METHODS AND SYSTEMS FOR IMAGE PROCESSING IN A MULTIVIEW VIDEO SYSTEM

• US 20090167866A1
• Filed: 09/04/2008
• Published: 07/02/2009
• Est. Priority Date: 12/31/2007
• Status: Active Grant

• Current Assignee: Industrial Technology Research Institute
• Original Assignee: Industrial Technology Research Institute
• Inventors: Chen, Hung-Ming, Jou, Fan-Di, Lee, Kual-Zheng
• Granted Patent: US 8,264,542 B2
• Time in Patent Office: Days
• US Class Current: 348/159
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30236 Traffic on road, railway or crossing
• CPC Class Codes: G06T 7/292 Multi-camera tracking
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]

Abstract

A system for image processing in a multiview video environment including a first camera and a second camera is disclosed. The system comprises a region of interest (ROI) module configured to receive first video signals from the first camera and detect at least one ROI in a first image related to the first video signals, a first lookup table configured to generate an attribute value in response to a type of a block, wherein the type of a block is related to a first vanishing point defined in the first image, a labeling module configured to identify a first point “p” most close to the first vanishing point, a second point “q” most remote to the first vanishing point and a length “h” between the first point “p” and the second point “q” in each of the at least one ROI, and generate first information on p, q and h, a second lookup table configured to generate second information on p′, q′ and h′ in response to the first information, wherein p′ is a first point most close to a second vanishing point defined in a second image related to the second camera, q′ is a second point most remote to the second vanishing point and h′ is a length between the first point p′ and the second point q′ in each of at least one ROI in the second image, and a transforming module configured to transform each of the at least one ROI in the first image into an ROI in the second image based on the second lookup table.

Claims

1. A system for image processing in a multiview video environment including a first camera and a second camera, the system comprising:

a region of interest (ROI) module configured to receive first video signals from the first camera and detect at least one ROI in a first image related to the first video signals;

a first lookup table configured to generate an attribute value in response to a type of a block, wherein the type of a block is related to a first vanishing point defined in the first image;

a labeling module configured to identify a first point “

p”

most close to the first vanishing point, a second point “

q”

most remote to the first vanishing point and a length “

h”

between the first point “

p” and

the second point “

q”

in each of the at least one ROI, and generate first information on p, q and h;

a second lookup table configured to generate second information on p′

, q′ and

h′

in response to the first information, wherein p′

is a first point most close to a second vanishing point defined in a second image related to the second camera, q′

is a second point most remote to the second vanishing point and h′

is a length between the first point p′ and

the second point q′

in each of at least one ROI in the second image; and

a transforming module configured to transform each of the at least one ROI in the first image into an ROI in the second image based on the second lookup table.

2. The system of claim 1, wherein the labeling module is configured to divide each of the at least one ROI in the first image into a number of blocks and assign an attribute value to the blocks in each of the at least of ROI in the first image based on the first lookup table.

3. The system of claim 1, wherein the labeling module is configured to identify the number of blocks related to an object in one of the at least one ROI in the first image.

4. The system of claim 1 further comprising a third camera, wherein the second lookup table generates third information on p″

, q″ and

h″

in response to the first information, wherein p″

is a first point most close to a third vanishing point defined in a third image related to the third camera, q″

is a second point most remote to the second vanishing point and h″

is a length between the first point p″ and

the second point q″

in each of at least one ROI in the third image.

5. The system of claim 1, wherein the first video signals include one of non-compressed video signals and compressed video signals.

6. A system for image processing in a multiview video environment, the system comprising:

a number of cameras C₁ to C_N, N being a positive integer;

a region of interest (ROI) module configured to receive first video signals from the camera C₁ and detect at least one ROI in a first image related to the first video signals;

a first lookup table configured to generate an attribute value in response to a type of a block, wherein the type of a block is related to a first vanishing point defined in the first image;

a labeling module configured to identify a first point “

p”

most close to the first vanishing point and a second point “

q”

most remote to the first vanishing point and a length “

h”

between the first point “

p” and

the second point “

q”

in each of the at least one ROI, and generate first information on p, q and h;

a second lookup table configured to generate second information on p′

, q′ and

h′

in response to the first information, wherein p′

is a first point most close to a second vanishing point defined in a second image related to each of the cameras C₂ to C_N, q′

is a second point most remote to the second vanishing point and h′

is a length between the first point p′ and

the second point q′

in each of at least one ROI in the second image; and

a number of transforming modules T₂ to T_N configured to receive the first information and transform each of the at least one ROI in the first image into an ROI in the second image related to each of the cameras C₂ to C_N based on the second lookup table.

