System and method for producing computer control signals from breath attributes
AssigneeXerox Corporation
InventorsMichael R. Furst, Edgar A. Bernal, Robert P. Loce, Lalit K. Mestha
Life of this patent
Estimating the term…
Abstract
A method for computing output using a non-contact (invisible) input signal includes acquiring depth data of a scene captured by a depth-capable sensor. The method includes generating a temporal series of depth maps corresponding to the depth data. The method includes generating at least one volumetric attribute from the depth data. The method includes generating an output based on the volumetric attribute to control actions.
Claims22
A system for computing output using a non-contact input signal, the system comprising:
- a computer programmed to perform a method for generating an input control signal and including the operations of:
- acquiring depth data of a scene captured by a depth-capable sensor;
- generating a temporal series of depth maps corresponding to the depth data;
- generating at least one volumetric attribute based on the depth data determined from the series of depth maps, the generating including:
- for each depth map, generating a binary image of a subject detected in the each depth map,
- segmenting the binary image into regions,
- comparing pixels corresponding to a select region of interest across the temporal series of depth maps to determine a change in a shape of the region,
- associating the change in the shape with a volumetric attribute;
- determining one of an optimal pose of the subject and an optimal orientation of the subject using a breath analyzer in communication with the computer;
- providing the one of the pose and orientation to an output device as an output, and providing a pose recommendation feedback for improving a quality of the depth data;
- and generating an input control signal based on the volumetric attribute to enable the subject to interact with an output device.
A method for computing output using a non-contact input signal, the method including:
- acquiring depth data of a scene captured by a depth-capable sensor;
- generating a temporal series of depth maps corresponding to the depth data;
- generating at least one volumetric attribute based on the depth data determined from the series of depth maps, the generating including:
- for each depth map, generating a binary image of a subject detected in the each depth map,
- segmenting the binary image into regions,
- comparing pixels corresponding to a select region of interest across the temporal series of depth maps to determine a change in a shape of the region,
- associating the change in the shape with a volumetric attribute;
- determining one of an optimal pose of the subject and an optimal orientation of the subject using a breath analyzer in communication with the computer;
- providing the one of the pose and orientation to an output device as an output, and providing a pose recommendation feedback for improving a quality of the depth data;
- and generating an input control signal based on the volumetric attribute to enable the subject to interact with an output device.
Dependencies are inferred from the claim text.