Method and apparatus for determining camera location information and/or camera pose information according to a global coordinate system

摘要

An approach is provided for processing and/or facilitating a processing of one or more images to determine camera location information, camera pose information, or a combination thereof associated with at least one camera capturing the one or more images, wherein the camera location information, the camera pose information, or a combination thereof is represented according to a global coordinate system. The approach involves causing, at least in part, an association of the camera location information, the camera pose information, or a combination thereof with the one or more images as meta-data information.

主权项

1. A method comprising:
processing one or more images to determine camera location information and camera pose information associated with at least one camera capturing the one or more images, wherein the camera location information and the camera pose information are represented according to an Earth Centered, Earth Fixed (ECEF) 3D Cartesian coordinate system; processing the one or more images to determine a local point cloud of one or more objects depicted in the one or more images, wherein the local point cloud is represented according to a local 3D Cartesian coordinate system; matching the local three-dimensional point cloud represented according to the local 3D Cartesian coordinate system to one or more reference point clouds represented according to the ECEF 3D Cartesian coordinate system to determine the camera location information and the camera pose information according to the ECEF 3D Cartesian coordinate system; associating the camera location information and the camera pose information represented according to the ECEF Cartesian coordinate system with the one or more images as meta-data information to form an augmented content; and rendering the augmented content, based on the associated camera location information and the camera pose information,
wherein the rendering of the augmented content is more accurate than a related rendering based upon rough sensor data of the one or more images.