Automatic Estimation of Movement Statistics of People

Thomas Ægidiussen Jensen, Henrik Anker Rasmussen, Thomas B. Moeslund

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

Automatic analysis of how people move about in a particular environment has a number of potential applications. However, no system has so far been able to do detection and tracking robustly. Instead, trajectories are often broken into tracklets. The key idea behind this paper is based around the notion that people need not be detected and tracked perfectly in order to derive useful movement statistics for a particular scene. Tracklets will suffice. To this end we build a tracking framework based on a HoG detector and an appearance-based particle filter. The detector is optimized by learning a scene model allowing for a speedup of the process together with a significantly reduced false positive rate. The developed system is applied in two different scenarios where it is shown that useful statistics can indeed be extracted.
Original languageEnglish
Title of host publicationArticulated Motion and Deformable Objects : 7th International Conference, AMDO 2012, Port d’Andratx, Mallorca, Spain, July 11-13, 2012. Proceedings
EditorsFrancisco J. Perales, Robert B. Fisher, Thomas B. Moeslund
PublisherSpringer Publishing Company
Publication date2012
Pages153-162
ISBN (Print)978-3-642-31566-4
ISBN (Electronic)978-3-642-31567-1
DOIs
Publication statusPublished - 2012
Event7th International Conference on Articulated Motion and Deformable Objects - Port d'Andratx, Mallorca, Spain
Duration: 11 Jul 201213 Jul 2012

Conference

Conference7th International Conference on Articulated Motion and Deformable Objects
CountrySpain
CityPort d'Andratx, Mallorca
Period11/07/201213/07/2012
SeriesLecture Notes in Computer Science
Volume7378
ISSN0302-9743

Fingerprint

Statistics
Detectors
Trajectories

Cite this

Ægidiussen Jensen, T., Rasmussen, H. A., & Moeslund, T. B. (2012). Automatic Estimation of Movement Statistics of People. In F. J. Perales, R. B. Fisher, & T. B. Moeslund (Eds.), Articulated Motion and Deformable Objects: 7th International Conference, AMDO 2012, Port d’Andratx, Mallorca, Spain, July 11-13, 2012. Proceedings (pp. 153-162). Springer Publishing Company. Lecture Notes in Computer Science, Vol.. 7378 https://doi.org/10.1007/978-3-642-31567-1_15
Ægidiussen Jensen, Thomas ; Rasmussen, Henrik Anker ; Moeslund, Thomas B. / Automatic Estimation of Movement Statistics of People. Articulated Motion and Deformable Objects: 7th International Conference, AMDO 2012, Port d’Andratx, Mallorca, Spain, July 11-13, 2012. Proceedings. editor / Francisco J. Perales ; Robert B. Fisher ; Thomas B. Moeslund. Springer Publishing Company, 2012. pp. 153-162 (Lecture Notes in Computer Science, Vol. 7378).
@inproceedings{05c7bd0979d64d0bb4186b60f07655bb,
title = "Automatic Estimation of Movement Statistics of People",
abstract = "Automatic analysis of how people move about in a particular environment has a number of potential applications. However, no system has so far been able to do detection and tracking robustly. Instead, trajectories are often broken into tracklets. The key idea behind this paper is based around the notion that people need not be detected and tracked perfectly in order to derive useful movement statistics for a particular scene. Tracklets will suffice. To this end we build a tracking framework based on a HoG detector and an appearance-based particle filter. The detector is optimized by learning a scene model allowing for a speedup of the process together with a significantly reduced false positive rate. The developed system is applied in two different scenarios where it is shown that useful statistics can indeed be extracted.",
author = "{{\AE}gidiussen Jensen}, Thomas and Rasmussen, {Henrik Anker} and Moeslund, {Thomas B.}",
year = "2012",
doi = "10.1007/978-3-642-31567-1_15",
language = "English",
isbn = "978-3-642-31566-4",
series = "Lecture Notes in Computer Science",
publisher = "Springer Publishing Company",
pages = "153--162",
editor = "Perales, {Francisco J.} and Fisher, {Robert B.} and Moeslund, {Thomas B.}",
booktitle = "Articulated Motion and Deformable Objects",
address = "United States",

