Please use this identifier to cite or link to this item: http://essuir.sumdu.edu.ua/handle/123456789/55650
Or use following links to share this resource in social networks: Recommend this item
Title Gait recognition on base of representation in spatiotemporal area
Authors Babii, Mykhailo Semenovych  
Keywords gait
recognition
Gabor wavelets
CASIA database
Type Conference Papers
Date of Issue 2017
URI http://essuir.sumdu.edu.ua/handle/123456789/55650
Publisher Sumy State University
License
Citation Babiy, M. Gait recognition on base of representation in spatiotemporal area [Текст] / M. Babiy // Advanced Information Systems and Technologies : proceedings of the V international scientific conference, Sumy, May 17-19 2017/ Edited by S.І. Protsenko, V.V. Shendryk. - Sumy : Sumy State University, 2017. - P. 89-91.
Abstract New method of automatic gait recognition from video is proposed. The method works with a sequence of silhouettes derived from the video after background subtraction, decreasing shadows and noise. Two-dimensional silhouette shape is converted into one-dimensional signal presenting distance from center of gravity to outline of this silhouette. A set of signals extracted from a sequence of silhouettes forms a two-dimensional picture. The features extraction is performed using Gabor wavelets. Testing the method on the samples of CASIA gait database showed high recognition accuracy.
Appears in Collections: Наукові видання (ЕлІТ)

Views

China China
1
France France
3
Germany Germany
77
Italy Italy
2
Lithuania Lithuania
1
Netherlands Netherlands
3159
Sweden Sweden
1
Ukraine Ukraine
1531
United Kingdom United Kingdom
12635
United States United States
1525
Unknown Country Unknown Country
17

Downloads

China China
2
Cuba Cuba
1
Germany Germany
2
India India
1
Nigeria Nigeria
1
Slovenia Slovenia
1
Ukraine Ukraine
1529
United Kingdom United Kingdom
1
United States United States
3158
Unknown Country Unknown Country
7

Files

File Size Format Downloads
Babiy_GAit.pdf 524,72 kB Adobe PDF 4703

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.