System and method for processing motion-related sensor data with social mind-body games for health application
First Claim
Patent Images
1. A method for processing motion-related sensor data for health application, the method comprising:
- receiving motion-related signals from motion sensors located on different subjects, wherein the motion sensors comprise at least one accelerometer and at least one gyroscope integrated within a smartphone;
processing the received motion-related signals on a frame-by-frame basis to detect distinct short-duration exercise motions performed by the subjects, the distinct short-duration exercise motions including arm motions, leg motions and full body motions, each frame representing a predefined time interval shorter than the total duration of a distinct short-duration exercise motion;
for each frame, performing a plurality of signal transformations to extract features for activity classification;
for each frame, performing hierarchical decision making using feature subsets for a plurality of different categories of short-duration exercise motions to classify a number of motion categories of the plurality of different categories of short-duration exercise motions;
for each frame, classifying a detected distinct short-duration exercise motion into one of the number of motion categories;
for each frame, estimating performance parameters of the detected distinct short-duration exercise motion, wherein the performance parameters define the performance of the detected distinct short-duration exercise motion in the frame; and
creating a picture-based mind-body and reward-based game that is associated to a particular subject of the different subjects, wherein the picture-based mind-body and reward-based game includes at least one of the distinct short-duration exercise motions to be performed using the smartphone to play the picture-based mind-body and reward-based game.
0 Assignments
0 Petitions
Accused Products
Abstract
A system and method for processing motion-related sensor data for health application examines motion-related signal from a motion sensor located on a subject on a frame-by-frame basis to detect physical activities performed by the subject. For each frame, a detected activity is classified into a category of activities and performance parameters of the detected activity are estimated.
-
Citations
18 Claims
-
1. A method for processing motion-related sensor data for health application, the method comprising:
-
receiving motion-related signals from motion sensors located on different subjects, wherein the motion sensors comprise at least one accelerometer and at least one gyroscope integrated within a smartphone; processing the received motion-related signals on a frame-by-frame basis to detect distinct short-duration exercise motions performed by the subjects, the distinct short-duration exercise motions including arm motions, leg motions and full body motions, each frame representing a predefined time interval shorter than the total duration of a distinct short-duration exercise motion; for each frame, performing a plurality of signal transformations to extract features for activity classification; for each frame, performing hierarchical decision making using feature subsets for a plurality of different categories of short-duration exercise motions to classify a number of motion categories of the plurality of different categories of short-duration exercise motions; for each frame, classifying a detected distinct short-duration exercise motion into one of the number of motion categories; for each frame, estimating performance parameters of the detected distinct short-duration exercise motion, wherein the performance parameters define the performance of the detected distinct short-duration exercise motion in the frame; and creating a picture-based mind-body and reward-based game that is associated to a particular subject of the different subjects, wherein the picture-based mind-body and reward-based game includes at least one of the distinct short-duration exercise motions to be performed using the smartphone to play the picture-based mind-body and reward-based game. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A system for processing motion-related sensor data for health application, the system comprising:
-
computer memory; processor configured to; receive motion-related signals from motion sensors located on different subjects and to process the received motion-related signals on a frame-by-frame basis to detect distinct short-duration exercise motions performed by the subjects, the distinct short-duration exercise motions including arm motions, leg motions and full body motions, each frame representing a predefined time interval shorter than the total duration of a distinct short-duration exercise motion, wherein the motion sensors comprise at least one accelerometer and at least one gyroscope integrated within a smartphone; perform, for each frame, a plurality of signal transformations to extract features for activity classification; perform, for each frame, hierarchical decision making using feature subsets for a plurality of different categories of short-duration exercise motions to classify a number of motion categories of the plurality of different categories of short-duration exercise motions; classify, for each frame, a detected distinct short-duration exercise motion into one of the number of motion categories; estimate, for each frame, performance parameters of the detected distinct short-duration exercise motion, wherein the performance parameters define the performance of the detected distinct short-duration exercise motion in the frame; and create a picture-based mind-body and reward-based game that is associated to a particular subject of the different subjects, wherein the picture-based mind-body and reward-based game includes at least one of the distinct short-duration exercise motions to be performed using the smartphone to play the picture-based mind-body and reward-based game. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17, 18)
-
Specification