Human face tracking system

• US 5,430,809 A
• Filed: 07/07/1993
• Issued: 07/04/1995
• Est. Priority Date: 07/10/1992
• Status: Expired due to Term

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Tomitaka, Tadafusa
• Primary Examiner(s): Boudreau, Leo H.
• Assistant Examiner(s): CAMMARATA, MICHAEL
• Application Number:
  US08/086,868
• Time in Patent Office: 727 Days
• Field of Search: 382/17, 382/2, 382/1, 382/9, 382/28, 382/18, 382/48, 348/169, 348/172, 348/77
• US Class Current: 382/173
• CPC Class Codes: G01S 3/7864 T.V. type tracking systems

Abstract

A video camera system with autonomous target tracking sets a measuring frame on an object with high accuracy using a hue signal and a brightness signal without being affected by intensity and direction of the light source. A display screen is divided into divided areas and for each divided area, a lightness divided area in which the values of the brightness signal are within prescribed ranges of luminance and a skin color divided area in which the values of the hue signal are within prescribed ranges corresponding to skin color are extracted. Based on the extraction result, the position of the object on the screen determined and the measuring frame is set without being affected by intensity and direction of the light source. Thereafter, the object is continuously centered within the measuring frame.

Claims

1. A video camera system comprising:

a lens block unit;

area dividing means for dividing a display image of image output signals outputted from said lens block unit into divided areas of prescribed dimensions;

skin color area extracting means for extracting skin color divided areas wherein values of a hue signal are within prescribed ranges corresponding to skin color;

lightness area extracting means for extracting lightness divided areas wherein values of a brightness signal are within prescribed ranges of luminance;

absorbing means for forming skin color divided area groups and lightness divided area groups by absorbing blank divided areas around said skin color divided areas and said lightness divided areas, respectively;

adjacent divided area group extracting means for extracting a set of a skin color divided area group and a lightness divided area group which are adjacent to each other from said skin color divided area groups and lightness divided area groups, respectively; and

measuring frame setting means for setting a measuring frame in order that said set of said skin color divided area group and said lightness divided area group are encompassed by said measuring frame and continuously centering said measuring frame around said set of said skin color divided area group and said lightness divided area group.

2. A video camera system of claim 1, wherein:

said measuring frame setting means sets said measuring frame by moving said measuring frame on a display screen depending upon a result of said extracting operation by said adjacent divided area group extracting means.

3. A video camera system of claim 1, wherein:

said measuring frame setting means includes means for setting said measuring frame by panning and/or tilting said lens block unit depending upon a result of said extracting operation by said adjacent divided area group extracting means.

4. A video camera system comprising:

a lens block unit;

area dividing means for dividing a display image of image output signals outputted from said lens block unit into divided areas of prescribed dimensions;

skin color area extracting means for extracting skin color divided areas wherein values of a hue signal are within prescribed ranges corresponding to skin color;

hair area extracting means for extracting hair divided areas wherein values of a brightness signal are within prescribed ranges corresponding to hair lightness in all of said divided areas;

absorbing means for forming skin color divided area groups and hair divided area groups by absorbing blank divided areas around said skin color divided areas and said hair divided areas, respectively;

adjacent divided area extracting means for extracting a set of a skin color divided area group and a hair divided area group which are adjacent to each other from said skin color divided area groups and said hair divided area groups, respectively;

face defining means for judging whether said set of said skin color divided area group and said hair divided area group constitutes a face area on a condition that said hair divided area group is adjacent to an upper part of said skin color divided area group and said hair divided area group extracted by said adjacent divided area extracting means; and

measuring frame setting for setting a measuring frame in order that said face area is encompassed by said measuring frame and continuously centering said measuring frame around said face area.

5. A video camera system of claim 4, wherein:

said measuring frame setting means includes means for setting said measuring frame by panning and/or tilting said lens block unit in order that a centroid of said face area coincides with a center of said display screen.

