Method and apparatus for visual background subtraction with one or more preprocessing modules

• US 20070047834A1
• Filed: 08/31/2005
• Published: 03/01/2007
• Est. Priority Date: 08/31/2005
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Connell, Jonathan
• Application Number:
  US11/216,667
• Publication Number:
  US 20070047834A1
• Time in Patent Office: Days
• US Class Current: 382/274
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/20182 Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering
• CPC Class Codes: G06T 5/50 using two or more images, e.g. averaging or subtraction
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06T 5/80 Geometric correction
• CPC Class Codes: G06T 5/90 Dynamic range modification of images or parts thereof
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: H04N 1/407 Control or modification of tonal gradation or of extreme levels, e.g. background level
• CPC Class Codes: H04N 1/6027 Correction or control of colour gradation or colour contrast H04N1/6058 takes precedence

Abstract

Methods and apparatus are provided for visual background subtraction using one or more preprocessing modules. One or more effects are detected in a received image signal and one or more blocks are selectively enabled to preprocess the image signal to compensate for the detected one or more effects. Visual analysis is then performed on the preprocessed signal using background subtraction. A spatially-variant temporal smoothing of the image signal is also disclosed. The spatially-variant temporal smoothing can be achieved by the mixing of a new intensity value with a previous intensity time-average as determined by a weighting matrix. The mixing can be influenced by a dynamic bias term that is a real-time estimate of a variance at the pixel, such as a degree of change, and the weighting can be determined by a relative stability of an observed value compared to a stability of the time-average.

Claims

1. A method for processing an image signal, comprising:

receiving an image signal that has been corrupted by one or more effects;

detecting said one or more effects in said received image signal;

selectively enabling one or more blocks to preprocess said image signal to compensate for said detected one or more effects; and

performing visual analysis on said preprocessed signal using background subtraction.

2. The method of claim 1, wherein said visual analysis identifies one or more objects in said preprocessed image signal.

3. The method of claim 1, wherein said one or more blocks performs a jitter correction on said image signal.

4. The method of claim 1, wherein said one or more blocks performs a color correction on said image signal.

5. The method of claim 1, wherein said one or more blocks performs a contrast enhancement on said image signal.

6. The method of claim 1, wherein said one or more blocks performs a cable-induced visual artifact reduction on said image signal.

7. The method of claim 1, wherein said one or more blocks performs a spatially-variant temporal smoothing on said image signal.

8. The method of claim 1, wherein said one or more blocks performs a lens geometry normalization on said image signal.

9. A system for processing an image signal, comprising:

a memory; and

at least one processor, coupled to the memory, operative to;

receive an image signal that has been corrupted by one or more effects;

detect said one or more effects in said received image signal;

selectively enable one or more blocks to preprocess said image signal to compensate for said detected one or more effects; and

perform visual analysis on said preprocessed signal using background subtraction.

10. The system of claim 9, wherein said visual analysis identifies one or more objects in said preprocessed image signal.

11. The system of claim 9, wherein said one or more blocks performs a jitter correction on said image signal.

12. The system of claim 9, wherein said one or more blocks performs a color correction on said image signal.

13. The system of claim 9, wherein said one or more blocks performs a contrast enhancement on said image signal.

14. The system of claim 9, wherein said one or more blocks performs a cable-induced visual artifact reduction on said image signal.

15. The system of claim 9, wherein said one or more blocks performs a spatially-variant temporal smoothing on said image signal.

16. The system of claim 9, wherein said one or more blocks performs a lens geometry normalization on said image signal.

17. An article of manufacture for processing an image signal, comprising a machine readable medium containing one or more programs which when executed implement the steps of:

receiving an image signal that has been corrupted by one or more effects;

detecting said one or more effects in said received image signal;

selectively enabling one or more blocks to preprocess said image signal to compensate for said detected one or more effects; and

performing visual analysis on said preprocessed signal using background subtraction.

18. The article of manufacture of claim 17, wherein said one or more blocks performs one or more of a jitter correction on said image signal, a color correction on said image signal, a contrast enhancement on said image signal, a cable-induced visual artifact reduction on said image signal, a spatially-variant temporal smoothing on said image signal, or a lens geometry normalization on said image signal.

19. A method for processing an image signal, comprising:

receiving an image signal that has been corrupted by one or more effects;

selectively enabling one or more blocks to preprocess said image signal to compensate for said one or more effects;

performing spatially-variant temporal smoothing to further preprocess said image signal; and

presenting said preprocessed image signal for visual analysis.

20. The method of claim 19, wherein said visual analysis identifies one or more objects in said preprocessed image signal.

21. The method of claim 19, wherein said visual analysis uses background subtraction.

22. The method of claim 19, wherein said visual analysis is performed by a human watching a video screen.

23. The method of claim 19, wherein said spatially-variant temporal smoothing is achieved by the mixing of a new intensity value with a previous intensity time-average as determined by a weighting matrix.

24. The method of claim 23, wherein said mixing is influenced by a dynamic bias term that is a real-time estimate of a variance at said pixel.

25. The method of claim 23, wherein said weighting is determined by a relative stability of an observed value compared to a stability of the time-average.

26. The method of claim 23, wherein an amount of said mixing is based on a degree of change observed at said pixel.

27. The method of claim 23, wherein an amount of said mixing is reduced as a degree of motion at said pixel increases.

28. The method of claim 19, wherein said spatially-variant temporal smoothing is achieved by associating one or more independent Kalman filters with each pixel position.