OpenDataCam 2.0.0

This project is offline lightweight DIY solution to monitor urban landscape. After installing this software on the specified hardware (Nvidia Jetson board + Logitech webcam), you will be able to count cars, pedestrians, motorbikes from your webcam live stream.

Behind the scenes, it feeds the webcam stream to a neural network (YOLO darknet) and make sense of the generated detections.

It is very alpha and we do not provide any guarantee that this will work for your use case, but we conceived it as a starting point from where you can build-on & improve.

πŸ‘‰ See Demo Video (4 min)

Demo OpenDataCam

Table of content

πŸ’» Hardware pre-requisite

If you have a Jetson Nano, please read this specific documentation

Also see In depth guide about compatible Cameras with Jetson

🎬 Get Started, quick setup

1. Software pre-requisite πŸ“¦

For jetson: Flash Jetson board to jetpack 4.2 or 4.2.1 ⚑️

Ignore this if you are not running on a jetson

See How to find out your jetpack version

If your jetson does not have jetpack 4.2 or 4.2.1 (CUDA 10, TensorRT 5, cuDNN 7.3, Ubuntu 18.04)

Follow this guide to flash your jetson

For non-jetson: Install nvidia-docker v2.0 πŸ”§

Ignore this if you are running on a jetson, nvidia-docker isn’t necessary with jetpack 4.2

Nvidia-docker v2.0 is only compatible with GNU/Linux x86_64 machine with a CUDA compatible GPU

Follow this guide to install nvidia-docker v2.0 on your machine

2. Install and start OpenDataCam πŸš€

Open a terminal or ssh to you machine and run the following commands depending on your platform

ls /dev/video*
# Output should be: /dev/video0

If this isn’t the case, run the install script anyway, and after you will need to modify the config.json file to select your desired VIDEO_INPUT (file, usbcam, raspberrycam, remote IP cam), we will improve setup / install process for v2.1 πŸ’ͺ

Install commands:

# Download install script
wget -N

# Give exec permission
chmod 777

# NB: You will be asked for sudo password when installing the docker container

# Install command for Jetson Nano
./ --platform nano

# Install command for Jetson TX2
./ --platform tx2

# Install command for Jetson Xavier
./ --platform xavier

# Install command for a Nvidia-docker machine (ARCH_BIN=6.1)
# NB: Will run from demo file, you can change this after install, see "5. Customize OpenDataCam"
./ --platform nvidiadocker_cuda_archbin_6_1

This command will download and start a docker container on the machine. After it finishes the docker container starts a webserver on port 8080.

The docker container is started in auto-restart mode, so if you reboot your machine it will automaticaly start opendatacam on startup. (Learn more about the specificities of docker on jetson)

You can also use opendatacam without docker

2. bis (optional) Upgrade OpenDataCam (from v2.x to another v2.x version)

NB: we do not handle auto update of the config.json file

3. Use OpenDataCam πŸ––

Open your browser at http://IPOFJETSON:8080 .

If you are running with the jetson connected to a screen: http://localhost:8080

NB: OpenDataCam only supports one client at a time, if you open the UI on two different devices, the stream will stop in one of them.

See Docker playbook οΈπŸ“š how to restart / stop OpenDataCam.

4. Configure your Wifi hotspot πŸ“²

In order to operate opendatacam from your phone / tablet / computer.

See Make jetson device / machine accessible via WIFI

5. Customize OpenDataCam οΈοΈβš™οΈ

We offer several customization options:

Learn how to customize OpenDataCam

6. Docker playbook οΈπŸ“š

Docker specificities on jetson

Docker doesn’t support GPU usage on Jetson (see issue #214 on docker-nvidia official repo , support should be landing around Q3-Q4 2019)

Meanwhile we need to give to the docker container access to the host platform GPU. We do so by mounting several volumes with this script.

That is why you need to use our install script to install a container. We have an open issue to simplify setup once nvidia-docker support lands for jetson devices.

How to show OpenDataCam logs

# List containers
sudo docker container list

sudo docker logs <containerID>

How to stop / restart OpenDataCam

# List containers
sudo docker container list

# Stop container (get id from previous command)
sudo docker stop <containerID>

# Start container (will mount the opendatacam_videos/ and the config.json + mount CUDA necessary stuff)
sudo ./

# Restart container (after modifying the config.json file for example)
sudo docker restart <containerID>

# Install a newer version of opendatacam
# Follow the 1. Install and start OpenDataCam

# See stats ( CPU , memory usage ...)
sudo docker stats <containerID>

# Clear all docker container, images ...
sudo docker system prune -a

πŸ”Œ API Documentation

In order to solve use cases that aren’t taken care by our opendatacam base app, you might be able to build on top of our API instead of forking the project.

πŸ—ƒ Data export documentation

⁉️ Troubleshooting

Common errors with answers

πŸŽ› Advanced uses

How to use opendatacam without docker

Read How to use opendatacam without docker

How to create / update the docker image

We host our docker images on Dockerhub

For jetson devices:

See How to create / update a docker image for a jetson device

For nvidia-docker machine:

See How to create / update a docker image for a nvidia-docker machine

🎯 How accurate is OpenDataCam ?

We are working on adding a benchmark to rank OpenDataCam on the MOT Challenge (Multiple Object Tracking Benchmark) for v2.1.

Accuracy depends on which YOLO weights your hardware is capable of running.

🚀 How fast is OpenDataCam ?

FPS depends on:

We made the default settings to run at least at 10 FPS on any Jetson.

Learn more in the Customize OpenDataCam documentation

πŸ›  Development notes

See Development notes

Technical architecture overview:

Technical architecture

πŸ’Œ Acknowledgments