6. A video camera system comprising:

a lens block unit;

area dividing means for dividing a display image of image output signals outputted from said lens block unit into divided areas of prescribed dimensions;

skin color area extracting means for extracting skin color divided area wherein values of a hue signal are within prescribed ranges corresponding to skin color;

hair area extracting means for extracting hair divided areas wherein values of a brightness signal are within prescribed ranges corresponding to lightness of hair;

absorbing means for forming skin color divided area groups and hair divided area groups by absorbing blank divided areas around said skin color divided areas and said hair divided areas, respectively;

adjacent divided area group extracting means for extracting a set of a skin color divided area group and a hair divided area group which are adjacent to each other from said skin color divided area groups and hair divided area groups, respectively;

face defining means for judging whether said set of said hair divided area group and said skin color divided area group constitutes a face area on a condition that respective sizes of said hair divided area group and said skin color divided area group are calculated, a ratio of said sizes of said hair divided area group and said skin color divided area group is within a prescribed range, and said hair divided area group is adjacent to an upper side of said skin color divided area group; and

measuring frame setting means for setting a measuring frame in order that said face area is encompassed by said measuring frame and continuously centering said measuring frame around said face area.

7. An autonomous target tracking method for autonomously tracking an object to be displayed on a display screen based on imaging output signals outputted from a lens block unit, said autonomous target tracking method comprising steps of:

dividing a display image of said image output signals into divided areas of prescribed dimensions;

extracting skin color divided areas wherein values of a hue signal are within prescribed ranges corresponding to skin color;

extracting lightness divided areas wherein values of a brightness signal are within prescribed ranges of luminance;

absorbing blank divided areas around said skin color divided areas and said lightness divided areas to form skin color divided area groups and lightness divided area groups, respectively;

extracting a set of a skin color divided area group and a lightness divided area group which are adjacent to each other from said skin color divided area groups and lightness divided area groups, respectively; and

setting a measuring frame in order that said set of said skin color divided area group and said lightness divided area group can be encompassed by said measuring frame and continuously centering said measuring frame around said set of said skin color divided area group and said lightness divided area group.

8. An autonomous target tracking method for autonomously tracking an object to be displayed on a display screen based on imaging output signals outputted from a lens block unit, said autonomous target tracking method comprising steps of:

dividing a display image of said image output signals into divided areas of prescribed dimensions;

extracting skin color divided areas wherein values of a the hue signal are within prescribed ranges corresponding to skin color;

extracting hair divided areas wherein values of a brightness signal are within prescribed ranges corresponding to hair lightness;

absorbing blank divided areas around said skin color divided areas and said hair divided areas to form skin color divided area groups and hair divided area groups, respectively;

extracting a set of a skin color divided area group and a hair divided area group which are adjacent to each other from said skin color divided area groups and said hair divided area groups, respectively;

judging whether said set of said skin color divided area group and said hair divided area group constitutes a face area on a condition that said hair divided area group is adjacent to an upper part of said skin color divided area group in said set of said skin color divided area group and said hair divided area group; and

setting a measuring frame in order that said face area is encompassed by said measuring frame and continuously centering said measuring frame around said face area.

9. An autonomous target tracking method for autonomously tracking an object to be displayed on a display screen based on imaging output signals outputted from a lens block unit, said autonomous target tracking method comprising steps of:

dividing a display image of said image output signals into divided areas of prescribed dimensions;

extracting skin color divided areas wherein values of a hue signal are within prescribed ranges corresponding to skin color;

extracting hair divided areas wherein values of a brightness signal are within prescribed ranges corresponding to lightness of hair;

absorbing blank divided areas around said skin color divided areas and said hair divided areas to form skin color divided area groups and hair divided area groups, respectively;

extracting a set of a skin color divided area group and a hair divided area group which are adjacent to each other from said skin color divided area groups and hair divided area groups, respectively;

judging whether said set of said hair divided area group and said skin color divided area group constitutes a face area on a condition that respective sizes of said hair divided area group and said skin color divided area group are calculated, a ratio of said sizes of said hair divided area group and said skin color divided area group is within a prescribed range, and said hair divided area group is adjacent to an upper side of said skin color divided area group; and

setting a measuring frame in order that said face area can be encompassed by said measuring frame and continuously centering said measuring frame around said face area.