Detecting and tracking objects in images

• US 8,483,437 B2
• Filed: 03/20/2012
• Issued: 07/09/2013
• Est. Priority Date: 01/07/2005
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Shamaie, Atid
• Primary Examiner(s): PATEL, KANJIBHAI B
• Application Number:
  US13/425,080
• Publication Number:
  US 20120176344A1
• Time in Patent Office: 476 Days
• Field of Search: 382/103, 382/107, 382/159, 382/181, 382/305, 382/312, 345/156, 345/166, 345/173, 345/179, 345/594, 345/661, 348/169
• US Class Current: 382/103
• CPC Class Codes: G06F 18/2135 based on approximation criteria, e.g. principal component analysis
• CPC Class Codes: G06F 18/2413 based on distances to training or reference patterns
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/7715 Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
• CPC Class Codes: G06V 40/107 Static hand or arm
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113

Abstract

According to one disclosed method, coordinates in a multi-dimensional space are determined for an image point characterizing a particular object. An equation describing a model in the space is provided. The model is characteristic of a set of training images of one or more other objects. The coordinates are applied to the equation to determine a distance between the image point and the model. Based on the determined distance, a determination is made as to whether the particular object matches the one or more other objects. A set of training images may be received. A multi-dimensional space (e.g., eigenspace) may be determined based on the set of training images. A set of training points may be generated by projecting the set of training images into the multi-dimensional space. An equation describing a model in the multi-dimensional space that is characteristic of the set of training points may be determined.

Claims

1. A computer-implemented method, comprising:

detecting, using electromagnetic radiation, an object associated with a user;

determining whether the detected object is of a predetermined object type using a recognition model, wherein the recognition model is characteristic of multiple training images of the predetermined object type; and

generating an input to a computer application based on the detected object if it is determined that the detected object is of the predetermined object type.

2. The computer-implemented method of claim 1, wherein:

the electromagnetic radiation is projected onto a first side of a surface, and

the object is near a second side of the surface.

3. The computer-implemented method of claim 2, wherein the object is a finger of the user.

4. The computer-implemented method of claim 2, wherein detecting, using the electromagnetic radiation projected onto the first side of the surface, the object near the second side of the surface further comprises:

capturing an image.

5. The computer-implemented method of claim 1, wherein the recognition model is defined in multi-dimensional space by an equation.

6. The computer-implemented method of claim 1, wherein the recognition model comprises multiple training points in multi-dimensional space, wherein each of the training points corresponds to one or more training images.

7. A system, comprising:

a processing device, and

a computer-readable storage medium encoded with executable instructions that, when executed by the processing device, cause the processing device to;

detect, using electromagnetic radiation, an object associated with a user;

determine whether the detected object is of a predetermined object type using a recognition model, wherein the recognition model is characteristic of multiple training images of the predetermined object type; and

generate an input to a computer application based on the detected object if it is determined that the detected object is of the predetermined object type.

8. The system of claim 7, the system further comprising:

a surface, wherein;

the electromagnetic radiation is projected onto a first side of the surface, and

the object is near a second side of the surface.

9. The system of claim 8, wherein the object is a finger.

10. The system of claim 7, wherein the executable instructions that, when executed by the processing device, cause the processing device to detect, using the electromagnetic radiation projected onto the surface, the object near the surface further comprise executable instructions that cause the processing device to:

cause an image to be captured.

11. The system of claim 7, wherein the recognition model is defined in multi-dimensional space by an equation.

12. The system of claim 7, wherein the recognition model comprises multiple training points in multi-dimensional space, wherein each of the training points corresponds to one or more training images.

13. A non-transitory computer-readable storage medium encoded with executable instructions that, when executed by a processor, cause the processor to perform operations comprising:

detecting, using electromagnetic radiation, an object associated with a user;

determining whether the detected object is of a predetermined object type using a recognition model, wherein the recognition model is characteristic of multiple training images of the predetermined object type; and

generating an input to a computer application based on the detected object if it is determined that the detected object is of the predetermined object type.

14. The non-transitory computer-readable storage medium of claim 13, wherein:

the electromagnetic radiation is projected onto a first side of a surface, and

the object is near a second side of the surface.

15. The non-transitory computer-readable storage medium of claim 14, wherein the object is a finger.

16. The non-transitory computer-readable storage medium of claim 13, wherein the executable instructions that, when executed by the processor, cause the processor to perform operations comprising detecting, using the electromagnetic radiation projected onto the surface, the object near the surface further comprises:

capturing an image that comprises of a plurality of data elements.

17. The non-transitory computer-readable storage medium of claim 13, wherein the recognition model is defined in multi-dimensional space by an equation.

18. The non-transitory computer-readable storage medium of claim 13, wherein the recognition model comprises multiple training points in multi-dimensional space, wherein each of the training points corresponds to one or more training images of the multiple training images.

19. An apparatus, comprising:

means for detecting, using electromagnetic radiation, an object associated with a user;

means for determining whether the detected object is of a predetermined object type using a recognition model, wherein the recognition model is characteristic of multiple training images of the predetermined object type; and

means for generating an input to a computer application based on the detected object if it is determined that the detected object is of the predetermined object type.

20. The apparatus of claim 19, wherein the recognition model is defined in multi-dimensional space by an equation.

21. The apparatus of claim 19, wherein the recognition model comprises multiple training points in multi-dimensional space, wherein each of the training points corresponds to one or more training images.