Video motion detection using block processing

• US 20070058837A1
• Filed: 09/15/2005
• Published: 03/15/2007
• Est. Priority Date: 09/15/2005
• Status: Abandoned Application

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Boregowda, Lokesh, Jain, Mayur, Rajagopal, Anupama
• Application Number:
  US11/227,588
• Publication Number:
  US 20070058837A1
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 7/223 using block-matching

Abstract

A system detects motion in video data. In an embodiment, a difference frame is created by comparing the pixels from a first frame and a second frame. The difference frame is divided up into blocks of pixels, and the system calculates standard deviations on a block basis. A threshold value is calculated based on the standard deviation, and the presence or absence of motion is determined based on that threshold value.

Claims

1. A method comprising:

creating a difference frame by determining the differences in pixel intensity values per channel between pixels in a first frame of video data and corresponding pixels in a second frame of video data;

dividing said difference frame into one or more blocks;

calculating standard deviations for each channel in each of said one or more blocks;

determining a maximum value and a mean value per channel of said standard deviations for said difference frame;

calculating a cumulative mean per channel of said maximum values and said mean values over a plurality of frames;

calculating a cumulative difference by subtracting said cumulative mean of said mean values from said cumulative mean of said maximum values;

determining that said cumulative difference is greater than zero;

calculating a threshold value;

labeling pixels of a current frame having intensity values below said threshold value as 0, and labeling pixels of said current frame having intensity values above said threshold value as 1, thereby giving a binary image of each channel; and

logically ANDing said binary images of each channel.

2. The method of claim 1, wherein said one or more blocks is selected from the group consisting of a 3*3 matrix, a 5*5 matrix, and an 8*8 matrix.

3. The method of claim 1, wherein said channels comprise a red channel, a green channel, and a blue channel.

4. The method of claim 1, wherein said threshold value is calculated by multiplying said maximum value of said standard deviation by a threshold factor.

5. The method of claim 4, wherein said threshold factor is equal to 1/sqrt(2).

6. The method of claim 1, further comprising:

determining that said cumulative difference is less than or equal to zero; and

reading a new frame of video data.

7. A machine readable medium comprising instructions thereon for executing a method comprising:

creating a difference frame by determining the differences in pixel intensity values per channel between pixels in a first frame of video data and corresponding pixels in a second frame of video data;

dividing said difference frame into one or more blocks;

calculating standard deviations for each channel in each of said one or more blocks;

determining a maximum value and a mean value per channel of said standard deviations for said difference frame;

calculating a cumulative mean per channel of said maximum values and said mean values over a plurality of frames;

calculating a cumulative difference by subtracting said cumulative mean of said mean values from said cumulative mean of said maximum values;

determining that said cumulative difference is greater than zero;

calculating a threshold value;

labeling pixels of a current frame having intensity values below said threshold value as 0, and labeling pixels of said current frame having intensity values above said threshold value as 1, thereby giving a binary image of each channel; and

logically ANDing said binary images of each channel.

8. The machine readable medium of claim 7, wherein said one or more blocks is selected from the group consisting of a 3*3 matrix, a 5*5 matrix, and an 8*8 matrix.

9. The machine readable medium of claim 7, wherein said channels comprise a red channel, a green channel, and a blue channel.

10. The machine readable medium of claim 7, wherein said threshold value is calculated by multiplying said maximum value of said standard deviation by a threshold factor.

11. The machine readable medium of claim 10, wherein said threshold factor is equal to 1/sqrt(2).

12. The machine readable medium of claim 7, further comprising:

determining that said cumulative difference is less than or equal to zero; and

reading a new frame of video data.

13. A method comprising:

creating a difference frame from a first frame of video data and a second frame of video data;

dividing said difference frame into a plurality of blocks;

calculating block-based standard deviations;

determining a maximum value of said standard deviations;

calculating a mean value of said standard deviations;

calculating a cumulative maximum value and a cumulative mean value over a plurality of frames;

calculating a threshold value from said maximum standard deviation; and

determining motion in said video data based on said threshold value.

14. The method of claim 13, wherein said difference frame is created by determining the differences in pixel intensity values per channel between pixels in said first frame and corresponding pixels in said second frame.

15. The method of claim 13, further comprising calculating a cumulative difference by subtracting said cumulative mean value from said cumulative maximum value.

16. The method of claim 15, further comprising:

determining that said cumulative difference is less than or equal to zero; and

fetching a new first frame of video data.

17. The method of claim 13, wherein said plurality of blocks is selected from the group consisting of a 3*3 matrix, a 5*5 matrix, and an 8*8 matrix.

18. The method of claim 13, wherein said calculations of said standard deviations are on a per channel basis.

19. The method of claim 13, wherein said threshold value is calculated by multiplying said maximum value of said standard deviation by a threshold factor.

20. The method of claim 19, wherein said threshold factor is equal to 1/sqrt(2).