2.5D gait biometrics using the Depth Gradient Histogram Energy Image

Martin Hofmann; Sebastian Bachmann; Gerhard Rigoll

doi:10.1109/BTAS.2012.6374606

2.5D gait biometrics using the Depth Gradient Histogram Energy Image

Martin Hofmann, Sebastian Bachmann, Gerhard Rigoll

Chair of Human-Machine Communication

Technical University of Munich

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

79 Scopus citations

Abstract

Using gait recognition methods, people can be identified by the way they walk. The most successful and efficient of these methods are based on the Gait Energy Image (GEI). In this paper, we extend the traditional Gait Energy Image by including depth information. First, GEI is extended by calculating the required silhouettes using depth data. We then formulate a completely new feature, which we call the Depth Gradient Histogram Energy Image (DGHEI). We compare the improved depth-GEI and the new DGHEI to the traditional GEI. We do this using a new gait database which was recorded with the Kinect sensor. On this database we show significant performance gain of DGHEI.

Original language	English
Title of host publication	2012 IEEE 5th International Conference on Biometrics
Subtitle of host publication	Theory, Applications and Systems, BTAS 2012
Pages	399-403
Number of pages	5
DOIs	https://doi.org/10.1109/BTAS.2012.6374606
State	Published - 2012
Event	2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012 - Arlington, VA, United States Duration: 23 Sep 2012 → 27 Sep 2012

Publication series

Name	2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012

Conference

Conference	2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012
Country/Territory	United States
City	Arlington, VA
Period	23/09/12 → 27/09/12

Access to Document

10.1109/BTAS.2012.6374606

Cite this

Hofmann, M., Bachmann, S., & Rigoll, G. (2012). 2.5D gait biometrics using the Depth Gradient Histogram Energy Image. In 2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012 (pp. 399-403). Article 6374606 (2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012). https://doi.org/10.1109/BTAS.2012.6374606

@inproceedings{54e142d8e33e4557b6e319879677d41f,

title = "2.5D gait biometrics using the Depth Gradient Histogram Energy Image",

abstract = "Using gait recognition methods, people can be identified by the way they walk. The most successful and efficient of these methods are based on the Gait Energy Image (GEI). In this paper, we extend the traditional Gait Energy Image by including depth information. First, GEI is extended by calculating the required silhouettes using depth data. We then formulate a completely new feature, which we call the Depth Gradient Histogram Energy Image (DGHEI). We compare the improved depth-GEI and the new DGHEI to the traditional GEI. We do this using a new gait database which was recorded with the Kinect sensor. On this database we show significant performance gain of DGHEI.",

author = "Martin Hofmann and Sebastian Bachmann and Gerhard Rigoll",

year = "2012",

doi = "10.1109/BTAS.2012.6374606",

language = "English",

isbn = "9781467313841",

series = "2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012",

pages = "399--403",

booktitle = "2012 IEEE 5th International Conference on Biometrics",

note = "2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012 ; Conference date: 23-09-2012 Through 27-09-2012",

}

Hofmann, M, Bachmann, S & Rigoll, G 2012, 2.5D gait biometrics using the Depth Gradient Histogram Energy Image. in 2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012., 6374606, 2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012, pp. 399-403, 2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012, Arlington, VA, United States, 23/09/12. https://doi.org/10.1109/BTAS.2012.6374606

2.5D gait biometrics using the Depth Gradient Histogram Energy Image. / Hofmann, Martin; Bachmann, Sebastian; Rigoll, Gerhard.
2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012. 2012. p. 399-403 6374606 (2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - 2.5D gait biometrics using the Depth Gradient Histogram Energy Image

AU - Hofmann, Martin

AU - Bachmann, Sebastian

AU - Rigoll, Gerhard

PY - 2012

Y1 - 2012

N2 - Using gait recognition methods, people can be identified by the way they walk. The most successful and efficient of these methods are based on the Gait Energy Image (GEI). In this paper, we extend the traditional Gait Energy Image by including depth information. First, GEI is extended by calculating the required silhouettes using depth data. We then formulate a completely new feature, which we call the Depth Gradient Histogram Energy Image (DGHEI). We compare the improved depth-GEI and the new DGHEI to the traditional GEI. We do this using a new gait database which was recorded with the Kinect sensor. On this database we show significant performance gain of DGHEI.

AB - Using gait recognition methods, people can be identified by the way they walk. The most successful and efficient of these methods are based on the Gait Energy Image (GEI). In this paper, we extend the traditional Gait Energy Image by including depth information. First, GEI is extended by calculating the required silhouettes using depth data. We then formulate a completely new feature, which we call the Depth Gradient Histogram Energy Image (DGHEI). We compare the improved depth-GEI and the new DGHEI to the traditional GEI. We do this using a new gait database which was recorded with the Kinect sensor. On this database we show significant performance gain of DGHEI.

UR - http://www.scopus.com/inward/record.url?scp=84871975250&partnerID=8YFLogxK

U2 - 10.1109/BTAS.2012.6374606

DO - 10.1109/BTAS.2012.6374606

M3 - Conference contribution

AN - SCOPUS:84871975250

SN - 9781467313841

T3 - 2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012

SP - 399

EP - 403

BT - 2012 IEEE 5th International Conference on Biometrics

T2 - 2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems, BTAS 2012

Y2 - 23 September 2012 through 27 September 2012

ER -

2.5D gait biometrics using the Depth Gradient Histogram Energy Image

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this