Intruding object detection method and intruding object monitor apparatus which automatically set a threshold for object detection

• US 20020071034A1
• Filed: 10/26/2001
• Published: 06/13/2002
• Est. Priority Date: 10/31/2000
• Status: Active Grant

• Current Assignee: Hitachi Kokusai Electric Incorporated (Hitachi, Ltd.)
• Original Assignee: Hitachi Kokusai Electric Incorporated (Hitachi, Ltd.)
• Inventors: Ito, Wataru, Ueda, Hirotada, Yamada, Hiromasa
• Granted Patent: US 7,035,430 B2
• Time in Patent Office: Days
• US Class Current: 348/152
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G08B 13/19602 Image analysis to detect motion of the intruder, e.g. by frame subtraction
• CPC Class Codes: G08B 13/19606 Discriminating between target movement or movement in an area of interest and other non-signicative movements, e.g. target movements induced by camera shake or movements of pets, falling leaves, rotating fan
• 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

A monitoring method and apparatus for detecting an intruding object within a monitoring field of view by applying a subtraction method to an image obtained from an imaging device. A differential image of luminance values between an input image from the imaging device and a reference background image stored in a storage device is generated. The differential image is binarized using a predetermined binarization threshold value and the bianrization threshold value is changed until a noise level of a bianrized image becomes not greater than a predetermined value and based on a binarization threshold value at which the noise level becomes not greater than the predetermined value, an intruding object is detected.

Claims

1. A monitoring method for detecting an intruding object within a monitoring field of view by applying a subtraction method to an image obtained from an imaging device, comprising the steps of:

generating a first differential image of luminance values between a first input image from said imaging device and a reference background image stored in a storage device;

binarizing said first differential image using a predetermined binarization threshold value, changing said binarization threshold value until a noise level of a binarized image becomes not greater than a predetermined value and setting, as a first binarization threshold value, said binarization threshold value at which the noise level becomes not greater than the predetermined value; and

detecting an intruding object based on said first binarization threshold value.

2. The monitoring method according to claim 1, wherein said binarization threshold value is changed in an arithmetic progression, in a geometric progression or randomly.

3. The monitoring method according to claim 2, wherein said binarization threshold value is increased.

4. The monitoring method according to claim 2, wherein said binarization threshold value is decreased.

5. The monitoring method according to claim 1, wherein said first input image is an image containing no intruding object.

6. The monitoring method according to claim 1, further comprising the steps of:

generating a second differential image of luminance values between a second input image containing an intruding object from said imaging device and said background image stored in said storage device;

binarizing said second differential image using a predetermined threshold value, changing said binarization threshold value until a size of said intruding object in a binarized image becomes not greater than a predetermined value and setting, as a second binarization threshold value, said binarization threshold value at which a size of said intruding object in said binarized image becomes not greater than the predetermined value;

setting a third binarization threshold value between said first and second binarization threshold value inclusive of said first and second binarization threshold values; and

detecting an intruding object based on said third binarization threshold value.

7. The monitoring method according to claim 6, wherein, in setting said first and second binarization threshold values, wherein said binarization threshold values are changed in an arithmetic progression, in a geometric progression or randomly.

8. The monitoring method according to claim 7, wherein said binarization threshold values are increased.

9. The monitoring method according to claim 7, wherein said binarization threshold values are decreased.

10. The monitoring method according to claim 6, wherein said size of said intruding object is represented by a circumscribed figure of said intruding object.

11. The monitoring method according to claim 6, further comprising the steps of:

recording a first and a second binarization threshold values obtained from said first and second input images, respectively;

executing said steps of binarizing over a predetermined number of frames and recording respective resultant binarization threshold values; and

selecting a predetermined first and a predetermined second threshold values from among the respective plurality of recorded binarization threshold values.

12. The monitoring method according to claim 11, wherein said step of selecting a predetermined first and a predetermined second threshold values includes the step of selecting a largest binarization threshold value with respect to said first threshold value and the step of selecting a smallest threshold value with respect to said second binarization threshold value.

13. The monitoring method according to claim 6, wherein said step of binarizing said first differential image using a predetermined threshold value includes the step of setting a masking zone.

14. The monitoring method according to claim 13, wherein said step of binarizing said second differential image using a predetermined threshold value includes the step of setting an area of the intruding object.

15. The monitoring method according to claim 6, further comprising obtaining a difference between said first and second binarization threshold values.

