Systems and Methods for Detecting Free-Standing Groups of Individuals

Number: 20170076157
Published: 2017-03-16
Filed: 2015-09-11
Assignee: Disney Enterprises, Inc.
Inventors: Vazquez; Marynel et al.
CPC: G06F18/29; G06T7/70; G06V10/763; G06T7/20; G06V20/30; G06V20/53
Verdict: Low Notable software
Source: Google Patents · FreePatentsOnline

The keeper's note

Computer-vision technique detecting free-standing groups of individuals — crowd-analysis tracking.

Abstract

There is provided a system and method for grouping a plurality of individuals, each individual of the plurality of individuals having a corresponding transactional segment, the system comprising amemory storing a group identification application, a processor for executing the group identification application to identify an o-space center of a first group, wherein the o-space center is an intersection of a plurality of transactional segments, obtain a non-parametric lower-body orientation probability distribution for each of the plurality of individuals, based on the o-space center, and determine that a first plurality of individuals fromthe plurality of individuals belong to the first group based on the non-parametric lower-body orientation probability distribution of each individual of the plurality of individuals, wherein each of the first plurality of individuals has a corresponding one of the plurality of transactional segments that intersect with one another.

Background

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 shows an exemplary system for detecting free-standing groups of individuals, according to one implementation of the present disclosure;

FIG. 2 shows an exemplary environment including the system of FIG. 1 for detecting free-standing groups of individuals, according to one implementation of the present disclosure;

FIG. 3 shows another exemplary environment including the system of FIG. 1 for detecting free-standing groups of individuals, according to one implementation of the present disclosure;

FIG. 4 shows a diagram depicting a step in an exemplary grouping analysis, according to one implementation of the present disclosure;

FIG. 5 shows a diagram depicting an exemplary grouping analysis, according to one implementation of the present disclosure;

FIG. 6 shows a diagram depicting an exemplary grouping analysis, according to one implementation of the present disclosure;

FIG. 7 shows a diagram of an exemplary coordinate system used in the exemplary grouping analysis of FIG. 6, according to one implementation of the present disclosure; and

FIG. 8 shows an exemplary flowchart illustrating a method of grouping individuals, according to one implementation of the present disclosure.DETAILED DESCRIPTION

The following description contains specific information pertaining to implementations in the present disclosure. The drawings in the present application and their accompanying detailed descri

Claims

1. A system for grouping a plurality of individuals, each individual of the plurality of individuals having a corresponding transactional segment, the system comprising: a memory storing a groupidentification executable code; a processor for executing the group identification executable code to: identify an o-space center of a first group, wherein the o-space center is an intersection of a plurality of transactional segments; obtain a non-parametric lower-body orientation probability distribution for each of the plurality of individuals, based on the o-space center; and determine that a first plurality of individuals from the pluralityof individuals belong to the first group based on the non-parametric lower-body orientation probability distribution of each individual of the plurality of individuals, wherein each of the first plurality of individuals has a corresponding one of the plurality of transactional segments that intersect with one another. 11. A method of identifying free-standing conversational groups among a plurality of individuals in an area, using a system having a memory and a processor, the method comprising: identifying, using the processor, an o-space center of a first group, wherein the o-space center is an intersection of a plurality of transactional segments; obtaining, using the processor, a non-parametric lower-body orientation probability distribution for each of the plurality of individuals, based on theo-space center; and determining, using the processor, that a first plurality of individuals from the plurality of individuals belong to the first group based on the non-parametriclower-body orientation probability distribution of each individual of the plurality of individuals, wherein each of the first plurality of individuals has a corresponding one of the plurality of transactional segments that intersect with one another.