Automatic gait recognition based on probabilistic approach

Imran Fareed Nizami, Sungjun Hong, Heesung Lee, Byungyun Lee, Euntai Kim

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A simple probabilistic method for online video based human identification is introduced in this article. The proposed method is based on a modified version of Motion Silhouette images (MSI) and recursive probability accumulation. The modified version of MSI is named the Moving Motion Silhouette Image (MMSI). Identification probability is accumulated recursively in a Bayesian framework to draw a single conclusion from the whole gait sequence. The probability is named the accumulated posterior probability (APP) and denotes the probability based on all the information available up to now. The proposed method is tested on the well-known publicly available NLPR and SOTON gait databases. The experimental results demonstrate the effectiveness of the proposed algorithm and indicate the fact that using MMSI and APP for information fusion yields higher recognition rates as compared to previous gait recognition systems.

Original languageEnglish
Pages (from-to)400-408
Number of pages9
JournalInternational Journal of Imaging Systems and Technology
Volume20
Issue number4
DOIs
Publication statusPublished - 2010 Dec 1

Fingerprint

Information fusion

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Software
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Nizami, Imran Fareed ; Hong, Sungjun ; Lee, Heesung ; Lee, Byungyun ; Kim, Euntai. / Automatic gait recognition based on probabilistic approach. In: International Journal of Imaging Systems and Technology. 2010 ; Vol. 20, No. 4. pp. 400-408.
@article{ea9d3935a7e94c45aa9433fae6f8f7fa,
title = "Automatic gait recognition based on probabilistic approach",
abstract = "A simple probabilistic method for online video based human identification is introduced in this article. The proposed method is based on a modified version of Motion Silhouette images (MSI) and recursive probability accumulation. The modified version of MSI is named the Moving Motion Silhouette Image (MMSI). Identification probability is accumulated recursively in a Bayesian framework to draw a single conclusion from the whole gait sequence. The probability is named the accumulated posterior probability (APP) and denotes the probability based on all the information available up to now. The proposed method is tested on the well-known publicly available NLPR and SOTON gait databases. The experimental results demonstrate the effectiveness of the proposed algorithm and indicate the fact that using MMSI and APP for information fusion yields higher recognition rates as compared to previous gait recognition systems.",
author = "Nizami, {Imran Fareed} and Sungjun Hong and Heesung Lee and Byungyun Lee and Euntai Kim",
year = "2010",
month = "12",
day = "1",
doi = "10.1002/ima.20256",
language = "English",
volume = "20",
pages = "400--408",
journal = "International Journal of Imaging Systems and Technology",
issn = "0899-9457",
publisher = "John Wiley and Sons Inc.",
number = "4",

}

Automatic gait recognition based on probabilistic approach. / Nizami, Imran Fareed; Hong, Sungjun; Lee, Heesung; Lee, Byungyun; Kim, Euntai.

In: International Journal of Imaging Systems and Technology, Vol. 20, No. 4, 01.12.2010, p. 400-408.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automatic gait recognition based on probabilistic approach

AU - Nizami, Imran Fareed

AU - Hong, Sungjun

AU - Lee, Heesung

AU - Lee, Byungyun

AU - Kim, Euntai

PY - 2010/12/1

Y1 - 2010/12/1

N2 - A simple probabilistic method for online video based human identification is introduced in this article. The proposed method is based on a modified version of Motion Silhouette images (MSI) and recursive probability accumulation. The modified version of MSI is named the Moving Motion Silhouette Image (MMSI). Identification probability is accumulated recursively in a Bayesian framework to draw a single conclusion from the whole gait sequence. The probability is named the accumulated posterior probability (APP) and denotes the probability based on all the information available up to now. The proposed method is tested on the well-known publicly available NLPR and SOTON gait databases. The experimental results demonstrate the effectiveness of the proposed algorithm and indicate the fact that using MMSI and APP for information fusion yields higher recognition rates as compared to previous gait recognition systems.

AB - A simple probabilistic method for online video based human identification is introduced in this article. The proposed method is based on a modified version of Motion Silhouette images (MSI) and recursive probability accumulation. The modified version of MSI is named the Moving Motion Silhouette Image (MMSI). Identification probability is accumulated recursively in a Bayesian framework to draw a single conclusion from the whole gait sequence. The probability is named the accumulated posterior probability (APP) and denotes the probability based on all the information available up to now. The proposed method is tested on the well-known publicly available NLPR and SOTON gait databases. The experimental results demonstrate the effectiveness of the proposed algorithm and indicate the fact that using MMSI and APP for information fusion yields higher recognition rates as compared to previous gait recognition systems.

UR - http://www.scopus.com/inward/record.url?scp=78649596354&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649596354&partnerID=8YFLogxK

U2 - 10.1002/ima.20256

DO - 10.1002/ima.20256

M3 - Article

VL - 20

SP - 400

EP - 408

JO - International Journal of Imaging Systems and Technology

JF - International Journal of Imaging Systems and Technology

SN - 0899-9457

IS - 4

ER -