Multi-scale crowd feature detection using vision sensing and statistical mechanics principles
Multi-scale crowd feature detection using vision sensing and statistical mechanics principles
Crowd behaviour analysis using vision has been subject to many different approaches. Multi-purpose crowd descriptors are one of the more recent approaches. These descriptors provide an opportunity to compare and categorize various types of crowds as well as classify their respective behaviours. Nevertheless, the automated calculation of descriptors which are expressed as measurements with accurate interpretation is a challenging problem. In this paper, analogies between human crowds and molecular thermodynamics systems are drawn for the measurement of crowd behaviour. Specifically, a novel descriptor is defined and measured for crowd behaviour at multiple scales. This descriptor uses the concept of Entropy for evaluating the state of crowd disorder. By results, the descriptor Entropy does indeed appear to capture the desired outcome for crowd entropy while utilizing easily detectable image features. Our new approach for machine understanding of crowd behaviour is promising, while it offers new complementary capabilities to the existing crowd descriptors, for example, as will be demonstrated, in the case of spectator crowds. The scope and performance of this descriptor are further discussed in detail in this paper.
Crowd behaviour detection, Crowd dynamics, Group detection and tracking, Multi-scale crowd features, Statistical mechanics, Video analysis
1-16
Arbab-Zavar, Banafshe
40e175ea-6557-47c6-b759-318d7e24984b
Sabeur, Zoheir
74b55ff0-94cc-4624-84d5-bb816a7c9be6
21 April 2020
Arbab-Zavar, Banafshe
40e175ea-6557-47c6-b759-318d7e24984b
Sabeur, Zoheir
74b55ff0-94cc-4624-84d5-bb816a7c9be6
Arbab-Zavar, Banafshe and Sabeur, Zoheir
(2020)
Multi-scale crowd feature detection using vision sensing and statistical mechanics principles.
Machine Vision and Applications, 31 (4), , [26].
(doi:10.1007/s00138-020-01075-4).
Abstract
Crowd behaviour analysis using vision has been subject to many different approaches. Multi-purpose crowd descriptors are one of the more recent approaches. These descriptors provide an opportunity to compare and categorize various types of crowds as well as classify their respective behaviours. Nevertheless, the automated calculation of descriptors which are expressed as measurements with accurate interpretation is a challenging problem. In this paper, analogies between human crowds and molecular thermodynamics systems are drawn for the measurement of crowd behaviour. Specifically, a novel descriptor is defined and measured for crowd behaviour at multiple scales. This descriptor uses the concept of Entropy for evaluating the state of crowd disorder. By results, the descriptor Entropy does indeed appear to capture the desired outcome for crowd entropy while utilizing easily detectable image features. Our new approach for machine understanding of crowd behaviour is promising, while it offers new complementary capabilities to the existing crowd descriptors, for example, as will be demonstrated, in the case of spectator crowds. The scope and performance of this descriptor are further discussed in detail in this paper.
Text
Arbab-Zavar-Sabeur 2020 Article Multi-scale Crowd Feature
- Version of Record
More information
Accepted/In Press date: 23 March 2020
e-pub ahead of print date: 21 April 2020
Published date: 21 April 2020
Additional Information:
Publisher Copyright:
© 2020, The Author(s).
Keywords:
Crowd behaviour detection, Crowd dynamics, Group detection and tracking, Multi-scale crowd features, Statistical mechanics, Video analysis
Identifiers
Local EPrints ID: 440935
URI: http://eprints.soton.ac.uk/id/eprint/440935
ISSN: 0932-8092
PURE UUID: 0d0964ee-07e7-45b8-ab64-d91ef2d7bd66
Catalogue record
Date deposited: 22 May 2020 16:40
Last modified: 16 Mar 2024 07:56
Export record
Altmetrics
Contributors
Author:
Banafshe Arbab-Zavar
Author:
Zoheir Sabeur
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics