Method and system for monitoring and feed-backing on execution of physical exercise routines

1. A system for monitoring performance of an exercise routine, comprising:

a computing device;

a plurality of motion and position sensors configured to generate sensory information related to at least one movement of a user performing the exercise routine;

a database containing routine information representing at least one frame of exercise routine;

a training module configured to: track at least one movement of a user performing the exercise routine on an exercise device;

use at least one of: appearance of the exercise device, appearance of a feature of the said exercise device, or machine representation model of thereof;

for at least one of: separate from the sensory information at least appearance of the exercise device or a feature of it, calibration and/or adjustment of the said generated sensory information, assistance in the generation of machine representation of the user from the sensory information;

generate at least a machine representation model of the user from the sensory information.

2. The system of claim 1 , wherein the training module is further configured to

compare the generated machine representation model generated from the sensory information to routine information stored in a database to detect at least dissimilarities between the machine representation model generated from the sensory information and the routine information contained in the database.

3. The system of claim 2 , wherein the training module is further configured to provide feedback on at least one movement of a user performing the exercise routine; where the feedback is provided by at least one of: a sound generating device, a speech generating device, a display, a touch screen, a mobile device.

4. The system of claim 3 , further comprising

providing feedback, upon detection of dissimilarities in the performance of the physical exercise routine, with at least one of instructions on how to improve the execution, instructions on how to maintain a correct pace, indications as to how the routine execution should be corrected, step by step instructions on how to perform a certain routine; where the feedback is provided by at least one of: a sound generating device, a speech generating device, a display, a touch screen, a mobile device.

5. The system of claim 3 , implemented using a mobile device which comprises at least:

A tripod or a stand for holding the mobile device relative to at least an appearance of an exercise device and/or user;

a mobile device comprising at least:

a camera and/or image sensor and or a plurality of motion and position sensors;

a computing device;

a database;

at least one of: a sound generating device, a speech generating device, a display, a touch screen.

6. The system of claim 3 , where the training module is further configured to automatically changing based on the feedback, at least one of: difficulty level provided by the exercise device, resistance provided by the exercise device, tension provided by the exercise device.

7. The system of claim 3 , wherein the feedback includes at least one of: a rate of at least one movement, an optimal rate for the at least one movement, and the instructions on how to maintain a correct pace.

8. The system of claim 2 , wherein the exercise routine is any one of: weight lifting, Pilates, Yoga, running, dancing, resistance-based machine exercise, and a ball-game.

9. The system of claim 2 , where the training module is further configured to synchronize the sensory information and the routine information based on identifying edge frames including start and end positions of the physical exercise routine.

10. The system of claim 2 , where the training module is further configured to configure the body parts and/or joints and/or bones to track, based on the exercise performed and/or the stage in the exercise performed.

11. The system of claim 2 , where the training module is further configured to configure the viewing angles of the position and motion sensors, based on the exercise performed and/or the stage in the exercise performed.

12. The system of claim 2 , wherein the training module is further configured to track a rate of movements and to count a number of physical exercise routine repetitions.

13. The system of claim 2 , wherein the generated sensory information includes at least a number of movements.

14. The system of claim 13 , further comprising:

detecting dissimilarities or similarities with respect to the number of movements.

15. The method of claim 2 , wherein the exercise routine is any one of: weight lifting, Pilates, Yoga, running, dancing, resistance-based machine exercise, and a ball-game.

16. The system of claim 1 , wherein the plurality of motion and position sensors are mounted on an exercise device.

17. The system of claim 1 , wherein the sensory information is sent over a network to a server by the training module, wherein the server is configured to process sensory information from multiple users.

18. A method for identifying which exercise routine is performed, comprising:

receiving sensory information from a plurality of motion and position sensors configured to track at least one movement of a user performing the exercise routine on an exercise device;

use at least one of: appearance of the exercise device, appearance of a feature of the said exercise device, or machine representation model of thereof;

for at least one of: separating from the sensory information at least appearance of the exercise device or a feature of it, calibration and/or adjustment of the said generated sensory information, assistance in the generation of skeletal model and/or machine representation model of the user from the sensory information;

generating at least a skeletal model and/or machine representation model of the user from the sensory information;

comparing the generated skeletal model and/or machine representation model generated from the sensory information to routine information stored in a database to detect at least similarities between the skeletal model and/or machine representation model generated from the sensory information and the routine information;

grading the level of match between comparing the generated skeletal model and/or machine representation model generated from the sensory information to routine information stored in a database;

deciding which exercise routine is being performed based on the best grade match.

19. A system for monitoring performance of an exercise routine, comprising:

a computing device;

a plurality of motion and position sensors configured to generate sensory information related to at least one movement of a user performing the exercise routine;

a database containing routine information representing at least one frame of exercise routine, and information on the number of movements;

a training module configured to: track at least one movement of a user performing the exercise routine on an exercise device;

generate at least a machine representation model of the user from the sensory information;

compare the generated machine representation model generated from the sensory information to routine information stored in a database to detect at least dissimilarities or similarities with respect to the number of movements, between the machine representation model generated from the sensory information and the routine information contained in the database;

upon detecting that the number of movements of the user matches the number of movements in the routine information, providing an instruction to stop the physical exercise routine.

20. A method for generating a skeletal model of a user performing at least one movement of an exercise routine, comprising:

receiving, by a computing device, sensory information from a plurality of motion and position sensors configured to track at least one movement of a user performing the physical exercise routine on an exercise device;

using the information known about specific interest points on the exercise device to find the location of outer joints by intersection of the collection of pixels representing the user with possible location of these interest points found using curve fitting methods;

use of the said outer joints as anchor points for casting skeletal model from routine information stored in a database;

comparing casted skeletal model to the point cloud representing the user generated from the sensory information to detect at least similarities between the casted skeletal model and the point cloud representing the user generated from the sensory information to detect at least similarities between the skeletal model and point cloud generated from the sensory information and the routine information;

grading the level of match between the casted skeletal model and the point cloud generated from the sensory information to routine information stored in a database;

deciding which casted skeletal model fits the point cloud representing the user based on the best grade match.