ZED 2i Datasheet

ZED 2i | ZED SDK
Rev 1 specifications are subject to change without notice - 2022 - All rights reserved
www.stereolabs.com
Functional SDK Diagram
ZED 2i ZED SDK
Application Layer
Stereo Camera
IMU
Barometer
Magnetometer
Sensor
Fusion
Neural
Depth Perception
Visual-Inertial Localization
Stereo SLAM
Static
Environment
Mapping
Dynamic
Objects
General SDK Description
SDK Modules
Stereo Capture The ZED 2i is a camera with dual lenses. It captures high-definition 3D video with a wide field
of view and outputs two synchronized left and right video streams in side-by-side format on
USB 3.0
Depth Sensing Depth Map
Depth maps captured by the ZED 2i store a distance value (Z) for each pixel (X, Y) in the
image. The distance is expressed in metric units (meters for example) and calculated from the
back of the left eye of the camera to the scene object.
3D Point Cloud
Another common way of representing depth information is by a 3-D point cloud. A point cloud
can be seen as a depth map in three dimensions. While a depth map only contains the
distance or Z information for each pixel, a point cloud is a collection of 3D points (X,Y,Z) that
represent the external surface of the scene and can contain color information.
Positional Tracking The ZED 2i uses visual tracking of its surroundings to understand the movement of the user or
system holding it. As the camera moves in the real-world, it reports its new position and
orientation. This information is called the camera 6DoF pose. Pose information is output at the
frame rate of the camera, up to 100 times per second in WVGA mode.
Spatial Mapping The ZED continuously scans its surroundings and creates a 3D map of what it sees. It
updates this map as the device moves around and captures new elements in the scene.
Since the camera perceives distances beyond the range of traditional RGB-D sensors, it can
quickly reconstruct 3D maps of large indoor and outdoor areas.
Object Detection Object detection is the ability to identify objects present in an image. Thanks to depth sensing
and 3D information, the ZED camera is able to provide the 2D and 3D position of the objects
in the scene.
Since ZED SDK 3.6, a custom detector can be used with the API. The 2D detection are
ingested and 3D informations such as position, 3D bounding box and more are computed.
More informations in the Custom Detector page
Body Tracking Body tracking module focuses on skeleton bone detection and tracking. A detected bone is
represented by its two end points also called keypoints. The ZED camera provides 2D and 3D
information for each keypoint as well as local rotation. The ZED SDK supports two body
formats: 18 or 34 keypoints.