Crowd Analysis by Using Optical Flow and Density Based Clustering

Francesco Santoro, Sergio Pedro, Zheng-Hua Tan, Thomas B. Moeslund

Publikation: Bidrag til tidsskriftKonferenceartikel i tidsskriftForskningpeer review

Resumé

In this paper, we present a system to detect and track crowds
in a video sequence captured by a camera. In a first step, we
compute optical flows by means of pyramidal Lucas-Kanade
feature tracking. Afterwards, a density based clustering is
used to group similar vectors. In the last step, it is applied a
crowd tracker in every frame, allowing us to detect and track
the crowds. Our system gives the output as a graphic overlay,
i.e it adds arrows and colors to the original frame sequence,
in order to identify crowds and their movements. For the
evaluation, we check when our system detect certains events
on the crowds, such as merging, splitting and collision.
OriginalsprogEngelsk
TidsskriftProceedings of the European Signal Processing Conference
Vol/bind18
Sider (fra-til)269-273
ISSN2076-1465
StatusUdgivet - aug. 2010
BegivenhedEUSIPCO 2010 - Aalborg, Danmark
Varighed: 23 aug. 2010 → …

Konference

KonferenceEUSIPCO 2010
LandDanmark
ByAalborg
Periode23/08/2010 → …

Fingerprint

Density (optical)
Optical flows
Merging
Cameras
Color

Citer dette

@inproceedings{2dc27dcb35454b988fa7a9046bc5b7ba,
title = "Crowd Analysis by Using Optical Flow and Density Based Clustering",
abstract = "In this paper, we present a system to detect and track crowdsin a video sequence captured by a camera. In a first step, wecompute optical flows by means of pyramidal Lucas-Kanadefeature tracking. Afterwards, a density based clustering isused to group similar vectors. In the last step, it is applied acrowd tracker in every frame, allowing us to detect and trackthe crowds. Our system gives the output as a graphic overlay,i.e it adds arrows and colors to the original frame sequence,in order to identify crowds and their movements. For theevaluation, we check when our system detect certains eventson the crowds, such as merging, splitting and collision.",
author = "Francesco Santoro and Sergio Pedro and Zheng-Hua Tan and Moeslund, {Thomas B.}",
year = "2010",
month = "8",
language = "English",
volume = "18",
pages = "269--273",
journal = "Proceedings of the European Signal Processing Conference",
issn = "2076-1465",
publisher = "European Association for Signal Processing (EURASIP)",

}

Crowd Analysis by Using Optical Flow and Density Based Clustering. / Santoro, Francesco; Pedro, Sergio; Tan, Zheng-Hua; Moeslund, Thomas B.

I: Proceedings of the European Signal Processing Conference, Bind 18, 08.2010, s. 269-273.

Publikation: Bidrag til tidsskriftKonferenceartikel i tidsskriftForskningpeer review

TY - GEN

T1 - Crowd Analysis by Using Optical Flow and Density Based Clustering

AU - Santoro, Francesco

AU - Pedro, Sergio

AU - Tan, Zheng-Hua

AU - Moeslund, Thomas B.

PY - 2010/8

Y1 - 2010/8

N2 - In this paper, we present a system to detect and track crowdsin a video sequence captured by a camera. In a first step, wecompute optical flows by means of pyramidal Lucas-Kanadefeature tracking. Afterwards, a density based clustering isused to group similar vectors. In the last step, it is applied acrowd tracker in every frame, allowing us to detect and trackthe crowds. Our system gives the output as a graphic overlay,i.e it adds arrows and colors to the original frame sequence,in order to identify crowds and their movements. For theevaluation, we check when our system detect certains eventson the crowds, such as merging, splitting and collision.

AB - In this paper, we present a system to detect and track crowdsin a video sequence captured by a camera. In a first step, wecompute optical flows by means of pyramidal Lucas-Kanadefeature tracking. Afterwards, a density based clustering isused to group similar vectors. In the last step, it is applied acrowd tracker in every frame, allowing us to detect and trackthe crowds. Our system gives the output as a graphic overlay,i.e it adds arrows and colors to the original frame sequence,in order to identify crowds and their movements. For theevaluation, we check when our system detect certains eventson the crowds, such as merging, splitting and collision.

M3 - Conference article in Journal

VL - 18

SP - 269

EP - 273

JO - Proceedings of the European Signal Processing Conference

JF - Proceedings of the European Signal Processing Conference

SN - 2076-1465

ER -