IP Library Granted Patent US 9,100,570
Granted Patent B2
US 9,100,570 · App. 14/112,254 · Granted Aug 4, 2015

Tonal stabilization of video

Inventors: Daniel Lischinski (Jerusalem, IL); Zeev Farbman (Jerusalem, IL)
Assignee: Yissum Research Development Company of The Hebrew University of Jerusalem Ltd.
H04N5/23232G06T5/002G06T2207/10016G06T2207/20012G06T2207/20028G06T2207/20182
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,100,570
App. No.
14/112,254
Granted
Aug 4, 2015
Kind
B2
Abstract

A method of tonally stabilizing a video sequence is provided herein. The method includes the following stages: automatically selecting one or more anchor frames from a sequence of frames; obtaining an anchor adjustment map for each selected anchor frame; applying an edge-preserving smoothing algorithm to the sequence of frames; generating for any given pair of smoothed frames, a robust set of pixels indicating pixels affected by external tonal fluctuation only; initializing an adjustment map for any given frame by applying the anchor adjustment map to accumulated color differences between pixels of the robust set of the given frame and the anchor frame; and completing the initialized adjustment map by predicting values of pixels in each adjustment map not included in the robust set by applying an interpolation at a color space for these pixels, wherein the adjustment maps are usable for tonally aligning the video sequence with the anchor frame.

Claims (41)

1. A method of tonally stabilizing a video sequence, the method comprising:

automatically selecting one or more anchor frames from a sequence of frames;

obtaining an anchor adjustment map for each selected anchor frame;

applying an edge-preserving smoothing algorithm to the sequence of frames;

generating for any given pair of smoothed frames, a robust set of pixels indicating pixels affected by external tonal fluctuation only;

initializing an adjustment map for any given frame by applying the anchor adjustment map to accumulated color differences between pixels of the robust set of the given frame and the anchor frame; and

completing the initialized adjustment map by predicting values of pixels in each adjustment map not included in the robust set by applying an interpolation at a color space for these pixels.

2. The method according to claim 1 , wherein the obtaining is achieved by generating an anchor adjustment map for each selected anchor frame.

3. The method according to claim 1 , further comprising tonally aligning one or more frames of the video sequence with its respective anchor frame by applying the completed adjustment map to its respective frame.

4. The method according to claim 3 , further comprising applying one or more predefined image processing algorithms to the tonally aligned sequence of frames.

5. The method according to claim 1 , wherein the edge-preserving smoothing algorithm comprises a bilateral filter with a spatial sigma being approximately 10% of the smaller image dimension and wherein a range sigma being approximately 10% of the values ranges.

6. The method according to claim 1 , wherein the anchor frames are selected from tonally stable sub sequences of frames in which global tonal fluctuations are below predefined thresholds.

7. The method according to claim 1 , wherein the adjustment map specifies for each pixel how its color channels need to be adjusted.

8. The method according to claim 1 , wherein the generating of the robust set is achieved by determining the corresponding pixels of any given two smoothed frames whose luminance differ from each other at a predefined threshold or below.

9. The method according to claim 1 , wherein the interpolation at the color space is based on global tonal fluctuations accumulated over the sequence of frames.

10. A system for tonally stabilizing a video sequence, the system comprising:

a computer processor;

an anchor selection module configured to automatically select one or more anchor frames from a sequence of frames;

a smoothing module configured to apply an edge-preserving smoothing algorithm to the sequence of frames;

a robust set generator configured to generate for any given pair of smoothed frames, a robust set of pixels indicating pixels affected by external tonal fluctuation only;

an adjustment map initializer configured to initialize an adjustment map for any given frame by applying an anchor adjustment map to accumulated color differences between pixels of the robust set of the given frame and the anchor frame; and

an interpolation module configured to complete the initialized adjustment map by predicting values of pixels in each adjustment map not included in the robust set by applying an interpolation at a color space for these pixels,

wherein the anchor selection module, the smoothing module, the robust set generator, the adjustment map initializer, and interpolation module are executed by the computer processor.

11. The system according to claim 10 , further comprising an anchor adjustment map generator configured to generate the anchor adjustment map for each selected anchor frame.

12. The system according to claim 10 , further comprising an alignment module configured to tonally align one or more frames of the video sequence with its respective anchor frame by applying the completed adjustment map to its respective frame.

13. The system according to claim 12 , further comprising an image processing module configured to apply one or more predefined image processing algorithms to the tonally aligned sequence of frames.

14. The system according to claim 10 , wherein the edge-preserving smoothing algorithm comprises a bilateral filter with a spatial sigma being approximately 10% of the smaller image dimension and wherein a range sigma being approximately 10% of the values ranges.

15. The system according to claim 10 , wherein the anchor frames are selected from tonally stable sub sequences of frames in which global tonal fluctuations are below predefined thresholds.

16. The system according to claim 10 , wherein the adjustment map specifies for each pixel how its color channels need to be adjusted.

17. The system according to claim 10 , wherein the robust set generator is configured to generate of the robust set by determining the corresponding pixels of any given two smoothed frames whose luminance differ from each other at a predefined threshold or below.

18. The system according to claim 10 , wherein the interpolation module is configured to apply the interpolation at the color space based on global tonal fluctuations accumulated over the sequence of frames.

19. A computer program product for tonally stabilizing a video sequence, the computer program product comprising:

a non-transitory computer readable medium having computer readable program embodied therewith, the computer readable program comprising:

computer readable program configured to automatically select one or more anchor frames from a sequence of frames;

computer readable program configured to apply an edge-preserving smoothing algorithm to the sequence of frames;

computer readable program configured to generate for any given pair of smoothed frames, a robust set of pixels indicating pixels affected by external tonal fluctuation only;

computer readable program configured to initialize an adjustment map for any given frame by applying an anchor adjustment map to accumulated color differences between pixels of the robust set of the given frame and the anchor frame; and

computer readable program configured to complete the initialized adjustment map by predicting values of pixels in each adjustment map not included in the robust set by applying an interpolation at a color space for these pixels.

20. The computer program product according to claim 19 , further comprising computer readable program configured to generate the anchor adjustment map for each selected anchor frame.

21. The computer program product according to claim 19 , further comprising computer readable program configured to tonally align one or more frames of the video sequence with its respective anchor frame by applying the completed adjustment map to its respective frame.

22. The computer program product according to claim 21 , further comprising computer readable program configured to apply one or more predefined image processing algorithms to the tonally aligned sequence of frames.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 10, 2019
From: STEPPING STONE, SERIES 85 OF ALLIED SECURITY TRUST I
To: JOLLY SEVEN, SERIES 70 OF ALLIED SECURITY TRUST I
Reel/Frame 049416/0975 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 19, 2018
From: YISSUM RESEARCH DEVELOPMENT COMPANY OF THE HEBREW UNIVERSITY OF JERUSALEM LTD.
To: STEPPING STONE, SERIES 85 OF ALLIED SECURITY TRUST I
Reel/Frame 047924/0090 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 3, 2014
From: LISCHINSKI, DANIEL; FARBMAN, ZEEV
To: YISSUM RESEARCH DEVELOPMENT COMPANY OF THE HEBREW UNIVERSITY OF JERUSALEM LTD.
Reel/Frame 032588/0372 →
Continuity (2)
Provisional Application 61476355 · Apr 18, 2011
Related Publication 20140300767A1 · Oct 9, 2014