Systems and Methods for Re-Identifying Objects in Images

Number: 20170256057
Published: 2017-09-07
Filed: 2016-03-04
Assignee: Disney Enterprises, Inc.
Inventors: Bak; Slawomir W., Carr; George Peter
CPC: G06T7/73; G06V20/52; G06V40/103
Verdict: Low Notable software
Source: Google Patents · FreePatentsOnline

The keeper's note

Re-identifies objects across images by dividing them into patches and extracting comparable feature representations.

Abstract

There is provided a system including a memory and a processor configured to receive a first image depicting a first object and a second image depicting a second object, divide the first image into a first plurality of patches and the second image into a second plurality of patches, extract plurality of feature vectors from each of the first plurality of patches and a second plurality of feature vectors from the second plurality of patches, determine dissimilarities based on a plurality of patch metrics, each patch dissimilarity measure being a dissimilarity between corresponding patches of the first plurality of patches and the second plurality of patches, compute an image dissimilarity between thefirst image and the second image based on an aggregate of the plurality of patch dissimilarity measures, evaluate the image dissimilarity to determine a probability of whether thefirst object and the second object are the same.

Background

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 shows a diagram of an exemplary system for re-identifying objects in images, according to one implementation of the present disclosure;

FIG. 2 shows a diagram of an exemplary pair of input images for use with the system of FIG. 1, according to one implementation of the present disclosure;

FIG. 3 shows a diagram of the images of FIG. 2 divided into patches for use with thesystem of FIG. 1, according to one implementation of the present disclosure;

FIG. 4shows a diagram of an exemplary comparison of the images of FIG. 2 using the system of FIG. 1, according to one implementation of the present disclosure;

FIG. 5 shows a diagram of a chart showing efficacy of different analysis methods using the system of FIG. 1, according to one implementation of the present disclosure;

FIG. 6 shows a diagram ofanother chart showing efficacy of different analysis methods using the system of FIG. 1, according to one implementation of the present disclosure;

FIG. 7 shows a diagram ofan exemplary dividing of an image into a various number of patches, according to one implementation of the present disclosure;

FIG. 8 shows a diagram of an exemplary image analysis, according to one implementation of the present disclosure; and

FIG. 9 showsa flowchart illustrating an exemplary method of re-identifying objects in images, according to one implementation of the present disclosure.DETAILED DESCRIPTION

Claims

1. A method for use by a system comprising a non-transitory memory and a hardware processor, the method comprising: receiving, using the hardware processor, a first image depicting a first object and a second image depicting a second object; dividing, using the hardware processor, the first image into a first plurality of patches and the second image into a second plurality of patches, wherein each patch of the second plurality of patches corresponds to one of the first plurality of patches at a same corresponding location; extracting, using the hardware processor, a first plurality of feature vectors from each of the first plurality of patches and a second plurality of feature vectors from each of the second plurality of patches; determining, using the hardware processor, a plurality of patch dissimilarity measures based on a plurality of patch metrics, each patch dissimilarity measure being a dissimilarity betweencorresponding patches of the first plurality of patches and the second plurality of patches; computing, using the hardware processor, an image dissimilarity between the first image and the second image based on an aggregate of the plurality of patch dissimilarity measures; and evaluating, using the hardware processor, the image dissimilarity to determine a probability of whether the first object and the second object are the same. 11. A system comprising: a non-transitory memory storing an executable code; and a hardware processor executing the executable code to: receive a first image depicting a first object and a second image depicting a second object; divide the first image into a first plurality of patches and the second image into a second plurality of patches, wherein each patch of the second plurality of patches corresponds to one of the first plurality of patches at a same corresponding location; extract a first plurality of feature vectors from each of the first plurality of patches and a second plurality of feature vectors from each of the second plurality of patches; determine a plurality of patch dissimilarity measures based on a plurality of patch metrics, each patch dissimilarity measure being a dissimilarity between corresponding patches of the first plurality of patches and the second plurality of patches; compute an image dissimilarity between the first image and the second image based on an aggregate of the plurality of patch dissimilarity measures; and evaluate the image dissimilarityto determine a probability of whether the first object and the second object are the same.