Docker Images

Simeon ADEBOLA edited this page Aug 24, 2018 · 20 revisions

The following instructions will get you a copy of OpenPTrack running using Docker.


Please see Supported Hardware.

Docker, nvidia-384, nvidia-docker 2 are required to use Open_PTrack docker images and this page guides you through the installation process.


Clone the open_ptrack_docker_config repository:

git clone
cd open_ptrack_docker_config

If you have nvidia-docker 1.0 installed, you need to remove it and all existing GPU containers. Run the following to do this:

sudo docker volume ls -q -f driver=nvidia-docker | xargs -r -I{} -n1 docker ps -q -a -f volume={} | xargs -r docker rm -f`

sudo apt-get purge -y nvidia-docker

If you have not yet installed docker and nvidia-docker 2 and nvidia-384 execute the following:

chmod +x setup_host

After successfully executing setup_host, reboot your system. After rebooting your system test nvidia-docker 2 by running

sudo docker run --runtime=nvidia --rm nvidia/cuda nvidia-smi

You should see an output similar to this:

| NVIDIA-SMI 384.130                Driver Version: 384.130                   |
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|   0  GeForce GTX 750 Ti  Off  | 00000000:01:00.0  On |                  N/A |
| 40%   31C    P8     1W /  38W |    188MiB /  1998MiB |      1%      Default |
| Processes:                                                       GPU Memory |
|  GPU       PID   Type   Process name                             Usage      |

Manually Building Docker Images (Optional)

This step is not required to run OpenPtrack as pre-built images are already available. If however you want to build the images yourself, the information is available here.

Running containers

After installing the prerequisites, simply start a single_camera_tracking or multi_camera_tracking container depending on your need.



cd ~/open_ptrack_docker_config/single_camera_tracking
chmod +x run_single_camera

To remove the container run : ./run_single_camera -r

To stop the container run: ./run_single_camera -s



cd ~/open_ptrack_docker_config/multi_camera_tracking

Edit ros_network.config inside multi_camera_tracking to match your system network configuration and then run:

chmod +x run_multi_camera

To remove the container run : ./run_multi_camera -r

To stop the container run: ./run_multi_camera -s

Once your container is running, follow Time Synchronization on the wiki here and then continue with the rest of the calibration.


To create a new terminal for a running container for example during calibration or multi camera tracking or face recognition, simply open a new terminal and follow the same procedure as above.

A special note: OpenPTrack is five years old in 2018! As we plan for the next five years, we would really appreciate hearing from users and developers of OPT via the OpenPTrack User & Developer Survey. It will help us to shape plans for the platform and improve outreach to our community.

About OpenPTrack v2

What's New In Gnocchi


Setting Up an OpenPTrack v2 System:

OpenPTrack System and Hardware Requirements

Build and Install


Running OpenPTrack v2:


Person Tracking

Pose Annotation

Object Tracking

Face Detection and Recognition

Tracking GUI

How to use the tracking data

How to receive tracking data in:

Deployment Guide

  1. Tested Hardware
  2. Network Configuration
  3. Imager Mounting and Placement
  4. Calibration in Practice
  5. Quick Start Example
  6. Imager Settings
  7. Manual Ground Plane
  8. Calibration Refinement (Person-Based)
  9. Calibration Refinement (Manual)


OPT on the NVidia Jetson

Hacking and Contributing to OPT.

OpenPTrack Website

Clone this wiki locally
You can’t perform that action at this time.
You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session.
Press h to open a hovercard with more details.