Skip to content

Part 2 of the Jetson and InfluxDB series. Core DeepStream vision pipeline and Integration with Telegraf.

Notifications You must be signed in to change notification settings

InfluxCommunity/jetson_series_vision_pipeline

Repository files navigation

Jetson Series Part 2: Vision AI Pipeline

This tutorial will show you how to setup and configure your own Vision AI solution using DeepStream, Telegraf and InfluxDB.

The goal:

enter image description here

Things you will need

  1. Jetson Device
  2. Web Cam
  3. Complete part 1 of the tutorial
  4. DeepStream 5.1 installed
  5. InfluxDB OSS installed on your Jetson (Ubuntu - ARM64)
  6. Mosquitto MQTT Broker (See Setup)

Background

Please follow my blog here

Setup

Note: This setup guide will provided you with the needed steps to run the tutorial. Please check out the blog located under Background for a deeper understanding of the architecture.

DeepStream

  1. Clone the the project repository to your Jetson device: https://github.com/InfluxCommunity/jetson_series_vision_pipeline
  2. Install the pip requriments for the project: python3 -m pip install -r requirements.txt

MQTT Broker

  1. Update your apt repositry and then install the Mosquitto Broker: sudo apt update && sudo apt install -y mosquitto
  2. (Optional) Enable the Mosquitto Broker to start on boot: sudo systemctl enable mosquitto
  3. Start the Mosquitto Broker: sudo systemctl start mosquitto

InfluxDB OSS

  1. Install InfluxDB OSS onto the Jetson and complete setup.
  2. Import both templates into InfluxDB OSS: Jetson_Stats & Inference_Template

Telegraf

  1. Update the following plugins:
    • influxdb_v2 (edge_jetson_stats): Add token (OSS)
    • influxdb_v2 (edge_inference): Add token (OSS)
    • influxdb_v2 (cloud_jetson_stats): Add token (Cloud)
  2. Move the file to the telegraf directory: sudo mv telegraf.conf /etc/telegraf/telegraf.conf
  3. Restart the telegraf service. Note make sure your InfluxDB Instance is ready: sudo systemctl restart telegraf

Running

python3 main.py /dev/video0

Grafana Dashboard (Version 3.0 Only)

  1. Create a Grafana account and Install the FlightSQL Library

  2. Setup the flightsql client like so: First steps, make sure to include the :443 Put in your database name

  3. Go ahead and upload the Vision AI Json file into your dashboard.

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

Please make sure to update tests as appropriate.

About

Part 2 of the Jetson and InfluxDB series. Core DeepStream vision pipeline and Integration with Telegraf.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages