IMAGING DEVICE FOR RECOGNITION AND METHOD OF CONTROLLING THE SAME

• US 20110285897A1
• Filed: 11/26/2010
• Published: 11/24/2011
• Est. Priority Date: 12/01/2009
• Status: Active Grant

• Current Assignee: Panasonic Intellectual Property Corporation of America (Panasonic Holdings Corporation)
• Original Assignee: Panasonic Intellectual Property Corporation of America (Panasonic Holdings Corporation)
• Inventors: Fujii, Takashi
• Granted Patent: US 8,860,875 B2
• Time in Patent Office: Days
• US Class Current: 348/345
• CPC Class Codes: G03B 15/00 Special procedures for taking photographs; Apparatus therefor
• CPC Class Codes: G03B 7/093 for control of exposure time
• CPC Class Codes: G06V 10/141 Control of illumination
• CPC Class Codes: G06V 40/166 using acquisition arrangements
• 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 23/675 comprising setting of focusing regions
• CPC Class Codes: H04N 23/73 by influencing the exposure time
• CPC Class Codes: H04N 23/75 by influencing optical camera components

Abstract

An imaging device for recognition (100) includes an image pickup unit (101) that sequentially generates a plurality of images by shooting an object, a face recognition unit (105) that recognizes, in each of the plurality of images, an object region in which the object is located in the image, a face tracking unit (106) that tracks the object region across the plurality of images, an area calculation unit (109) that calculates an area of the object region, and an exposure control unit (102) that sets a first exposure time for the image pickup unit (101) in the case where the area is smaller than a first threshold, and sets a second exposure time longer than the first exposure time in the case where the area is equal to or larger than the first threshold.

Claims

1. An imaging device for recognition including an image pickup unit that sequentially generates a plurality of images by shooting an object, an object recognition unit that recognizes, in each of the plurality of images, an object region in which the object is located in the image, and a tracking unit that tracks the object region across the plurality of images, said imaging device for recognition comprising:

an area calculation unit configured to calculate an area of the object region; and

an exposure control unit configured to set a first exposure time for the image pickup unit in the case where the area is smaller than a first threshold, and to set a second exposure time longer than the first exposure time in the case where the area is equal to or larger than the first threshold.

2. The imaging device for recognition according to claim 1, further comprising

a moving speed calculation unit configured to calculate a moving speed of the object region;

wherein said exposure control unit is further configured to set a third exposure time in the case where the moving speed is lower than a second threshold, and to set a fourth exposure time shorter than the third exposure time in the case where the moving speed is equal to or higher than the second threshold.

3. The imaging device for recognition according to claim 1, further comprising

a light amount calculation unit configured to calculate a light amount in the object region,

wherein said exposure control unit is configured to set a fifth exposure time for the image pickup unit in the case where a light amount for recognition proportional to the area and to the light amount is equal to or larger than a third threshold, and to set a sixth exposure time longer than the fifth exposure time in the case where the light amount for recognition is smaller than the third threshold.

4. The imaging device for recognition according to claim 1,

wherein said exposure control unit is configured to set the first exposure time in the case where a resolution for recognition proportional to the area and inversely proportional to a motion blur in the object region is lower than a fourth threshold, and to set the second exposure time in the case where the resolution for recognition is equal to or higher than the fourth threshold.

16. A semiconductor integrated circuit comprising the image pickup unit, the object recognition unit, said tracking unit, said area calculation unit, and said exposure control unit according to claim 1.

5. An imaging device for recognition including an image pickup unit that sequentially generates a plurality of images by shooting an object, an object recognition unit that recognizes, in each of the plurality of images, an object region in which the object is located in the image, and a tracking unit that tracks the object region across the plurality of images, said imaging device for recognition comprising:

an area calculation unit configured to calculate an area of the object region; and

a focusing position control unit configured to set a first focusing position for said imaging device for recognition in the case where the area is smaller than a first threshold, and to set a second focusing position farther from the object than is the first focusing position in the case where the area is equal to or larger than the first threshold.

6. The imaging device for recognition according to claim 5,

wherein said focusing position control unit is configured to set the first focusing position in the case where a resolution for recognition proportional to the area and inversely proportional to a focal blur in the object region is lower than a second threshold, and to set the second focusing position in the case where the resolution for recognition is equal to or higher than the second threshold.

17. A semiconductor integrated circuit comprising the image pickup unit, the object recognition unit, said tracking unit, said area calculation unit, and said focusing position control unit according to claim 5.

7. An imaging device for recognition including an image pickup unit that sequentially generates a plurality of images by shooting an object, an object recognition unit that recognizes, in each of the plurality of images, an object region in which the object is located in the image, and a tracking unit that tracks the object region across the plurality of images, said imaging device for recognition comprising:

an area calculation unit configured to calculate an area of the object region; and

a diaphragm control unit configured to set a first aperture value for said imaging device for recognition in the case where the area is smaller than a first threshold, and to set a second aperture value higher than the first aperture value in the case where the area is equal to or larger than the first threshold.

8. The imaging device for recognition according to claim 7, further comprising

a light amount calculation unit configured to calculate a light amount in the object region,

wherein said diaphragm control unit is further configured to set a third aperture value in the case where the light amount is smaller than a second threshold, and to set a fourth aperture value higher than the third aperture value in the case where the light amount is equal to or larger than the second threshold.

9. The imaging device for recognition according to claim 8,

wherein said diaphragm control unit is configured to set the first aperture value in the case where a light amount for recognition proportional to the area and to the light amount is smaller than a third threshold, and to set a sixth exposure time longer than the fifth exposure time in the case where the light amount for recognition is equal to or larger than the third threshold.

18. A semiconductor integrated circuit comprising the image pickup unit, the object recognition unit, the tracking unit, said area calculation unit, and said diaphragm control unit according to claim 7.

10. A method of controlling an imaging device for recognition including an image pickup unit that sequentially generates a plurality of images by shooting an object, said method comprising:

recognizing, in each of the plurality of images, an object region in which the object is located in the image;

tracking the object region across the plurality of images;

calculating an area of the object region; and

controlling an exposure of the image pickup unit so as to set a first exposure time in the case where the area is smaller than a first threshold, and to set a second exposure time longer than the first exposure time in the case where the area is equal to or larger than the first threshold.

13. A non-transitory computer-readable recording medium comprising a program configured to cause a computer to execute said method according to claim 10.

11. A method of controlling an imaging device for recognition including an image pickup unit that sequentially generates a plurality of images by shooting an object, said method comprising:

recognizing, in each of the plurality of images, an object region in which the object is located in the image;

tracking the object region across the plurality of images;

calculating an area of the object region; and

controlling a focusing position of said imaging device for recognition so as to set a first focusing position in the case where the area is smaller than a first threshold, and to set a second focusing position farther from the object than is the first focusing position in the case where the area is equal to or larger than the first threshold.

14. A non-transitory computer-readable recording medium comprising a program configured to cause a computer to execute said method according to claim 11.

12. A method of controlling an imaging device for recognition including an image pickup unit that sequentially generates a plurality of images by shooting an object, said method comprising:

recognizing, in each of the plurality of images, an object region in which the object is located in the image;

tracking the object region across the plurality of images;

calculating an area of the object region; and

controlling a diaphragm so as to set a first aperture value in the case where the area is smaller than a first threshold, and to set a second aperture value higher than the first aperture value in the case where the area is equal to or larger than the first threshold.

15. A non-transitory computer-readable recording medium comprising a program configured to cause a computer to execute said method according to claim 12.