Open Video Tracker — User Guide

Introduction

Open Video Tracker is a Blender add‑on that automates converting video footage into 3D point clouds and camera tracks using photogrammetry techniques. It integrates FFmpeg, COLMAP, and GLOMAP to provide a streamlined workflow for video tracking and 3D reconstruction.

Note: The add‑on is currently available for Windows only. Use the CUDA build if you have an NVIDIA RTX GPU; otherwise, use the standard version.

Video Demo

See the end-to-end workflow in action.

Installation

Step 1 — Download the add‑on
  • Download the Open Video Tracker add‑on (Windows only for now).
  • If you have an NVIDIA RTX GPU, download the CUDA build; otherwise, download the standard build.
  • Locate the open_video_tracker folder containing the add‑on files.
Step 2 — Install in Blender
  1. Open Blender
  2. Go to EditPreferences
  3. Select the Add-ons tab
  4. Click Install from Disk
  5. Navigate to and select the open_video_tracker folder
  6. Click Install From Disk
Step 3 — Verify installation
  1. Switch to the 3D Viewport
  2. Open the right sidebar and look for the Open Video Tracker tab
  3. If it’s visible, the installation was successful

User Interface Overview

Open Video Tracker main panel Open Video Tracker import options panel
Screenshots of the main panel and import options.
Main Panel

The main interface is located in the 3D Viewport sidebar under the “Open Video Tracker” tab.

Video Selection
  • Video Path: File browser to select input video file
  • Video Information: Displays frame rate, resolution, and bitrate
Frame Extraction Settings
  • Quality: Native, High, Balanced, Low, Lowest
Feature Extraction Settings
  • Max Image Size (default: 2000 px)
  • Use GPU: Enable for CUDA version
  • Camera Model: Simple Radial recommended
  • Max Num Features (default: 8192)
Sequential Matching
  • Overlap: Number of overlapping frames (default: 10)
Reconstruction Settings
  • Max Tracks per image (default: 1000)
  • Constraint Type: Balance between point and camera constraints
  • Advanced Options: GLOMAP parameters (epipolar error, iterations)
Execution Controls
  • Track Video: Start the processing pipeline
  • Progress: Real-time progress indicator
Import Options Panel

Camera Import

  • Import Cameras: Enable camera track import
  • Camera Extent: Size of camera visualization
  • Add Background Images
  • Add Image Planes
  • Animation Options

Point Import

  • Import Points
  • Point Cloud Display: Sparsity and rendering options
  • GPU Rendering
  • Mesh Options

Workflow

Step 1 — Prepare your video
  • Supported formats: MP4, AVI, MOV, MKV, WMV, FLV, WebM
  • Use high-quality, stable footage
  • Ensure good lighting and contrast
  • Start with short clips for testing
Step 2 — Configure processing settings

Video Quality

  • Native/High: Best quality, slowest processing
  • Balanced: Good quality/performance
  • Low/Lowest: Fastest, smaller files

Feature Extraction

  • Increase Max Image Size for high-res videos
  • Enable GPU if available
  • Choose camera model based on camera type

Reconstruction

  • Adjust Max Tracks for scene complexity
  • Use Balanced constraints for most cases
Step 3 — Run the pipeline
  • Click Track Video
  • Monitor progress
  • Processing time depends on video length and settings
  • Do not close Blender during processing
Step 4 — Import results

After processing completes, the add‑on automatically imports:

  • Camera objects with animation data
  • Point cloud data
  • Background images (if enabled)

Configuration Options

Camera Models
  • Simple Radial: Most consumer cameras (smartphones, DSLRs)
  • Simple Radial Fisheye: Action cameras (GoPro)
  • OpenCV: Computer vision cameras
  • Full OpenCV: Complex distortion scenarios
Constraint Types
  • Points Only: When camera positions are unreliable
  • Cameras Only: When point features are sparse
  • Balanced: Recommended default
  • Points and Cameras: Maximum constraints, slower

Running the Pipeline

Progress
  • Each step is logged to the Blender console
  • View via WindowToggle System Console (Windows)
Expected output

The add‑on uses the same directory as the .blend file and creates:

{your_blend_file_directory}/
└── video_tracking/
    └── {video_name}/
        ├── images/           # Extracted frames
        ├── sparse/           # Reconstruction data
        │   ├── 0/            # Model files
        │   ├── cameras.txt   # Camera data
        │   ├── images.txt    # Image data
        │   └── points3D.txt  # Point cloud data
        └── database.db       # COLMAP database

Importing Results

Camera Import
  • Camera Extent: Visual size of camera objects
  • Background Images: Show original frames
  • Image Planes: Create textured planes
  • Animation: Convert camera motion to keyframes
Point Cloud Import
  • Display Sparsity: Reduce density for performance
  • GPU Rendering
  • Mesh Conversion: Convert points to mesh objects

Post‑Processing

Coming soon.

Best Practices

Video Preparation
  • Resolution: Higher resolution improves tracking but increases time
  • Frame Rate: 24–30 fps is optimal
  • Stabilization: Use stabilized footage when possible
  • Lighting: Ensure consistent, even lighting
  • Motion: Prefer smooth camera movement
Processing Optimization
  • Start Small: Test with short clips first
  • GPU Usage: Enable when available
  • Quality Settings: Use Balanced for initial tests
  • Memory Management: Monitor RAM with large videos
Scene Considerations
  • Feature‑Rich scenes track better
  • Minimize motion blur
  • Include objects of known scale
  • Ensure sufficient frame overlap

Quick Fixes

  • Processing fails: Check executable paths in preferences
  • Out of memory: Reduce Max Image Size or use lower quality
  • Poor tracking: Adjust camera model or increase Max Features
  • Slow processing: Enable GPU or reduce video resolution

Credits

Logos and trademarks are the property of their respective owners.