Waymo, Alphabet's self-driving car subsidiary, has expanded its Open Dataset and invited challengers to tackle one of five challenges related to the data.
Researchers can use the data to participate in one of the challenges: two-dimensional (2D) detection, 2D tracking, three-dimensional (3D) detection, 3D tracking, and domain adaptation.
The 2D challenges require participants to create 2D boxes for objects in a scene, while the 3D challenges include LiDAR range images to analyze and 3D upright boxes for the images or specific sequence.
Domain adaptation includes number segments from Waymo vehicles operating in rainy conditions.
Teams can include up to 10 people. Top prize in the challenge is $15,000.
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found