Gait recognition using low spatial and temporal resolution videos

Due to limited transmission bandwidth and storage capacity, the gait sequences captured by a Closed Circuit Television (CCTV) camera are recorded at low frame-rates with low spatial resolution, which significantly affect the performance of a gait recognition method. Thus, this paper proposes a gait...

Full description

Saved in:
Bibliographic Details
Published in2nd International Workshop on Biometrics and Forensics pp. 1 - 6
Main Authors Das Choudhury, Sruti, Yu Guan, Chang-Tsun Li
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.03.2014
Subjects
Cameras
dual-tree complex wavelet transform
gait keyframe image
Gait recognition
Image reconstruction
Probes
Procrustes image distance
Spatial resolution
Video sequences
weighted Krawtchouk moments
Online AccessGet full text
DOI10.1109/IWBF.2014.6914252

Cover

More Information
Summary:Due to limited transmission bandwidth and storage capacity, the gait sequences captured by a Closed Circuit Television (CCTV) camera are recorded at low frame-rates with low spatial resolution, which significantly affect the performance of a gait recognition method. Thus, this paper proposes a gait recognition method which uses dual-tree complex wavelet transform for spatial resolution enhancement of the input low resolution silhouettes. To achieve invariance to low frame-rate gait sequences, the method determines seven key frames from a gait sequence based on silhouette matching by weighted Krawtchouk moments to form a Gait Keyframe Image (GKI). The subjects are identified based on a similarity score obtained by Procrustes image distance between the gallery and probe GKIs. Experimental analysis on OU-ISIR gait dataset D demonstrates the efficacy of the method.
DOI:10.1109/IWBF.2014.6914252