3D vision

Move from 2D images to 3D positions: segment detected objects in point clouds and measure distance from a depth camera so a robot can reason about physical space.

Segment 3D objects
Use the vision service's GetObjectPointClouds method to find and label objects in 3D space, combining a 2D detector with a depth camera's point cloud.

Measure depth
Retrieve point clouds and depth images from a depth camera, read depth at specific pixels, and measure distance to detected objects.