Apparatus for extracting/combining change region in image corresponding to moving object

• US 5,099,324 A
• Filed: 06/27/1990
• Issued: 03/24/1992
• Est. Priority Date: 06/30/1989
• Status: Expired due to Fees

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Abe, Shozo
• Primary Examiner(s): Groody, James J.
• Assistant Examiner(s): LEE, MICHAEL
• Application Number:
  US07/544,588
• Time in Patent Office: 636 Days
• Field of Search: 358/105, 358/108, 358/136, 358/167, 358/36
• US Class Current: 348/155
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06V 10/273 removing elements interfering with the pattern to be recognised
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: G08B 13/19602 Image analysis to detect motion of the intruder, e.g. by frame subtraction
• CPC Class Codes: G08B 13/19613 Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
• CPC Class Codes: G08B 13/19691 Signalling events for better perception by user, e.g. indicating alarms by making display brighter, adding text, creating a sound

Abstract

An area to be monitored is picked up by a TV camera, and data of the picked-up image is converted into digital data in units of frames and stored in frame memories. The image data stored in the frame memories are read out, and a change region is extracted as an image of a moving object. The extracted moving object image has a plurality of dispersed regions including a shadow image. Only the dispersed regions corresponding to the moving object are extracted by setting a frame, and a noise image including the shadow image is removed.

Claims

1. An image information processing apparatus comprising:

image pickup means for picking up image information in an area to be monitored at predetermined time intervals to obtain a plurality of items of image information;

extracting means for extracting an image of a moving object included in the plurality of picked up image information; and

deleting means for deleting a noise image including a shadow image of the moving object obtained adjacent to the image of the moving object.

2. An apparatus according to claim 1, wherein said extracting means includes:

memory means for storing continuous first, second, and third items of image information of the plurality of items of image information;

first subtracting means for obtaining a first difference image between the first and second items of image information stored in said memory means;

second subtraction means for obtaining a second difference image between the second and third items of image information stored in said memory means; and

means for obtaining the image of the moving object by performing logical AND of the first and second difference images obtained from said first and second subtracting means.

3. An apparatus according to claim 1, wherein said extracting means includes:

means for obtaining a plurality of dispersed images as the image of the moving object;

means for setting a frame for covering a predetermined region including the image of the moving object; and

means for performing predetermined labeling for the dispersed images.

4. An apparatus according to claim 3, wherein said noise image deleting means includes:

means for determining whether the plurality of dispersed images are included in the frame; and

means for ignoring the dispersed images not included in the frame as noise images.

5. An apparatus according to claim 4, wherein said determining means includes:

means for determining whether the dispersed images included in the frame and the dispersed images not included in the frame together form an L-shaped pattern; and

means for ignoring the dispersed images not included in the frame as a shadow image if an L-shaped pattern is determined.

6. An apparatus according to claim 1, wherein said extracting means includes means for setting a predetermined region including the moving object as a frame.

7. An apparatus according to claim 6, wherein said noise image deleting means includes means for processing an image obtained outside the frame as a noise image.

8. An image information processing apparatus, comprising:

image pickup means for picking up image information in an area to be monitored at predetermined time intervals to obtain a plurality of items of image information;

extracting means for extracting an image of a change region included in the plurality of picked up image information, said extracting means including memory means for storing continuous first, second and third images of the plurality of items of image information, first subtracting means for obtaining a first difference image between the first and second items of image information stored in the memory means, second subtracting means for obtaining a second difference image between the second and third items of image information stored in said memory means, and means for obtaining the image of the moving object to perform logical AND of said first and second difference images obtained from said first and second subtracting means;

deleting means for deleting a noise image including a shadow image obtained adjacent to the image of the change region; and

means for shaping the image of the change region to obtain a moving object image.

9. An apparatus according to claim 8, wherein said extracting means includes:

means for obtaining a plurality of dispersed images as the image of the moving object;

means for setting a frame for covering a predetermined region including the image of the moving object; and

means for performing predetermined labeling for the dispersed images to form labeled dispersed images.

10. An apparatus according to claim 9, wherein said noise image deleting means includes:

means for determining whether the plurality of dispersed images are included in the frame; and

means for ignoring the dispersed images not included in the frame as noise images.

11. An apparatus according to claim 10, wherein said determining means includes:

means for determining whether the dispersed images included in the frame and the dispersed images not included in the frame together form an L-shaped pattern; and

means for ignoring the dispersed images not included in the frame as a shadow image if an L-shaped pattern is determined.

12. An apparatus according to claim 8, wherein said extracting means has means for setting a predetermined region including the moving object as a frame.

13. An apparatus according to claim 12, wherein said noise image deleting means includes means for processing an image obtained outside the frame as a noise image.

14. An apparatus according to claim 9, wherein said shaping means includes:

detecting means for detecting labeled dispersed images included in the frame;

extracting means for extracting a labeled region having a maximum area of the detected dispersed images;

detecting means for detecting all labeled regions present above and below the maximum labeled region and included in the frame; and

combining means for combining all the detected labeled regions with the maximum labeled region.

15. An image information processing apparatus comprising:

image pickup means for picking up image information in an area to be monitored at predetermined time intervals to obtain a plurality of items of image information;

extracting means for extracting an image of a moving object included in the plurality of picked up image information, said extracting means including means for setting a predetermined region including the moving object as a frame; and

deleting means for deleting a noise image including a shadow image of the moving object obtained adjacent to the image of the moving object.

16. An apparatus according to claim 15, wherein said extracting means includes:

memory means for storing continuous first, second and third items of image information of the plurality of items of image information;

first subtraction means for obtaining a first difference image between the first and second items of image information stored in said memory means;

second subtraction means for obtaining a second difference image between the second and third items of image information stored in said memory means; and

means for obtaining the image of the moving object by performing logical AND of the first and second difference images obtained from said first and second subtraction means.

17. An apparatus according to claim 15, wherein said extracting means includes:

means for obtaining a plurality of dispersed images as the image of the moving object;

means for setting a frame for covering a predetermined region including the image of the moving object; and

means for performing predetermined labeling for the dispersed images.

18. An apparatus according to claim 17, wherein said noise image deleting means includes:

means for determining whether the plurality of dispersed images are included in the frame; and

means for ignoring the dispersed images not included in the frame as noise images.

19. An apparatus according to claim 18, wherein said determining means includes:

means for determining whether the dispersed images included in the frame and the dispersed images not included in the frame together form an L-shaped pattern; and

means for ignoring the dispersed images not included in the frame as a shadow image if an L-shaped pattern is determined.

20. An apparatus according to claim 15, wherein said noise image deleting means includes means for processing an image obtained outside the frame as a noise image.