Visual and physical motion sensing for three-dimensional motion capture

摘要

A system includes a visual data collector for collecting visual information from an image of one or more features of an object. The system also includes a physical data collector for collecting sensor information provided by at one or more sensors attached to the object. The system also includes a computer system that includes a motion data combiner for combining the visual information the sensor information. The motion data combiner is configured to determine the position of a representation of one or more of the feature in a virtual representation of the object from the combined visual information and sensor information. Various types of virtual representations may be provided from the combined information, for example, one or more poses (e.g., position and orientation) of the object may be represented.

主权项

1. A computer-implemented method comprising:
receiving first visual information for an object including information for a plurality of visual markers associated with the object,the first visual information being obtained from a a first image of the object, wherein the object comprises at least a first feature and a second feature, wherein each feature is associated with a visual marker from the plurality of visual markers, and wherein the object comprises at least one inertial sensor; receiving first position-related information corresponding to the object, the first position-related information being wirelessly transmitted from the at least one inertial sensor of the object; wherein the first position-related information is synchronized with the first visual information; generating a first virtual pose for the object using the first position-related information transmitted wirelessly from the at least one inertial sensor of the object and the first visual information for the object, wherein the first virtual pose of the object comprises a first position of the first feature and a first position of the second feature in a virtual representation of the object, and wherein the first position of the first feature and the first position of the second feature are based on the first position-related information transmitted wirelessly from the at least one inertial sensor of the object and the first visual information for the object; receiving second visual information for the object, the second visual information being obtained from a second image of the object, wherein the second image is generated after the first image is generated; receiving second position-related information corresponding to the object, the second position-related information being wirelessly transmitted from the at least one inertial sensor of the object; and generating a second virtual pose for the object using the second position-related information and the second visual information for the object, wherein the second virtual pose of the object comprises a second position of the first feature and a second position of the second feature in the virtual representation of the object.