AUTOMATIC DETECTION OF STEREOSCOPIC CONTENT IN VIDEO/IMAGE DATA

• US 20140321732A1
• Filed: 04/25/2013
• Published: 10/30/2014
• Est. Priority Date: 04/25/2013
• Status: Active Grant

• Current Assignee: NVIDIA Corporation
• Original Assignee: NVIDIA Corporation
• Inventors: Bhat, Himanshu Jagadish, Kale, Gautam Pratap
• Granted Patent: US 9,092,658 B2
• Time in Patent Office: Days
• US Class Current: 382/154
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 7/32 using correlation-based methods
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: H04N 13/106 Processing image signals for multi-view video sequence encoding H04N19/597
• CPC Class Codes: H04N 2213/007 Aspects relating to detection of stereoscopic image format, e.g. for adaptation to the display format

Abstract

A method includes calculating, through a processor of a computing device communicatively coupled to a memory, correlation between two portions of an image and/or a video frame on either side of a reference portion thereof. The method also includes determining, through the processor, whether content of the image and/or the video frame is stereoscopic or non-stereoscopic based on the determined correlation.

Claims

1. A method comprising:

calculating, through a processor of a computing device communicatively coupled to a memory, correlation between two portions of at least one of an image and a video frame on either side of a reference portion thereof; and

determining, through the processor, whether content of the at least one of the image and the video frame is one of;

stereoscopic and non-stereoscopic based on the determined correlation.

2. The method of claim 1, wherein calculating the correlation further comprises:

calculating an offset at which the correlation between the two portions is optimal; and

calculating the optimal correlation for at least one of;

each row and each column of the at least one of the image and the video frame.

3. The method of claim 2, further comprising:

calculating an average offset for the at least one of the image and the video frame; and

calculating variance of offsets for the at least one of;

rows and columns of the at least one of the image and the video frame around the average offset.

4. The method of claim 3, further comprising:

calculating a sample variance in the offsets based on dividing the calculated variance thereof by a dimension of the at least one of the image and the video frame; and

determining that the content is stereoscopic if the sample variance is below a threshold value thereof derived as a factor of another dimension of the at least one of the image and the video frame perpendicular to the dimension.

5. The method of claim 1, further comprising:

performing, through the processor, high-pass filtering to detect an edge around one of the reference portion and a central portion of the at least one of the image and the video frame; and

utilizing the edge detection in conjunction with the calculated correlation to detect stereoscopic content of the at least one of the image and the video frame.

6. The method of claim 4, further comprising:

obtaining directional distribution of variation in peaks of results of correlation in the at least one of the image and the video frame; and

determining parity between a left eye view and a right eye view in the at least one of the image and the video frame based on the obtained directional distribution.

7. The method of claim 1, wherein at least one of:

the computing device is one of a data source, a server and a client device communicatively coupled to the data source,

instructions associated with initiating the correlation calculation and the content determination are provided as part of a driver component associated with at least one of the processor, an operating system executing on the computing device and an application executing on the computing device, and

the reference portion is a central portion of the at least one of the image and the video frame.

8. A computing device comprising:

a memory; and

a processor communicatively coupled to the memory, the processor being configured to execute instructions to;

correlate between two portions of at least one of an image and a video frame on either side of a reference portion thereof, and

determine whether content of the at least one of the image and the video frame is one of;

stereoscopic and non-stereoscopic based on the determined correlation.

9. The computing device of claim 8, wherein the processor is configured to execute instructions to correlate between the portions based on:

calculating an offset at which the correlation between the two portions is optimal, and

calculating the optimal correlation for at least one of;

each row and each column of the at least one of the image and the video frame.

10. The computing device of claim 9, wherein the processor is configured to further execute instructions to:

calculate an average offset for the at least one of the image and the video frame; and

calculate variance of offsets for the at least one of;

rows and columns of the at least one of the image and the video frame around the average offset.

11. The computing device of claim 10, wherein the processor is configured to further execute instructions to:

calculate a sample variance in the offsets based on dividing the calculated variance thereof by a dimension of the at least one of the image and the video frame, and

determine that the content is stereoscopic if the sample variance is below a threshold value thereof derived as a factor of another dimension of the at least one of the image and the video frame perpendicular to the dimension.

12. The computing device of claim 8, wherein the processor is further configured to execute instructions to:

perform high-pass filtering to detect an edge around one of the reference portion and a central portion of the at least one of the image and the video frame, and

utilize the edge detection in conjunction with the calculated correlation to detect stereoscopic content of the at least one of the image and the video frame.

13. The computing device of claim 11, wherein the processor is further configured to execute instructions to:

obtain directional distribution of variation in peaks of results of correlation in the at least one of the image and the video frame, and

determine parity between a left eye view and a right eye view in the at least one of the image and the video frame based on the obtained directional distribution.

14. The computing device of claim 8, wherein at least one of:

the computing device is one of a data source, a server and a client device communicatively coupled to the data source,

instructions associated with initiating the correlation calculation and the content determination are provided as part of a driver component associated with at least one of the processor, an operating system executing on the computing device, and an application executing on the computing device, and

the reference portion is a central portion of the at least one of the image and the video frame.

15. A non-transitory medium, readable through a computing device and including instructions embodied therein that are executable through the computing device, comprising:

instructions to calculate, through a processor of the computing device communicatively coupled to a memory, correlation between two portions of at least one of an image and a video frame on either side of a reference portion thereof; and

instructions to determine, through the processor, whether content of the at least one of the image and the video frame is one of;

stereoscopic and non-stereoscopic based on the determined correlation.

16. The non-transitory medium of claim 15, wherein instructions to calculate the correlation further comprises:

instructions to calculate an offset at which the correlation between the two portions is optimal; and

instructions to calculate the optimal correlation for at least one of;

each row and each column of the at least one of the image and the video frame.

17. The non-transitory medium of claim 16, further comprising:

instructions to calculate an average offset for the at least one of the image and the video frame; and

instructions to calculate variance of offsets for the one of;

rows and columns of the at least one of the image and the video frame around the average offset.

18. The non-transitory medium of claim 17, further comprising:

instructions to calculate a sample variance in the offsets based on dividing the calculated variance thereof by a dimension of the at least one of the image and the video frame; and

instructions to determine that the content is stereoscopic if the sample variance is below a threshold value thereof derived as a factor of another dimension of the at least one of the image and the video frame perpendicular to the dimension.

19. The non-transitory medium of claim 15, further comprising:

instructions to perform, through the processor, high-pass filtering to detect an edge around one of the reference portion and a central portion of the at least one of the image and the video frame; and

instructions to utilize the edge detection in conjunction with the calculated correlation to detect stereo content of the at least one of the image and the video frame.

20. The non-transitory medium of claim 18, further comprising:

instructions to obtain directional distribution of variation in peaks of results of correlation in the at least one of the image and the video frame; and

instructions to determine parity between a left eye view and a right eye view in the at least one of the image and the video frame based on the obtained directional distribution.