com.unity.perception is in active development. Its features and API are subject to significant change as development progresses.

Perception Package (Unity Computer Vision)

The Perception package provides a toolkit for generating large-scale datasets for computer vision training and validation. It is focused on a handful of camera-based use cases for now and will ultimately expand to other forms of sensors and machine learning tasks.

Visit the Unity Computer Vision page for more information on our tools and offerings!

Getting Started

Quick Installation Instructions
Get your local Perception workspace up and running quickly. Recommended for users with prior Unity experience.

Perception Tutorial
Detailed instructions covering all the important steps from installing Unity Editor, to creating your first computer vision data generation project, building a randomized Scene, and generating large-scale synthetic datasets by leveraging the power of Unity Simulation. No prior Unity experience required.

Human Pose Labeling and Randomization Tutorial
Step by step instructions for using the keypoint, pose, and animation randomization tools included in the Perception package. It is recommended that you finish Phase 1 of the Perception Tutorial above before starting this tutorial.

FAQ
Check out our FAQ for a list of common questions, tips, tricks, and some sample code.

Documentation

In-depth documentation on individual components of the package.

Feature	Description
Labeling	A component that marks a GameObject and its descendants with a set of labels
Label Config	An asset that defines a taxonomy of labels for ground truth generation
Perception Camera	Captures RGB images and ground truth from a Camera.
Dataset Capture	Ensures sensors are triggered at proper rates and accepts data for the JSON dataset.
Randomization	The Randomization tool set lets you integrate domain randomization principles into your simulation.

Community and Support

For setup problems or discussions about leveraging the Perception package in your project, please create a new thread on the Unity Computer Vision forum and make sure to include as much detail as possible. If you run into any other problems with the Perception package or have a specific feature request, please submit a GitHub issue.

For any other questions or feedback, connect directly with the Computer Vision team at computer-vision@unity3d.com.

Example Projects

SynthDet

SynthDet is an end-to-end solution for training a 2D object detection model using synthetic data.

Unity Simulation Smart Camera example

The Unity Simulation Smart Camera Example illustrates how the Perception package could be used in a smart city or autonomous vehicle simulation. You can generate datasets locally or at scale in Unity Simulation.

Robotics Object Pose Estimation Demo

The Robotics Object Pose Estimation Demo & Tutorial demonstrates pick-and-place with a robot arm in Unity. It includes using ROS with Unity, importing URDF models, collecting labeled training data using the Perception package, and training and deploying a deep learning model.

Local development

The repository includes two projects for local development in TestProjects folder, one set up for HDRP and the other for URP.

Suggested IDE Setup

For closest standards conformity and best experience overall, JetBrains Rider or Visual Studio w/ JetBrains Resharper are suggested. For optimal experience, perform the following additional steps:

• To allow navigating to code in all packages included in your project, in your Unity Editor, navigate to Edit -> Preferences... -> External Tools and check Generate all .csproj files.

Known issues

• The Linux Editor 2019.4.7f1 and 2019.4.8f1 might hang when importing HDRP-based Perception projects. For Linux Editor support, use 2019.4.6f1 or 2020.1

License

• License

Citation

If you find this package useful, consider citing it using:

@misc{com.unity.perception2021,
    title={Unity {P}erception Package},
    author={{Unity Technologies}},
    howpublished={\url{https://github.com/Unity-Technologies/com.unity.perception}},
    year={2020}
}