OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Data & Analytics

Opendatacam

Opendatacam is an open-source computer-vision application that detects and tracks moving objects in live camera feeds and recorded videos, then counts them as they cross user-defined counters.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Opendatacam — OpenViST project profile in AI Data & Analytics.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a camera feed or video can serve as the input for counting moving objects, particularly for traffic and public-space flow studies.

Who it is for

  • People conducting traffic studies, including modal-split and turn-count analysis.
  • Researchers and practitioners who need counts or trajectory analysis from camera footage.
  • Developers extending the application through its API or exported counter and tracker data.

Documented uses

  • Count objects crossing defined lines in a scene.
  • Analyze prerecorded video or real-time camera feeds.
  • Review movement trajectories and counts across multiple object classes.
  • Adapt detection to a target object by training a custom model when the built-in classes do not cover it.
Before you choose

Requirements & limits

The project is open source under the MIT license. The documented quick setup requires Docker and Docker Compose; supported installation instructions also specify hardware and NVIDIA software prerequisites.

  • Counters are defined by the user in the interface or API, and counts are recorded when detected objects cross them.
  • The README describes support for more than 50 common object types, with custom-model training available for other targets.
  • The documented installation paths focus on Jetson devices and computers with NVIDIA GPUs.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up OpenDataCam with Docker

Start the documented demo application on a supported Jetson device or NVIDIA GPU computer.

Before you start

  • Docker and Docker Compose.
  • For an NVIDIA GPU computer: CUDA 11, cuDNN 8, NVIDIA Container Toolkit and nvidia-container-runtime.
  • For a Jetson device: JetPack 5.x.
  • A terminal and sudo access for installation.

Steps

  1. Download the installation script with wget -N https://raw.githubusercontent.com/opendatacam/opendatacam/v3.0.2/docker/install-opendatacam.sh.

  2. Make it executable with chmod 777 install-opendatacam.sh.

  3. Run ./install-opendatacam.sh --platform nano for Jetson Nano, --platform xavier for Jetson Xavier/Xavier NX, or --platform desktop for a laptop, desktop or server with an NVIDIA GPU.

  4. Open a browser at http://[IP_OF_JETSON]:8080 or, on the connected Jetson screen, http://localhost:8080.

Expected outcome

The installer starts a Docker container and web server on port 8080 with a demo video ready for counting.

Guide limitations

  • The documented platform options are Jetson Nano, Jetson Xavier/Xavier NX, and a computer with an NVIDIA GPU.
  • The installer requests a sudo password. The container is set to auto-restart; the README says to stop it with docker-compose down in the installation-script folder.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
opendatacam/opendatacam · Official homepage title · retained in its source language
How we review sourcesSuggest a correction