}

Ægidiussen Jensen, T, Rasmussen, HA & Moeslund, TB 2012, Automatic Estimation of Movement Statistics of People. in FJ Perales, RB Fisher & TB Moeslund (eds), Articulated Motion and Deformable Objects: 7th International Conference, AMDO 2012, Port d’Andratx, Mallorca, Spain, July 11-13, 2012. Proceedings. Springer Publishing Company, Lecture Notes in Computer Science, vol. 7378, pp. 153-162, 7th International Conference on Articulated Motion and Deformable Objects, Port d'Andratx, Mallorca, Spain, 11/07/2012. https://doi.org/10.1007/978-3-642-31567-1_15

Automatic Estimation of Movement Statistics of People. / Ægidiussen Jensen, Thomas ; Rasmussen, Henrik Anker; Moeslund, Thomas B.

Articulated Motion and Deformable Objects: 7th International Conference, AMDO 2012, Port d’Andratx, Mallorca, Spain, July 11-13, 2012. Proceedings. ed. / Francisco J. Perales; Robert B. Fisher; Thomas B. Moeslund. Springer Publishing Company, 2012. p. 153-162 (Lecture Notes in Computer Science, Vol. 7378).

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Automatic Estimation of Movement Statistics of People

AU - Ægidiussen Jensen, Thomas

AU - Rasmussen, Henrik Anker

AU - Moeslund, Thomas B.

PY - 2012

Y1 - 2012

N2 - Automatic analysis of how people move about in a particular environment has a number of potential applications. However, no system has so far been able to do detection and tracking robustly. Instead, trajectories are often broken into tracklets. The key idea behind this paper is based around the notion that people need not be detected and tracked perfectly in order to derive useful movement statistics for a particular scene. Tracklets will suffice. To this end we build a tracking framework based on a HoG detector and an appearance-based particle filter. The detector is optimized by learning a scene model allowing for a speedup of the process together with a significantly reduced false positive rate. The developed system is applied in two different scenarios where it is shown that useful statistics can indeed be extracted.

AB - Automatic analysis of how people move about in a particular environment has a number of potential applications. However, no system has so far been able to do detection and tracking robustly. Instead, trajectories are often broken into tracklets. The key idea behind this paper is based around the notion that people need not be detected and tracked perfectly in order to derive useful movement statistics for a particular scene. Tracklets will suffice. To this end we build a tracking framework based on a HoG detector and an appearance-based particle filter. The detector is optimized by learning a scene model allowing for a speedup of the process together with a significantly reduced false positive rate. The developed system is applied in two different scenarios where it is shown that useful statistics can indeed be extracted.

UR - http://www.scopus.com/inward/record.url?scp=84864668512&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-31567-1_15

DO - 10.1007/978-3-642-31567-1_15

M3 - Article in proceeding

SN - 978-3-642-31566-4

T3 - Lecture Notes in Computer Science

SP - 153

EP - 162

BT - Articulated Motion and Deformable Objects

A2 - Perales, Francisco J.

A2 - Fisher, Robert B.

A2 - Moeslund, Thomas B.

PB - Springer Publishing Company

ER -

Ægidiussen Jensen T, Rasmussen HA, Moeslund TB. Automatic Estimation of Movement Statistics of People. In Perales FJ, Fisher RB, Moeslund TB, editors, Articulated Motion and Deformable Objects: 7th International Conference, AMDO 2012, Port d’Andratx, Mallorca, Spain, July 11-13, 2012. Proceedings. Springer Publishing Company. 2012. p. 153-162. (Lecture Notes in Computer Science, Vol. 7378). https://doi.org/10.1007/978-3-642-31567-1_15