Microsoft Technology Licensing, LLC

Joseph Michael Degol

Sudipta Narayan Sinha

Victor Manuel Fragoso Rojas

Yashar Bahman

Ondrej Miksik

Jae Yong Lee

Brent Armen Ellwein

Tien Do

In various embodiments there is a method for camera localization within a scene. An image of a scene captured by the camera is input to a machine learning model, which has been trained for the particular scene to detect a plurality of 3D scene landmarks. The 3D scene landmarks are pre-specified in a pre-built map of the scene. The machine learning model outputs a plurality of predictions, each prediction comprising: either a 2D location in the image which is predicted to depict one of the 3D scene landmarks, or a 3D bearing vector, being a vector originating at the camera and pointing towards a predicted 3D location of one of the 3D scene landmarks. Using the predictions, an estimate of a position and orientation of the camera in the pre-built map of the scene is computed.

Camera localization

One example provides a computing system comprising a storage machine storing instructions executable by a logic machine to extract features from a source and target images to form source and target feature maps, form a correlation map comprising a plurality of similarity scores, form an initial correspondence map comprising initial mappings between pixels of the source feature map and corresponding pixels of the target feature map, refine the initial correspondence map by, for each of one or more pixels of the source feature map, for each of a plurality of candidate correspondences, inputting a four-dimensional patch into a trained scoring function, the trained scoring function being configured to output a correctness score, and selecting a refined correspondence based at least upon the correctness scores, and output a refined correspondence map comprising a refined correspondence for each of the one or more pixels of the source feature map.

Pixel correspondence via patch-based neighborhood consensus

A computer implemented method includes capturing images of an environment via a camera, detecting image features in the environment based on the captured images, the image features including at least one web feature derived from a fiducial web formed of a collection of non-repeating intersecting lines applied to an object in the environment, and estimating a camera pose based on the detected image features including the at least one web feature.

Fiducial web for computer vision

Growing community of inventors

Seattle, WA, United States of America

Joseph Michael Degol