Optimized object scanning using sensor fusion

A method of operating an image capture device to capture two-dimensional images of an object in a physical environment, the method comprising:

• capturing two-dimensional images of the object with the image capture device from a plurality of vantage points;
• using at least one sensor associated with the image capture device to detect information about one or more of a position, motion, or orientation of the image capture device in the physical environment at one or more of the vantage points;
• determining object poses from the two-dimensional images;
• and
• using the detected information about the image capture device at the one or more of the vantage points for selecting object poses to transform object features in the captured two-dimensional images into a three-dimensional computational model of the object.

A device operative to perform object scanning through application of sensor fusion, comprising:

• an image sensor operative to capture two-dimensional images of a scene in a three-dimensional space;
• at least one tracking sensor operative to detect supplemental information comprising one or more of a position, motion, or orientation of the device within the three-dimensional space;
• one or more processors;
• a data storage system, operative to store images from the image sensor, and to store the supplemental information from the tracking sensor;
• and
• a machine-readable memory device operative to store instructions, which when executed, cause the one or more processors to
• operate the at least one tracking sensor to detect the supplemental information for the device within the three-dimensional space,
• apply sensor fusion by which the detected information from the tracking sensor is utilized to operate the image sensor to capture two-dimensional images of the scene at a selected one of position, motion, or orientation of the device within the three-dimensional space.

A machine-readable memory device operative to store instructions which, when executed by one or more processors disposed in an electronic device, cause the electronic device to:

• capture a plurality of images of an object from a respective plurality of vantage points using a camera disposed in the electronic device that is configured to capture two-dimensional images with respect to world coordinates that describe at least one of position, motion, or orientation of the camera;
• generate world tracking metadata for the electronic device at one or more of the vantage points;
• perform object pose optimization for transforming captured images into a three-dimensional model of the object using the world tracking metadata to provide an initial point of optimization;
• and
• enable construction of the three-dimensional model of the object using the optimized object poses.