Communications of the ACM
Technique Improves AI Ability to Understand 3D Space Using 2D Images
The work would help the artificial intelligence used in autonomous vehicles navigate in relation to other vehicles, using the two-dimensional images it receives from an onboard camera.
Credit: Tianfu Wu, Matt Shipman
A technique developed by researchers at North Carolina State University (NC State) uses two-dimensional (2D) images to improve the ability of artificial intelligence (AI) programs to identify three-dimensional (3D) objects.
Called MonoCon, the technique could improve the navigation of autonomous vehicles in relation to other vehicles using 2D images from onboard cameras, which are less expensive than LiDAR sensors.
MonoCon can put 3D objects identified in 2D images into a "bounding box," which indicates to the AI the outermost edges of the objects.
Said NC State's Tianfu Wu, "In addition to asking the AI to predict the camera-to-object distance and the dimensions of the bounding boxes, we also ask the AI to predict the locations of each of the box's eight points and its distance from the center of the bounding box in two dimensions," which "helps the AI more accurately identify and predict 3D objects based on 2D images."
From NC State University News
View Full Article
Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA
No entries found