camera2: rtsp://XXXX

4. helm install video-analytics-demo-l4t

To use the rtsp steam output, add the below configuration when installing the helm chart

cat <<EOF | tee values.yaml
service:
  type: NodePort
  port: 80
  rtspnodePort: 31113
  webuiPort: 5080
  webuinodePort: 31115
EOF

Run the below command to install the video analytics demo above custom values

helm install iva --values ./values.yaml video-analytics-demo-l4t

View the Video Output

  1. Use the below WebUI URL to access deepstream application from browser
http://IPAddress of Node:31115

NOTE: WebUI application need at least 1.25GB storage on Jetson/ARM system

  1. 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 opt/nvidia/deepstream/deepstream-6.0/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

Technical Support

Email: EGXSupport@nvidia.com