Identification of humans using gait
Kale, Amit ; Sundaresan, Aravind ; Rajagopalan, A. N. ; Cuntoor, Naresh P. ; Roy-Chowdhury, Amit K. ; Krüger, Volker LU
and Chellappa, Rama
(2004)
In IEEE Transactions on Image Processing
13(9).
p.1163-1173
- Abstract
We propose a view-based approach to recognize humans from their gait. Two different image features have been considered: The width of the outer contour of the binarized silhouette of the walking person and the entire binary silhouette itself. To obtain the observation vector from the image features, we employ two different methods. In the first method, referred to as the indirect approach, the high-dimensional image feature is transformed to a lower dimensional space by generating what we call the frame to exemplar (FED) distance. The FED vector captures both structural and dynamic traits of each individual. For compact and effective gait representation and recognition, the gait information in the FED vector sequences is captured in a... (More)
We propose a view-based approach to recognize humans from their gait. Two different image features have been considered: The width of the outer contour of the binarized silhouette of the walking person and the entire binary silhouette itself. To obtain the observation vector from the image features, we employ two different methods. In the first method, referred to as the indirect approach, the high-dimensional image feature is transformed to a lower dimensional space by generating what we call the frame to exemplar (FED) distance. The FED vector captures both structural and dynamic traits of each individual. For compact and effective gait representation and recognition, the gait information in the FED vector sequences is captured in a hidden Markov model (HMM). In the second method, referred to as the direct approach, we work with the feature vector directly (as opposed to computing the FED) and train an HMM. We estimate the HMM parameters (specifically the observation probability B) based on the distance between the exemplars and the image features. In this way, we avoid learning high-dimensional probability density functions. The statistical nature of the HMM lends overall robustness to representation and recognition. The performance of the methods is illustrated using several databases.
(Less)
- author
- Kale, Amit
; Sundaresan, Aravind
; Rajagopalan, A. N.
; Cuntoor, Naresh P.
; Roy-Chowdhury, Amit K.
; Krüger, Volker
LU
and Chellappa, Rama
- publishing date
- 2004-09-01
- type
- Contribution to journal
- publication status
- published
- subject
- in
- IEEE Transactions on Image Processing
- volume
- 13
- issue
- 9
- pages
- 11 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- pmid:15449579
- scopus:4344637549
- ISSN
- 1057-7149
- DOI
- 10.1109/TIP.2004.832865
- language
- English
- LU publication?
- no
- id
- f7575cf9-99a0-4c4d-8eaa-a9a29abcfa5d
- date added to LUP
- 2019-07-08 21:21:13
- date last changed
- 2024-05-29 23:26:56
@article{f7575cf9-99a0-4c4d-8eaa-a9a29abcfa5d,
abstract = {{<p>We propose a view-based approach to recognize humans from their gait. Two different image features have been considered: The width of the outer contour of the binarized silhouette of the walking person and the entire binary silhouette itself. To obtain the observation vector from the image features, we employ two different methods. In the first method, referred to as the indirect approach, the high-dimensional image feature is transformed to a lower dimensional space by generating what we call the frame to exemplar (FED) distance. The FED vector captures both structural and dynamic traits of each individual. For compact and effective gait representation and recognition, the gait information in the FED vector sequences is captured in a hidden Markov model (HMM). In the second method, referred to as the direct approach, we work with the feature vector directly (as opposed to computing the FED) and train an HMM. We estimate the HMM parameters (specifically the observation probability B) based on the distance between the exemplars and the image features. In this way, we avoid learning high-dimensional probability density functions. The statistical nature of the HMM lends overall robustness to representation and recognition. The performance of the methods is illustrated using several databases.</p>}},
author = {{Kale, Amit and Sundaresan, Aravind and Rajagopalan, A. N. and Cuntoor, Naresh P. and Roy-Chowdhury, Amit K. and Krüger, Volker and Chellappa, Rama}},
issn = {{1057-7149}},
language = {{eng}},
month = {{09}},
number = {{9}},
pages = {{1163--1173}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{IEEE Transactions on Image Processing}},
title = {{Identification of humans using gait}},
url = {{http://dx.doi.org/10.1109/TIP.2004.832865}},
doi = {{10.1109/TIP.2004.832865}},
volume = {{13}},
year = {{2004}},
}