您最多选择25个主题 主题必须以中文或者字母或数字开头,可以包含连字符 (-),并且长度不得超过35个字符

2.1 KiB

Unity Perception package (com.unity.perception)

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

The Perception package is in active development. Its features and API are subject to significant change as development progresses.

Installation instructions

Setting up your first perception scene

Randomizing your simulation

Example projects using Perception

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 Perception could be used in a smart city or autonomous vehicle simulation. Datasets can be generated locally or at scale in Unity Simulation.

Package contents

Feature Description
Labeling Component which marks a GameObject and its descendants with a set of labels
LabelConfig Asset which defines a taxonomy of labels for ground truth generation
Perception Camera Captures RGB images and ground truth from a Camera
DatasetCapture Ensures sensors are triggered at proper rates and accepts data for the JSON dataset
Randomization Integrate domain randomization principles into your simulation

Known Issues

  • The Linux Editor 2019.4.7f1 and 2019.4.8f1 have been found to hang when importing HDRP-based perception projects. For Linux Editor support, use 2019.4.6f1 or 2020.1