Determining the relative locations of multiple motion-tracking devices
The technology disclosed relates to coordinating motion-capture of a hand by a network of motion-capture sensors having overlapping fields of view. In particular, it relates to designating a first sensor among three or more motion-capture sensors as having a master frame of reference, observing motion of a hand as it passes through overlapping fields of view of the respective motion-capture sensors, synchronizing capture of images of the hand within the overlapping fields of view by pairs of the motion-capture devices, and using the pairs of the hand images captured by the synchronized motion-capture devices to automatically calibrate the motion-capture sensors to the master frame of reference frame.
1. A method of coordinating three-dimensional (3D) motion-capture, the method comprising:
designating a first 3D motion-capture sensor among two or more 3D motion-capture sensors as having a master frame of reference, each respective 3D motion-capture sensor of the two or more 3D motion-capture sensors: (i) having networked connectivity to other 3D motion-capture sensors of the two or more 3D motion-capture sensors; and (ii) monitoring a portion of a monitored space falling within a field of view of the respective 3D motion-capture sensor;
observing, by the first 3D motion-capture sensor and at least one other 3D motion-capture sensor of the two or more 3D motion-capture sensors, 3D motion of a hand in the monitored space as the hand passes through at least two overlapping fields of view of the first 3D motion-capture sensor and the at least one other 3D motion-capture sensor;
utilizing the networked connectivity between the first 3D motion-capture sensor and the at least one other 3D motion-capture sensor to synchronize a capture of at least one pair of images of the hand within the at least two overlapping fields of view;
calibrating the at least one other 3D motion-capture sensor to the master frame of reference of the first 3D motion-capture sensor independently of a pre-determined landmark location of a surrounding environment; and
in response to a loss of connectivity with the first 3D motion-capture sensor, designating a second 3D motion-capture sensor as a new master sensor having the master frame of reference.
2. The method of claim 1 , further including calibrating a third 3D motion-capture sensor to the master frame of reference of the second 3D motion-capture sensor independently of a pre-determined landmark location of the surrounding environment.
3. The method of claim 1 , further including recognizing a gesture of the hand based on a motion of a generated 3D model of the hand generated by capturing the pair of images from calibrated 3D motion-capture sensors.
4. The method of claim 1 , wherein the calibrating is performed using one or more rigid geometric coordinate transformations between the new master sensor and the at least one other 3D motion-capture sensor calculated based on a determined shift between corresponding points on the hand in the captured at least one pair of images.
5. The method of claim 4 , wherein the one or more rigid geometric coordinate transformations include at least one affine transformation.
6. The method of claim 4 , wherein the calculating of the one or more rigid geometric coordinate transformations includes generating translation or rotation parameters that describe geometric shifts relating any two images of the hand captured by the new master sensor and the at least one other 3D motion-capture sensor.
7. The method of claim 1 , wherein one of the two or more 3D motion-capture sensors is configured to be installed into a head mounted display.
8. The method of claim 1 , further comprising the at least one other 3D motion-capture sensor supplying an image to the new master sensor for the calibrating of the at least one other 3D motion-capture sensor.
9. The method of claim 1 , further comprising analyzing an image from the new master sensor and the image supplied from the at least one other 3D motion-capture sensor through a sensor interface to perform the calibrating of the at least one other 3D motion-capture sensor.
10. A non-transitory computer readable storage medium impressed with computer program instructions to coordinate three-dimensional (3D) motion-capture, the instructions, when executed on a processor, implement a method comprising:
designating a first 3D motion-capture sensor among two or more 3D motion-capture sensors as being a master sensor having a master frame of reference, each respective 3D motion-capture sensor of the two or more 3D motion-capture sensors: (i) having networked connectivity to other 3D motion-capture sensors of the two or more 3D motion-capture sensors; and (ii) monitoring a portion of a monitored space falling within a field of view of the respective 3D motion-capture sensor;
observing, by the first 3D motion-capture sensor and at least one other 3D motion-capture sensor of the two or more 3D motion-capture sensors, 3D motion of a hand in the monitored space as the hand passes through at least two overlapping fields of view of the first 3D motion-capture sensor and the at least one other 3D motion-capture sensor;
utilizing connectivity between the first 3D motion-capture sensor and the at least one other 3D motion-capture sensor to synchronize a capture of at least one pair of images of the hand within the at least two overlapping fields of view;
calibrating the at least one other 3D motion-capture sensor to the master frame of reference of the first 3D motion-capture sensor independently of a pre-determined landmark location of a surrounding environment; and
in response to a loss of connectivity with the first 3D motion-capture sensor, designating a second 3D motion-capture sensor as a new master sensor having the master frame of reference.
11. The non-transitory computer readable storage medium of claim 10 , wherein the method further includes calibrating a third 3D motion-capture sensor to the master frame of reference of the second 3D motion-capture sensor independently of a pre-determined landmark location of the surrounding environment.
12. The non-transitory computer readable storage medium of claim 10 , wherein the calibrating is performed using one or more rigid geometric coordinate transformations between the master sensor and the at least one other 3D motion-capture sensor calculated based on a determined shift between corresponding points on the hand in the captured at least one pair of images.
13. The non-transitory computer readable storage medium of claim 12 , wherein the one or more rigid geometric coordinate transformations are calculated by generating translation or rotation parameters that describe geometric shifts relating any two images of the hand captured by the first and second 3D motion-capture sensors.
14. The non-transitory computer readable storage medium of claim 12 , wherein the one or more rigid geometric coordinate transformations include at least one affine transformation.
15. The non-transitory computer readable storage medium of claim 10 , wherein one of the two or more 3D motion-capture sensors is configured to be installed into a head mounted display.
16. The non-transitory computer readable storage medium of claim 10 , wherein the method further includes the at least one other 3D motion-capture sensor supplying an image to the master sensor for the calibrating of the at least one other 3D motion-capture sensor.
17. The non-transitory computer readable storage medium of claim 16 , wherein the method further includes analyzing an image from the master sensor and the image supplied from the at least one other 3D motion-capture sensor through a sensor interface to perform the calibrating of the at least one other 3D motion-capture sensor.
18. A motion capture sensory system for coordinating three-dimensional (3D) motion-capture, the motion capture sensory system including:
two or more 3D motion-capture sensors, each respective 3D motion-capture sensor monitoring a portion of a monitored space falling within a field of view of the respective 3D motion-capture sensor, wherein each respective 3D motion-capture sensor (i) has networked connectivity to other 3D motion-capture sensors of the two or more 3D motion-capture sensors; and (ii) monitors a portion of a monitored space falling within a field of view of the respective 3D motion-capture sensor,
wherein the two or more 3D motion-capture sensors are configured to perform:
designating a first 3D motion-capture sensor among two 3D motion-capture sensors as being a master sensor having a master frame of reference, the master frame of reference being for at least one geometric coordinate of a hand;
observing, by the first 3D motion-capture sensor and at least one other 3D motion-capture sensor of the two or more 3D motion-capture sensors, 3D motion of the hand in the monitored space as the hand passes through at least two overlapping fields of view of the first 3D motion-capture sensor and the at least one other 3D motion-capture sensor;
utilizing connectivity between the first 3D motion-capture sensor and the at least one other 3D motion-capture sensor to synchronize a capture of at least one pair of images of the hand within the at least two overlapping fields of view;
calibrating the first 3D motion-capture sensor to the master frame of reference of the first 3D motion-capture sensor independently of a pre-determined landmark location of a surrounding environment; and
in response to a loss of connectivity with the first 3D motion-capture sensor, designating a second 3D-motion capture sensor as a new master sensor having the master frame of reference.