Crowd estimation using key‐point matching with support vector regression

Abstract The crowd behaviour understanding and density estimation are some of the fast‐growing fields in video surveillance. There are many techniques (detection and regression) that are used as the method of crowd analysis and estimation. In the present approach, SVR (support vector regression) is...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: E.M.C.L Ekanayake, Yunqi Lei
Formato: article
Lenguaje:EN
Publicado: Wiley 2021
Materias:
Acceso en línea:https://doaj.org/article/0590108273ae48ba83ad4b95eb10047d
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:0590108273ae48ba83ad4b95eb10047d
record_format dspace
spelling oai:doaj.org-article:0590108273ae48ba83ad4b95eb10047d2021-11-29T03:38:16ZCrowd estimation using key‐point matching with support vector regression1751-96671751-965910.1049/ipr2.12300https://doaj.org/article/0590108273ae48ba83ad4b95eb10047d2021-12-01T00:00:00Zhttps://doi.org/10.1049/ipr2.12300https://doaj.org/toc/1751-9659https://doaj.org/toc/1751-9667Abstract The crowd behaviour understanding and density estimation are some of the fast‐growing fields in video surveillance. There are many techniques (detection and regression) that are used as the method of crowd analysis and estimation. In the present approach, SVR (support vector regression) is used as the basic analysis technique and the novel key‐point matching with SURF (speedup robust feature) is used as the feature extractor for moving objects in the video. The traditional linear regression methods used mainly key‐point as one of the statistical features instead of matching with consecutive frames, but we used the magnitude of the optical flow for foreground object extraction instead of inter‐frame difference. The combination of the optical flow of foreground objects and key‐point matching generates new features apart from conventional features such as areas and corners. In this new approach, key‐point pairing with linear regression is tested with the PETS2009 dataset, and performance is compared with the existing approaches.E.M.C.L EkanayakeYunqi LeiWileyarticlePhotographyTR1-1050Computer softwareQA76.75-76.765ENIET Image Processing, Vol 15, Iss 14, Pp 3551-3558 (2021)
institution DOAJ
collection DOAJ
language EN
topic Photography
TR1-1050
Computer software
QA76.75-76.765
spellingShingle Photography
TR1-1050
Computer software
QA76.75-76.765
E.M.C.L Ekanayake
Yunqi Lei
Crowd estimation using key‐point matching with support vector regression
description Abstract The crowd behaviour understanding and density estimation are some of the fast‐growing fields in video surveillance. There are many techniques (detection and regression) that are used as the method of crowd analysis and estimation. In the present approach, SVR (support vector regression) is used as the basic analysis technique and the novel key‐point matching with SURF (speedup robust feature) is used as the feature extractor for moving objects in the video. The traditional linear regression methods used mainly key‐point as one of the statistical features instead of matching with consecutive frames, but we used the magnitude of the optical flow for foreground object extraction instead of inter‐frame difference. The combination of the optical flow of foreground objects and key‐point matching generates new features apart from conventional features such as areas and corners. In this new approach, key‐point pairing with linear regression is tested with the PETS2009 dataset, and performance is compared with the existing approaches.
format article
author E.M.C.L Ekanayake
Yunqi Lei
author_facet E.M.C.L Ekanayake
Yunqi Lei
author_sort E.M.C.L Ekanayake
title Crowd estimation using key‐point matching with support vector regression
title_short Crowd estimation using key‐point matching with support vector regression
title_full Crowd estimation using key‐point matching with support vector regression
title_fullStr Crowd estimation using key‐point matching with support vector regression
title_full_unstemmed Crowd estimation using key‐point matching with support vector regression
title_sort crowd estimation using key‐point matching with support vector regression
publisher Wiley
publishDate 2021
url https://doaj.org/article/0590108273ae48ba83ad4b95eb10047d
work_keys_str_mv AT emclekanayake crowdestimationusingkeypointmatchingwithsupportvectorregression
AT yunqilei crowdestimationusingkeypointmatchingwithsupportvectorregression
_version_ 1718407628057477120