- Palo Alto CA, US Ziqiang Huang - Palo Alto CA, US
International Classification:
G01S 7/497 G01S 17/931 G01S 17/89 G05D 1/02
Abstract:
A method includes obtaining first user input identifying at least one LIDAR point in a set of LIDAR points associated with an object in an image, and obtaining second user input identifying the object in the image. The method may also include generating a constraint on a relationship between a LIDAR sensor used to capture the set of LIDAR points and a camera used to capture the image. The method may additionally include reducing a cost associated with the LIDAR point being inconsistent with the object in the image subject to the constraint.