7. The system of claim 6, wherein the labeling module is configured to divide each of the at least one ROI in the first image into a number of blocks and assign an attribute value to the blocks in each of the at least of ROI in the first image based on the first lookup table.

8. The system of claim 6, wherein the labeling module is configured to identify the number of blocks related to an object in one of the at least one ROI in the first image.

9. The system of claim 6 further comprising a number of video encoders E₁ to E_N to respectively receive video signals from the cameras C₁ to C_N.

10. The system of claim 6, wherein the first video signals include one of non-compressed video signals and compressed video signals.

11. A method for image processing in a multiview video environment including a first camera and a second camera, the method comprising:

receiving first video signals from the first camera;

identifying at least one region of interest (ROI) in a first image related to the first video signals;

configuring a first lookup table, wherein the first lookup table generates an attribute value in response to a type of a block, wherein the type of a block is related to a first vanishing point defined in the first image;

identifying a first point “

p”

most close to the first vanishing point, a second point “

q”

most remote to the first vanishing point and a length “

h”

between the first point “

p” and

the second point “

q”

in each of the at least one ROI, and generating first information on p, q and h;

configuring a second lookup table, wherein the second lookup table generates second information on p′

, q′ and

h′

in response to the first information, wherein p′

is a first point most close to a second vanishing point defined in a second image related to the second camera, q′

is a second point most remote to the second vanishing point and h′

is a length between the first point p′ and

the second point q′

in each of at least one ROI in the second image; and

transforming each of the at least one ROI in the first image into an ROI in the second image based on the second lookup table.

12. The method of claim 11, wherein the labeling module is configured to divide each of the at least one ROI in the first image into a number of blocks and assign an attribute value to the blocks in each of the at least of ROI in the first image based on the first lookup table.

13. The method of claim 11, wherein the labeling module is configured to identify the number of blocks related to an object in one of the at least one ROI in the first image.

14. The method of claim 11 further comprising a third camera, wherein the second lookup table generates third information on p″

, q″ and

h″

in response to the first information, wherein p″

is a first point most close to a third vanishing point defined in a third image related to the third camera, q″

is a second point most remote to the second vanishing point and h″

is a length between the first point p″ and

the second point q″

in each of at least one ROI in the third image.

15. The method of claim 11, wherein the first video signals include one of non-compressed video signals and compressed video signals.

16. A method for image processing in a multiview video environment, the method comprising:

providing a number of cameras C₁ to C_N, N being a positive integer;

receiving first video signals from the camera C₁;

detect at least one region of interest (ROI) in a first image related to the first video signals;

configuring a first lookup table, wherein the first lookup table generates an attribute value in response to a type of a block, wherein the type of a block is related to a first vanishing point defined in the first image;

identifying a first point “

p”

most close to the first vanishing point and a second point “

q”

most remote to the first vanishing point and a length “

h”

between the first point “

p” and

the second point “

q”

in each of the at least one ROI, and generate first information on p, q and h;

configuring a second lookup table, wherein the second lookup table generates second information on p′

, q′ and

h′

in response to the first information, wherein p′

is a first point most close to a second vanishing point defined in a second image related to each of the cameras C₂ to C_N, q′

is a second point most remote to the second vanishing point and h′

is a length between the first point p′ and

the second point q′

in each of at least one ROI in the second image; and

receiving the first information and transforming each of the at least one ROI in the first image into an ROI in the second image related to each of the cameras C₂ to C_N based on the second lookup table.

17. The method of claim 16, wherein the labeling module is configured to divide each of the at least one ROI in the first image into a number of blocks and assign an attribute value to the blocks in each of the at least of ROI in the first image based on the first lookup table.

18. The method of claim 16, wherein the labeling module is configured to identify the number of blocks related to an object in one of the at least one ROI in the first image.

19. The method of claim 16 further comprising a number of video encoders E₁ to E_N to respectively receive video signals from the cameras C₁ to C_N.

20. The method of claim 16, wherein the first video signals include one of non-compressed video signals and compressed video signals.