IP Library Granted Patent US 9,595,112
Granted Patent B2
US 9,595,112 · App. 14/722,651 · Granted Mar 14, 2017

Incremental principal component pursuit for video background modeling

Inventors: Paul A. Rodriquez-Valderrama (Barranco, PE); Brendt Wohlberg (Santa Fe, NM)
Assignee: STC.UNM
G06T7/0081G06T7/0087G06T7/11G06T7/143G06T7/254G06T7/194G06T2207/10016G06T2207/20081G06T2207/20144
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 9,595,112
App. No.
14/722,651
Granted
Mar 14, 2017
Kind
B2
Abstract

An incremental Principal Component Pursuit (PCP) algorithm for video background modeling that is able to process one frame at a time while adapting to changes in background, with a computational complexity that allows for real-time processing, having a low memory footprint and is robust to translational and rotational jitter.

Claims (21)

1. A computer system method for video background modeling including an incremental principal component pursuit algorithm comprising a low computational cost executed by a processor, the method comprising the steps of:

providing the incremental principal component pursuit algorithm with the low computational cost O(14·m·r)+O(15·N c ·N r (2·log 2 (N r )+log 2 (N c )) per frame per inner loop;

receiving an input video sequence comprising a plurality of frames;

estimating a low-rank approximation of a background of the input video sequence;

segmenting foreground objects from background objects appearing in the input video sequence by processing the input video sequence in an incremental fashion to obtain a processed input video sequence, wherein a computational complexity of each frame of the input video sequence is O(8·m·r)+O(r 3 ), where m=N r (frame rows)×N c (frame columns)×N d (frame depth or channels), and r is the rank of a matrix that represents the background; and

displaying the processed input video sequence to obtain an output video sequence.

2. The computer system method for video background modeling including an incremental principal component pursuit algorithm executed by a processor according to claim 1 , wherein the incremental principal component pursuit algorithm comprises a low memory footprint.

3. The computer system method for video background modeling including an incremental principal component pursuit algorithm executed by a processor according to claim 2 , wherein the low memory footprint is O(3·m·r).

4. The computer system method for video background modeling including an incremental principal component pursuit algorithm executed by a processor according to claim 2 , wherein the low memory footprint is O(3·m·r)+O(4·m).

5. The computer system method for video background modeling including an incremental principal component pursuit algorithm executed by a processor according to claim 1 , wherein the low computational cost is O(14·m·r) per frame.

6. The computer system method for video background modeling including an incremental principal component pursuit algorithm executed by a processor according to claim 1 , wherein the incremental fashion is one frame at a time.

7. A computer system method for video background modeling including executed by a processor, the method comprising the steps of:

providing an incremental principal component pursuit algorithm comprising a low computational cost, wherein the low computational cost is one of: O(14·m·r)+O(15·N c ·N r (2·log 2 (N r )+log 2 (N c )) per frame per inner loop and O(14·m·r) per frame;

receiving an input video sequence comprising a plurality of frames;

estimating a low-rank approximation of a background of the input video sequence;

segmenting foreground objects from background objects appearing in the input video sequence by processing the input video sequence in an incremental fashion to obtain a processed input video sequence, wherein a computational complexity of each frame of the input video sequence is O(8·m·r)+O(r3), where m=N r (frame rows)×N c (frame columns)×N d (frame depth or channels), and r is the rank of a matrix that represents the background; and

displaying the processed input video sequence to obtain an output video sequence.

8. The computer system method for video background modeling including an incremental principal component pursuit algorithm executed by a processor according to claim 7 , wherein the incremental principal component pursuit algorithm comprises a low memory footprint.

9. The computer system method for video background modeling including an incremental principal component pursuit algorithm executed by a processor according to claim 8 , wherein the low memory footprint is O(3·m·r).

10. The computer system method for video background modeling including an incremental principal component pursuit algorithm executed by a processor according to claim 8 , wherein the low memory footprint is O(3·m·r)+O(4·m).

11. The computer system method for video background modeling including an incremental principal component pursuit algorithm executed by a processor according to claim 7 , wherein the incremental fashion is one frame at a time.

Assignments (5)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 8, 2018
From: LOS ALAMOS NATIONAL SECURITY, LLC
To: TRIAD NATIONAL SECURITY, LLC
Reel/Frame 047485/0471 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 6, 2018
From: RODRIGUEZ-VALDERRAMA, PAUL
To: THE REGENTS OF THE UNIVERSITY OF NEW MEXICO
Reel/Frame 046559/0932 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 6, 2018
From: THE REGENTS OF THE UNIVERSITY OF NEW MEXICO
To: STC.UNM
Reel/Frame 046559/0950 →
CONFIRMATORY LICENSE Recorded Dec 13, 2016
From: LOS ALAMOS NATIONAL SECURITY
To: U.S. DEPARTMENT OF ENERGY
Reel/Frame 040717/0806 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 30, 2016
From: WOHLBERG, BRENDT
To: LOS ALAMOS NATIONAL SECURITY
Reel/Frame 039059/0381 →
Continuity (4)
Provisional Application 62067904 · Oct 23, 2014
Provisional Application 62037685 · Aug 15, 2014
Provisional Application 62003152 · May 27, 2014
Related Publication 20150348274A1 · Dec 3, 2015