16. The method according to claim 15, further comprising the step of determining an abnormality when said difference between said first and second binarization threshold values is not greater than a predetermined value.

17. The monitoring method according to claim 6, further comprising the steps of:

recording a first binarization threshold value obtained from said first input images;

executing said step of binarizing over a predetermined number of frames and recording resultant binarization threshold values; and

selecting a first bianrization threshold value from among a plurality of the recording binarization threshold values.

18. The monitoring method according to claim 17, wherein said step of selecting a first binarization threshold value includes the step of selecting a largest binarization threshold value with respect to said first binarization threshold value.

19. The monitoring method according to claim 6, further comprising the steps of:

recording a second binarization threshold value obtained from said second input image;

executing said step of binarizing over a predetermined number of frames and recording resultant binarization threshold values; and

selecting a predetermined second threshold value from among the plurality of the recorded binarization threshold values.

20. The monitoring method according to claim 19, wherein said step of selecting a second binarization threshold value includes the step of selecting a smallest binarization threshold value with respect to said second binarization threshold value.

21. A monitoring apparatus for detecting an intruding object within a monitoring field of view by applying a subtraction method to an image obtained from an imaging device, comprising

an imaging device which outputs a first input image;

a first storage device which stores a reference background image;

a processing unit which generates a first differential image of luminance values between said first input image and said reference background image;

a first binarizing unit which binarizes said first differential image using a predetermined binarization threshold value, changes said binarization threshold value until a noise component of said binarized image becomes not greater than a predetermined value and outputs, as a first binarization threshold value, said binarization threshold value at which said noise component of said binarized image becomes not greater than the predetermined value;

a detection unit which detects an intruding object based on said first binarization threshold value.

22. The monitoring apparatus according to claim 21, wherein said first binarizing unit changes said binarization threshold value in an arithmetic progression, in a geometric progression or randomly.

23. The monitoring apparatus according to claim 21, wherein said first input image is an image containing no intruding object.

24. The monitoring apparatus according to claim 21, wherein said imaging device outputs a second input image containing an intruding object, said monitoring apparatus further comprising:

a processing unit which generates a second differential image of luminance values between said second input image and said reference background image stored in said first storage device;

a second binarizing unit which binarizes said second differential image using a predetermined binarization threshold value, changes said binarization threshold value until a size of an intruding object in a binarized image becomes not greater than a predetermined value and outputs, as a second binarization threshold value, said binarization threshold value at which said size of said intruding object in said bianrized image becomes not greater than the predetermined value; and

a threshold value setting unit which sets a third binarization threshold value between said first and second binarization threshold values inclusive of said first and second binarization threshold values,

wherein said detection unit detects an intruding object based on said third binarization threshold value.

25. The monitoring apparatus according to claim 24, wherein, when setting said first and second binarization threshold values, said first and second binarizing units change said binarization threshold value in an arithmetic progression, in a geometric progression or randomly.

26. The monitoring apparatus according to claim 24, wherein said size of said intruding object is represented by a circumscribed figure of said intruding object.

27. The monitoring apparatus according to claim 24, further comprising a second storage device which stores a first and a second binarization threshold values obtained from said first and second input images, respectively, and a selection unit which selects a predetermined first binarization threshold value and a predetermined second binarization threshold value from among binary threshold values obtained by executing the binarizing processing over a plurality of number of frames in said first and second binarizing units.

28. The monitoring apparatus according to claim 27, wherein said selection unit selects a largest binarization threshold value from among the first binarization threshold values obtained at said first binarizing unit and selects a smallest binarization threshold value from among the second binarization threshold values obtained at said second binarizing unit.

29. The monitoring apparatus according to claim 24, wherein said first binarizing unit has a function of setting a masking zone when binarizing said first differential image using a predetermined binarization threshold value.

30. The monitoring apparatus according to claim 29, wherein said second-binarizing unit has a function of setting an area of an intruding object when binarizing said second differential image using a predetermined binarization threshold value.

31. The monitoring apparatus according to claim 24, further comprising an arithmetic processing unit which calculates a difference between said first and second binarization threshold values.

32. The monitoring apparatus according to claim 31, further comprising a processing unit which determines an abnormality when the difference between said first and second binarization threshold values is not greater than a predetermined value.

33. The monitoring apparatus according to claim 24, wherein said processing units for generating the first and second differential images are implemented in a unitary processing unit.

34. The monitoring apparatus according to claim 24, wherein said first and second binarizing units are implemented in a unitary processing unit.