Classification of Gait Types Based on the Duty-factor

Preben Fihl, Thomas B. Moeslund

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

6 Citations (Scopus)
2095 Downloads (Pure)

Abstract

This paper deals with classification of human gait types based on the notion that different gait types are in fact different types of locomotion, i.e., running is not simply walking done faster. We present the duty-factor, which is a descriptor based on this notion. The duty-factor is independent on the speed of the human, the cameras setup etc. and hence a robust descriptor for gait classification. The dutyfactor is basically a matter of measuring the ground support of the feet with respect to the stride. We estimate this by comparing the incoming silhouettes to a database of silhouettes with known ground support. Silhouettes are extracted using the Codebook method and represented using Shape Contexts. The matching with database silhouettes is done using the Hungarian method. While manually estimated duty-factors show a clear classification the presented system contains misclassifications due to silhouette noise and ambiguities in the database silhouettes.

Original languageEnglish
Title of host publicationIEEE Conference on Advanced Video and Signal Based Surveillance, 2007. AVSS 2007
Number of pages6
PublisherIEEE Computer Society Press
Publication date2007
ISBN (Electronic)9781424416967
DOIs
Publication statusPublished - 2007
EventIEEE Conference on Advanced Video and Signal Based Surveillance - London, United Kingdom
Duration: 5 Sep 20077 Sep 2007
Conference number: 6

Conference

ConferenceIEEE Conference on Advanced Video and Signal Based Surveillance
Number6
CountryUnited Kingdom
CityLondon
Period05/09/200707/09/2007

Fingerprint

Ground supports
Cameras

Keywords

  • Computer Vision
  • Action Recognition
  • Gait Analysis

Cite this

Fihl, P., & Moeslund, T. B. (2007). Classification of Gait Types Based on the Duty-factor. In IEEE Conference on Advanced Video and Signal Based Surveillance, 2007. AVSS 2007 IEEE Computer Society Press. https://doi.org/10.1109/AVSS.2007.4425330
Fihl, Preben ; Moeslund, Thomas B. / Classification of Gait Types Based on the Duty-factor. IEEE Conference on Advanced Video and Signal Based Surveillance, 2007. AVSS 2007. IEEE Computer Society Press, 2007.
@inproceedings{3509ed2062c311dcb024000ea68e967b,
title = "Classification of Gait Types Based on the Duty-factor",
abstract = "This paper deals with classification of human gait types based on the notion that different gait types are in fact different types of locomotion, i.e., running is not simply walking done faster. We present the duty-factor, which is a descriptor based on this notion. The duty-factor is independent on the speed of the human, the cameras setup etc. and hence a robust descriptor for gait classification. The dutyfactor is basically a matter of measuring the ground support of the feet with respect to the stride. We estimate this by comparing the incoming silhouettes to a database of silhouettes with known ground support. Silhouettes are extracted using the Codebook method and represented using Shape Contexts. The matching with database silhouettes is done using the Hungarian method. While manually estimated duty-factors show a clear classification the presented system contains misclassifications due to silhouette noise and ambiguities in the database silhouettes.",
keywords = "Computer Vision, Action Recognition, Gait Analysis",
author = "Preben Fihl and Moeslund, {Thomas B.}",
year = "2007",
doi = "10.1109/AVSS.2007.4425330",
language = "English",
booktitle = "IEEE Conference on Advanced Video and Signal Based Surveillance, 2007. AVSS 2007",
publisher = "IEEE Computer Society Press",
address = "United States",

}

Fihl, P & Moeslund, TB 2007, Classification of Gait Types Based on the Duty-factor. in IEEE Conference on Advanced Video and Signal Based Surveillance, 2007. AVSS 2007. IEEE Computer Society Press, London, United Kingdom, 05/09/2007. https://doi.org/10.1109/AVSS.2007.4425330

Classification of Gait Types Based on the Duty-factor. / Fihl, Preben; Moeslund, Thomas B.

IEEE Conference on Advanced Video and Signal Based Surveillance, 2007. AVSS 2007. IEEE Computer Society Press, 2007.

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

TY - GEN

T1 - Classification of Gait Types Based on the Duty-factor

AU - Fihl, Preben

AU - Moeslund, Thomas B.

PY - 2007

Y1 - 2007

N2 - This paper deals with classification of human gait types based on the notion that different gait types are in fact different types of locomotion, i.e., running is not simply walking done faster. We present the duty-factor, which is a descriptor based on this notion. The duty-factor is independent on the speed of the human, the cameras setup etc. and hence a robust descriptor for gait classification. The dutyfactor is basically a matter of measuring the ground support of the feet with respect to the stride. We estimate this by comparing the incoming silhouettes to a database of silhouettes with known ground support. Silhouettes are extracted using the Codebook method and represented using Shape Contexts. The matching with database silhouettes is done using the Hungarian method. While manually estimated duty-factors show a clear classification the presented system contains misclassifications due to silhouette noise and ambiguities in the database silhouettes.

AB - This paper deals with classification of human gait types based on the notion that different gait types are in fact different types of locomotion, i.e., running is not simply walking done faster. We present the duty-factor, which is a descriptor based on this notion. The duty-factor is independent on the speed of the human, the cameras setup etc. and hence a robust descriptor for gait classification. The dutyfactor is basically a matter of measuring the ground support of the feet with respect to the stride. We estimate this by comparing the incoming silhouettes to a database of silhouettes with known ground support. Silhouettes are extracted using the Codebook method and represented using Shape Contexts. The matching with database silhouettes is done using the Hungarian method. While manually estimated duty-factors show a clear classification the presented system contains misclassifications due to silhouette noise and ambiguities in the database silhouettes.

KW - Computer Vision

KW - Action Recognition

KW - Gait Analysis

U2 - 10.1109/AVSS.2007.4425330

DO - 10.1109/AVSS.2007.4425330

M3 - Article in proceeding

BT - IEEE Conference on Advanced Video and Signal Based Surveillance, 2007. AVSS 2007

PB - IEEE Computer Society Press

ER -

Fihl P, Moeslund TB. Classification of Gait Types Based on the Duty-factor. In IEEE Conference on Advanced Video and Signal Based Surveillance, 2007. AVSS 2007. IEEE Computer Society Press. 2007 https://doi.org/10.1109/AVSS.2007.4425330