-
Notifications
You must be signed in to change notification settings - Fork 65
Build and Install
This describes how to install required dependencies (including ROS Kinetic), softwares, drivers and the OpenPTrack v2 “Gnocchi release” on a PC.
We currently offer two approaches to installing OpenPTrack V2. You only need one of these approaches. Due to the large number of dependencies and extensive build process, if you just want to run OpenPTrack, we suggest trying the Docker approach first.
This approach uses pre-built Docker images to run OPT. You can download images of the dependencies and our latest source branch via Docker. This is especially good if you are an OPT beginner, are not too familiar with or are not interested in customization options for dependencies and drivers. Instructions are found here.
This approach takes you step by step through the installation process. It starts with the dependencies, then CUDA and other softwares, and finally the OpenPTrack v2 modules. Users of this approach are able to customize the steps based on their understanding of their machine requirements and their knowledge. This approach can easily be used by intermediate and advanced users. Instructions can be found here.
- System Requirements
- Supported Hardware
- Initial Network Configuration
- Example Hardware List for UCLA Setup
- Making the Checkerboard
- Time Synchronization
- Pre-Tracking Configuration
- Camera Network Configuration
- Single Camera
- Setting Parameters
- Multi-Sensor Person Tracking
- HOG vs YOLO Detectors
- World Coordinate Settings
- Single Camera
- Pose Initialization
- Multi Sensor Pose Annotation
- Pose Best Practices
- Setting Parameters
- Single Camera
- Setting Parameters
- Multi Sensor Object Tracking
- YOLO Custom Training & Testing
- Yolo Trainer
- Single Camera
- Setting Parameters
- Multi Sensor Face Detection and Recognition
- Face Detection and Recognition Data Format
How to receive tracking data in: