Video camera system which automatically follows subject changes

• US 5,812,193 A
• Filed: 12/11/1996
• Issued: 09/22/1998
• Est. Priority Date: 11/07/1992
• Status: Expired due to Term

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Sasaki, Takayuki, Tomitaka, Tadafusa
• Primary Examiner(s): Faile, Andrew
• Assistant Examiner(s): Ho, Tuan V.
• Application Number:
  US08/763,426
• Time in Patent Office: 650 Days
• Field of Search: 348/207, 348/208, 348/143, 348/155, 348/169, 348/170, 348/171, 348/172, 348/362, 348/364, 348/649, 348/652, 348/700, 348/703, 348/345, 348/352, 348/347, 348/369, 348/14 , 348/15, 382/173, 382/115, 382/191
• US Class Current: 348/369
• CPC Class Codes: G01S 3/7864 T.V. type tracking systems
• CPC Class Codes: H04N 23/61 based on recognised objects
• CPC Class Codes: H04N 23/695 Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects

Abstract

A video camera system can suitably track a moving object without influence of other objects outside the desired image. Detection feature patterns are formed after brightness and hue frequency feature data are obtained on the basis of image information of the detection measurement frame. The position of detection measurement frame having a feature pattern with the largest similarity to the standard feature pattern obtained from the standard measurement frame is determined. An imaging condition of a television camera is controlled on the basis of the position information of the detection measurement frame in order to attain a video camera system enabling to suitably track the object motion. Further, a video camera system can obtain a face image of constantly a same size with a simple construction. An area of the face image on the display plane is detected as the detected face area, and by comparing this with a standard face area, zooming-processing is performed such that the difference becomes 0. Thus, it is unnecessary to use the method of a distance sensor, etc., and a video camera system with a simple construction can be obtained.

Claims

1. A video signal tracking method comprising:

an input image forming step for forming image data of an input image expressing basic model of a video signal;

a target area extracting step for extracting a target area from said image data of input image, said image data being divided into a plurality of unit areas, and a first color area prospective and a second color area prospective, wherein said target area extracting step includes absorbing discontinuous areas when extracting said first color area prospective and said second color area prospective;

a detecting target size calculating step for calculating the size of said extracted target area;

a deviation detecting step for obtaining the deviation between the size of a detecting target obtained in a reference detecting target size calculating step and the size of a reference target obtained in said reference target size memory step; and

an input image zooming step for zooming the size of input image formed onto said input image forming step corresponding to the deviation output of said deviation detecting step, in order that said deviation become nearly 0, wherein the image data of the input image the sizes of which are corresponding to up-shot, bust shot and/or full body shot as said target model is formed in said input image forming step.

2. A video signal tracking method according to claim 1, wherein;

said target area includes a first color area and a skin color area.

3. A video signal tracking method according to claim 2, wherein;

the reference size of the target of selected shot is drawn out from target size table which is provided corresponding to said plurality of the steps, and then is calculated it.

4. A video signal tracking method according to claim 3 wherein;

said reference target size is compared with detected present object size, and zooming means is controlled so that the difference obtained from comparing result becomes nearly 0.

5. A video signal tracking method according to claim 4, wherein;

when absorbing said discontinuous areas the image information of designated unit area is absorbed with a first color prospective unit area, if there is said first color prospective area being contiguous to an unit area centering around said each area.

6. A video signal tracking method according to claim 4, wherein;

when absorbing said discontinuous areas, the image information of designated unit area is absorbed with a second color prospective unit area, if there is said second color prospective area being contiguous to an unit area with centering around said each unit area.

7. A video signal tracking method according to claim 4, wherein;

when extracting said first color prospective area and said second prospective color area, discontinuous areas are absorbed each other, and then a first color area and a second color area are combining.

8. A video signal tracking method according to claim 7, wherein;

when combining first color area and second color area, the image information of designated area is combined with a first group of color unit area, if there is a first color unit area being contiguous to an unit area centering around said each area.

9. A video signal tracking method according to claim 8, wherein;

when combining first color area and second color area, the image information of the designated unit area and an image information of an unit area being contiguous to second prospective color unit area are combined with said second prospective unit area, if there is said second color prospective unit area being contiguous to the designated unit area.

10. A video signal tracking method according to claim 7, wherein;

the size of first color area and second color area are further calculated.

11. A video signal tracking method according to claim 10, wherein;

said first color is determined hair color, and said second color is determined skin color.

12. A video camera system comprising:

a group of lenses for focusing lights from an object;

an imaging element for converting the lights from said lens group into an electric signal;

an analog-to-digital converter for converting an analog imaging signal from said imaging element into a digital signal;

input image forming means for forming an image data of an input picture expressing a basic model of the object analog-digital converted;

target area extracting means for extracting a target area from said image data of input image, said image data being divided into a plurality of unit areas, and a first color area prospective and a second color area prospective are extracted, such that when extracting said first color area prospective and said second color area prospective discontinuous areas are absorbed;

detecting target size calculating means for calculating the size of said extracted target area;

difference detecting means for obtaining difference between the size of reference target obtained from a reference target size memory means and the size of detecting target obtained from reference detecting target size calculating means; and

input image zooming means for zooming the size of input image formed onto said input image forming means corresponding to the difference output of said difference detecting means so that said difference becomes nearly 0, wherein said input image forming means selectively forms the input image data the size of which is corresponding to up-shot, bust shot and/or full body shot as said target model.

13. A video camera system according to claim 12, wherein;

said target area includes a first color area and a skin color area.

14. A video camera system according to claim 13, wherein:

the reference size of the target of selected shot is drawn out from target size table which is provided corresponding to said plurality of the shots, and then is calculated.

15. A video camera system according to claim 14, wherein;

said reference target size is compared with detected the present object size, and zooming means is controlled, so that the difference obtained from comparing result becomes nearly 0.

16. A video camera system according to claim 15, wherein;

when absorbing discontinuous areas, the image information of designated unit area is absorbed with a first color prospective unit area, if there is said first color prospective area being contiguous to an unit area centering around said each area.

17. A video camera system according to claim 15, wherein;

when absorbing said discontinuous areas, the image information of designated unit area is absorbed with a second color prospective unit area, if there is said second color prospective area being contiguous to an unit area centering around said each unit area.

18. A video camera system according to claim 15, wherein;

when extracting said first color prospective area and said second prospective color area, discontinuous areas is absorbed, and then a first color area and a second color area are combined.

19. A video camera system according to claim 18, wherein;

when combining first color area and second color area, the image information of designated area is combined with a first group of color unit area, if there is a first color unit area being contiguous to an unit area centering around said each area.

20. A video camera system according to claim 19, wherein;

when combining said first color area and second color area, the image information of the neighboring area having the image information of the designated unit area and an image information of an unit area being contiguous to second prospective unit area combined with said second prospective color small area, if there is a second color prospective unit area being contiguous to the designated unit area.

21. A video camera system according to claim 19, wherein;

the size of first color area and second color area combined each other are further calculated.

22. A video camera system according to claim 21, wherein;

said first color is determined hair color, and said second color is determined skin color.