Title :
Gait recognition based on Hidden Markov models
Author_Institution :
Sch. of Inf. Sci. & Eng., Northeastern Univ., Shenyang, China
Abstract :
In this paper, proposed a method for gait recognition based on the HMM. In this method sparse presentation is used and experience is done in CASIA B database, and all the study are based on this database. Firstly, a gait silhouette or feature cycle is divided into several temporally adjacent clusters. Each cluster is calculated and gets several adjacent PFDEI binary images. Secondly, Hidden Markov mode (HMM) is built to describe the relationship among the PFDEI. Finally, sparse representation is applied to analyze binary image to learning its parameters. Experimental results show that such methods to be identified effective.
Keywords :
feature extraction; gait analysis; hidden Markov models; image motion analysis; image recognition; learning (artificial intelligence); visual databases; CASIA B database; HMM; adjacent PFDEI binary images; feature cycle; frame difference energy image; gait recognition; gait silhouette; hidden Markov model; sparse presentation; temporally adjacent clusters; Decision support systems; Handheld computers; Mechatronics; HMM; KPCA; PFDEI; dictinary; sparse representation;
Conference_Titel :
Mechatronic Science, Electric Engineering and Computer (MEC), 2011 International Conference on
Conference_Location :
Jilin
Print_ISBN :
978-1-61284-719-1
DOI :
10.1109/MEC.2011.6025745
