Here Global B.v.

Niranjan Kotha

David Johnston Lawlor

Anish Mittal

Jeff Connell

Zhanwei Chen

A method, apparatus and computer program product are provided for establishing correspondences between images using through generation of a translation between the different perspectives. Methods may include: receiving first sensor data from a first image sensor, where the first sensor data includes a first image of an environment captured from a first perspective; receiving second sensor data from a second image sensor of a second image of the environment captured from a second perspective; identifying image correspondence points between the first sensor data and the second sensor data; computing pairwise vectors between corresponding pairs of first projected points of the first sensor data and second projected points of the second sensor data; clustering the pairwise vectors according to magnitude and orientation; and generating a translation vector from clusters of pairwise vectors, where the translation vector represents a shift of the second image sensor data to correspond to ground truth data.

Method, apparatus, and computer program product for point-to-point translation between images

An approach is provided for determining the quality of camera pose data. The approach, for example, involves identifying camera pose data for a camera used to capture an image. The approach further involves processing the image to determine a pixel location of features visible in the image, wherein each feature has a known physical location (e.g., obtained using survey techniques or equivalent). The approach further involves determining a camera physical location of the camera based on the camera pose data. The approach further involves determining an physical location of the image plane based on the camera pose data and/or camera parameters (e.g., intrinsic camera parameters). The approach further involves projecting a ray from the camera physical location thorough the image plane physical location corresponding to the pixel location determined for each feature, and computing a minimum distance between the projected ray and the known physical location of each feature. The approach further involves providing an aggregation of the minimum distances as an output indicating a quality of the camera pose data.

Growing community of inventors

Chicago, IL, United States of America

Niranjan Kotha