VIDEO BASED MATCHING AND TRACKING
First Claim
1. A method of analyzing a first image abstraction and a second image abstraction to determine whether the first image abstraction and the second image abstraction are similar to one another, the method comprising:
- accessing the first image abstraction;
accessing the second image abstraction;
combining at least a part of the first image abstraction with at least a part of the second image abstraction to generate a combined image abstraction; and
analyzing the combined image abstraction in order to determine whether the first image abstraction and the second image abstraction are similar to one another.
7 Assignments
0 Petitions
Accused Products
Abstract
An analytical device is disclosed that analyzes whether a first image is similar to (or the same as) as a second image. The analytical device analyzes the first image by combining at least a part (or all) of the first image with at least a part (or all) of the second image, and by analyzing at least a part (or all) of the combined image. Part or all of the combination may be analyzed with respect to the abstraction of the first image and/or the abstraction of the second image. The abstraction may be based on a Bag of Features (BoF) description, based on a histogram of intensity values, or based on other types of abstraction methodologies. The analysis may involve comparing one or more aspects of the combination (such as the entropy or randomness of the combination) with the one or more aspects of the abstracted first image and/or abstracted second image. Based on the comparison, the analytical device may determine whether the first image is similar to or the same as the second image. The analytical device may work with a variety of images in a variety of applications including a video tracking system, a biometric analytic system, or a database image analytical system.
38 Citations
26 Claims
-
1. A method of analyzing a first image abstraction and a second image abstraction to determine whether the first image abstraction and the second image abstraction are similar to one another, the method comprising:
-
accessing the first image abstraction; accessing the second image abstraction; combining at least a part of the first image abstraction with at least a part of the second image abstraction to generate a combined image abstraction; and analyzing the combined image abstraction in order to determine whether the first image abstraction and the second image abstraction are similar to one another. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A method for tracking an object in multiple image frames, the method comprising:
-
accessing one or more image patches in a current image frame; abstracting the one or more image patches using a Bag of Features (BoF) description to generate abstracted one or more image patches; accessing an object abstraction of the object, the object abstraction being based, at least in part on one or more image frames previous to the current image frame; and analyzing the object abstraction and the abstracted one or more image patches to determine which of the one or more image patches is most similar to the object. - View Dependent Claims (13, 14, 15, 16, 17, 18)
-
-
19. An apparatus for analyzing a first image abstraction and a second image abstraction to determine whether the first image abstraction and the second image abstraction are similar to one another, the apparatus comprising:
-
at least one memory configured to store the first image abstraction and the second image abstraction; and a controller in communication with the memory and configured to; combine at least a part of the first image abstraction with at least a part of the second image abstraction to generate a combined image abstraction; and analyze the combined image abstraction in order to determine whether the first image abstraction and the second image abstraction are similar to one another. - View Dependent Claims (20, 21, 22, 23, 24)
-
-
25. An apparatus for tracking an object in multiple image frames, the apparatus comprising:
-
at least one memory configured to store one or more image patches in a current image frame and an object abstraction of the object, the object abstraction being based, at least in part on one or more image frames previous to the current image frame; and a controller in communication with the memory and configured to; abstract the one or more image patches using a Bag of Features (BoF) description to generate abstracted one or more image patches; and analyze the object abstraction and the abstracted one or more image patches to determine which of the one or more image patches is most similar to the object. - View Dependent Claims (26)
-
Specification