Object detection and selection using gesture recognition

• US 8,379,134 B2
• Filed: 02/26/2010
• Issued: 02/19/2013
• Est. Priority Date: 02/26/2010
• Status: Active Grant

• Current Assignee: Malikie Innovations Limited (Key Patent Innovations Limited)
• Original Assignee: Blackberry Limited
• Inventors: Foster, Brett
• Primary Examiner(s): Perungavoor, Sath V
• Assistant Examiner(s): PARIKH, DAKSHESH D
• Application Number:
  US12/713,238
• Publication Number:
  US 20110211073A1
• Time in Patent Office: 1,089 Days
• Field of Search: None
• US Class Current: 348/345
• CPC Class Codes: H04N 23/11 for generating image signals from visible and infrared light wavelengths
• CPC Class Codes: H04N 23/61 based on recognised objects
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body
• CPC Class Codes: H04N 23/635 Region indicators; Field of view indicators
• CPC Class Codes: H04N 23/675 comprising setting of focusing regions
• CPC Class Codes: H04N 5/33 Transforming infrared radiation cameras or camera modules for generating image signals from infrared radiation H04N23/20; circuitry of SSIS for transforming infrared radiation into image signals H04N25/20

Abstract

Object detection and selection for use in a device having digital camera functionality is described. The mechanism detects the occurrence of a gesture by a pointing member in an image frame captured by an IR image sensor. The gesture is then recognized and an object pointed to is detected. The object detected is then selected as a result of the gesture recognition.

Claims

1. A method of object selection for use in a device having digital camera functionality, the method comprising:

detecting the occurrence of a gesture by a pointing member in an image frame captured by an image sensor;

recognizing the gesture and determining an object pointed to thereby; and

selecting the object as a result of the gesture recognition,

wherein gesture recognition comprises;

capturing a first image using infrared (IR) illumination turned on

capturing a second image using infrared (IR) illumination turned off;

calculating a third image as the difference between the first and second images;

performing a union find on the third image to identify one or more distinct objects located in the third image;

discarding from consideration those of the one or more distinct objects that are smaller than a threshold size;

discarding from consideration those of the one or more distinct objects that are not along an edge of the third image; and

determining vectors and points for each of the one or more distinct objects that has not been discarded from consideration.

2. The method in accordance with claim 1, further comprising performing an operation using the selected object.

3. The method in accordance with claim 1, wherein the object comprises a face or area of focus.

4. The method in accordance with claim 1, further comprising displaying an indication that the device is currently using the pointed to object.

5. The method in accordance with claim 1, further comprising maintaining the selection of the object after the pointing member has been removed from the image frame.

6. A method of identifying a desired area of focus for use in a device having digital camera functionality, the method comprising:

performing gesture recognition to detect a gesture by a pointing member in an image captured by an image sensor;

recognizing the gesture; and

determining the area pointed to by the recognized gesture,

wherein gesture recognition comprises;

capturing a first image using infrared (IR) illumination turned on;

capturing a second image using infrared (IR) illumination turned off;

calculating a third image as the difference between the first and second images;

performing a union find on the third image to identify one or more distinct objects located in the third image;

discarding from consideration those of the one or more distinct objects that are smaller than a threshold size;

discarding from consideration those of the one or more distinct objects that are not along an edge of the third image; and

determining vectors and points for each of the one or more distinct objects that has not been discarded from consideration.

7. The method in accordance with claim 6, further comprising:

changing the current focus of the camera to that of the pointed to area detected as a result of the gesture recognition.

8. The method in accordance with claim 6, further comprising displaying an indication that the current focus of the device is set to the pointed to area.

9. The method in accordance with claim 6, further comprising maintaining the current focus of the camera to that of the pointed to area after the pointing member has been removed from the image frame.

10. The method in accordance with claim 6, further comprising performing image filtering on the third image to yield a filtered third image so that the union is performed on the filtered third image.

11. The method in accordance with claim 6, wherein the image sensor comprises:

a visible light image sensor;

an infrared (IR) light image sensor;

a lens; and

a reflective IR filter mounted at a substantially 45 degrees between the visible and IR light image sensors, the reflective IR filter operative to pass visible light to the visible light image sensor while reflecting IR light onto the IR light image sensor.

12. A method of object selection for use in a device having digital camera functionality, the method comprising:

performing gesture recognition to detect the occurrence of a gesture by a pointing member in an image frame captured by an image sensor; and

identifying that the pointing member points to a particular object and selecting the object in response thereto,

wherein gesture recognition comprises;

capturing a first image using infrared (IR) illumination turned on;

capturing a second image using infrared (IR) illumination turned off;

calculating a third image as the difference between the first and second images;

performing a union find on the third image to identify one or more distinct objects located in the third image;

discarding from consideration those of the one or more distinct objects that are smaller than a threshold size;

discarding from consideration those of the one or more distinct objects that are not along an edge of the third image; and

determining vectors and points for each of the one or more distinct objects that has not been discarded from consideration.

13. The method in accordance with claim 12, further comprising:

performing an operation using the selected object.

14. The method in accordance with claim 13, wherein the operation comprises selecting and highlighting a face pointed to by the pointing member.

15. The method in accordance with claim 13, further comprising performing image filtering on the third image to yield a filtered third image so that the union is performed on the filtered third image.

16. The method in accordance with claim 12, further comprising displaying an indication that the device is currently using the pointed to object.

17. The method in accordance with claim 12, further comprising maintaining the selection of the object after the pointing member has been removed from the image frame.

18. The method in accordance with claim 12, further comprising performing image filtering on the third image to yield a filtered third image so that the union is performed on the filtered third image.

19. A mobile communications device, comprising:

a digital camera subsystem;

a cellular subsystem;

a memory;

a processor coupled to the one or more radio circuits and the memory, the processor operative;

to perform gesture recognition to detect the occurrence of a gesture by a pointing member in an image captured by an image sensor;

to recognize the gesture; and

to determine an area pointed to by the recognized gesture, wherein gesture recognition comprises;

capturing a first image using infrared (IR) illumination turned on;

capturing a second image using infrared (IR) illumination turned off;

calculating a third image as the difference between the first and second images;

performing a union find on the third image to identify one or more distinct objects located in the third image;

discarding from consideration those of the one or more distinct objects that are smaller than a threshold size;

discarding from consideration those of the one or more distinct objects that are not along an edge of the third image; and

determining vectors and points for each of the one or more distinct objects that has not been discarded from consideration.

20. The mobile communications device in accordance with claim 19, wherein the processor is further operative:

to change the current focus of the camera to that of the pointed to area detected as a result of the gesture recognition.

21. The mobile communications device in accordance with claim 19, wherein the image sensor comprises:

a visible light image sensor;

an infrared (IR) light image sensor;

a lens;

a reflective IR filter mounted at a substantially 45 degrees between the visible and IR light image sensors, the reflective IR filter operative to pass visible light to the visible light image sensor while reflecting IR light onto the IR light image sensor.

22. The mobile communications device in accordance with claim 19, further comprising performing image filtering on the third image to yield a filtered third image so that the union is performed on the filtered third image.