GrCS

Granular computing-based crowd segmentation

Kok Ven Jyn , Chee Seng Chan

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Crowd segmentation is important in serving as the basis for a wide range of crowd analysis tasks such as density estimation and behavior understanding. However, due to interocclusions, perspective distortion, clutter background, and random crowd distribution, localizing crowd segments is technically a very challenging task. This paper proposes a novel crowd segmentation framework-based on granular computing (GrCS) to enable the problem of crowd segmentation to be conceptualized at different levels of granularity, and to map problems into computationally tractable subproblems. It shows that by exploiting the correlation among pixel granules, we are able to aggregate structurally similar pixels into meaningful atomic structure granules. This is useful in outlining natural boundaries between crowd and background (i.e., noncrowd) regions. From the structure granules, we infer the crowd and background regions by granular information classification. GrCS is scene-independent and can be applied effectively to crowd scenes with a variety of physical layout and crowdedness. Extensive experiments have been conducted on hundreds of real and synthetic crowd scenes. The results demonstrate that by exploiting the correlation among granules, we can outline the natural boundaries of structurally similar crowd and background regions necessary for crowd segmentation.

Original languageEnglish
Article number7434629
Pages (from-to)1157-1168
Number of pages12
JournalIEEE Transactions on Cybernetics
Volume47
Issue number5
DOIs
Publication statusPublished - 1 May 2017
Externally publishedYes

Fingerprint

Granular computing
Pixels
Experiments

Keywords

  • Crowd analysis
  • crowd segmentation
  • granular computing (GrC)

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Information Systems
  • Human-Computer Interaction
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

GrCS : Granular computing-based crowd segmentation. / Ven Jyn , Kok; Chan, Chee Seng.

In: IEEE Transactions on Cybernetics, Vol. 47, No. 5, 7434629, 01.05.2017, p. 1157-1168.

Research output: Contribution to journalArticle

Ven Jyn , Kok ; Chan, Chee Seng. / GrCS : Granular computing-based crowd segmentation. In: IEEE Transactions on Cybernetics. 2017 ; Vol. 47, No. 5. pp. 1157-1168.
@article{b3d8a75e5f5e4826893b61ec2bba2de4,
title = "GrCS: Granular computing-based crowd segmentation",
abstract = "Crowd segmentation is important in serving as the basis for a wide range of crowd analysis tasks such as density estimation and behavior understanding. However, due to interocclusions, perspective distortion, clutter background, and random crowd distribution, localizing crowd segments is technically a very challenging task. This paper proposes a novel crowd segmentation framework-based on granular computing (GrCS) to enable the problem of crowd segmentation to be conceptualized at different levels of granularity, and to map problems into computationally tractable subproblems. It shows that by exploiting the correlation among pixel granules, we are able to aggregate structurally similar pixels into meaningful atomic structure granules. This is useful in outlining natural boundaries between crowd and background (i.e., noncrowd) regions. From the structure granules, we infer the crowd and background regions by granular information classification. GrCS is scene-independent and can be applied effectively to crowd scenes with a variety of physical layout and crowdedness. Extensive experiments have been conducted on hundreds of real and synthetic crowd scenes. The results demonstrate that by exploiting the correlation among granules, we can outline the natural boundaries of structurally similar crowd and background regions necessary for crowd segmentation.",
keywords = "Crowd analysis, crowd segmentation, granular computing (GrC)",
author = "{Ven Jyn }, Kok and Chan, {Chee Seng}",
year = "2017",
month = "5",
day = "1",
doi = "10.1109/TCYB.2016.2538765",
language = "English",
volume = "47",
pages = "1157--1168",
journal = "IEEE Transactions on Cybernetics",
issn = "2168-2267",
publisher = "IEEE Advancing Technology for Humanity",
number = "5",

}

TY - JOUR

T1 - GrCS

T2 - Granular computing-based crowd segmentation

AU - Ven Jyn , Kok

AU - Chan, Chee Seng

PY - 2017/5/1

Y1 - 2017/5/1

N2 - Crowd segmentation is important in serving as the basis for a wide range of crowd analysis tasks such as density estimation and behavior understanding. However, due to interocclusions, perspective distortion, clutter background, and random crowd distribution, localizing crowd segments is technically a very challenging task. This paper proposes a novel crowd segmentation framework-based on granular computing (GrCS) to enable the problem of crowd segmentation to be conceptualized at different levels of granularity, and to map problems into computationally tractable subproblems. It shows that by exploiting the correlation among pixel granules, we are able to aggregate structurally similar pixels into meaningful atomic structure granules. This is useful in outlining natural boundaries between crowd and background (i.e., noncrowd) regions. From the structure granules, we infer the crowd and background regions by granular information classification. GrCS is scene-independent and can be applied effectively to crowd scenes with a variety of physical layout and crowdedness. Extensive experiments have been conducted on hundreds of real and synthetic crowd scenes. The results demonstrate that by exploiting the correlation among granules, we can outline the natural boundaries of structurally similar crowd and background regions necessary for crowd segmentation.

AB - Crowd segmentation is important in serving as the basis for a wide range of crowd analysis tasks such as density estimation and behavior understanding. However, due to interocclusions, perspective distortion, clutter background, and random crowd distribution, localizing crowd segments is technically a very challenging task. This paper proposes a novel crowd segmentation framework-based on granular computing (GrCS) to enable the problem of crowd segmentation to be conceptualized at different levels of granularity, and to map problems into computationally tractable subproblems. It shows that by exploiting the correlation among pixel granules, we are able to aggregate structurally similar pixels into meaningful atomic structure granules. This is useful in outlining natural boundaries between crowd and background (i.e., noncrowd) regions. From the structure granules, we infer the crowd and background regions by granular information classification. GrCS is scene-independent and can be applied effectively to crowd scenes with a variety of physical layout and crowdedness. Extensive experiments have been conducted on hundreds of real and synthetic crowd scenes. The results demonstrate that by exploiting the correlation among granules, we can outline the natural boundaries of structurally similar crowd and background regions necessary for crowd segmentation.

KW - Crowd analysis

KW - crowd segmentation

KW - granular computing (GrC)

UR - http://www.scopus.com/inward/record.url?scp=84960984423&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960984423&partnerID=8YFLogxK

U2 - 10.1109/TCYB.2016.2538765

DO - 10.1109/TCYB.2016.2538765

M3 - Article

VL - 47

SP - 1157

EP - 1168

JO - IEEE Transactions on Cybernetics

JF - IEEE Transactions on Cybernetics

SN - 2168-2267

IS - 5

M1 - 7434629

ER -