Activity recognition in thermal infrared video

Author

Hossen, Jakir ; Jacobs, Eddie L. ; Chowdhury, Fahmida Kishowara

Author_Institution

Dept. of Electr. & Comput. Eng., Univ. of Memphis, Memphis, TN, USA

fYear

2015

fDate

9-12 April 2015

Firstpage

1

Lastpage

2

Abstract

In this paper, we investigate the tracking and recognition of limited activity in thermal infrared video. We have improved the pose segmentation from the background using a universal segmentation technique. Gait energy images (GEI) have been developed for collected repetitive and non-repetitive activities. Seven invariant moments features are extracted from the sequences of GEI of each activity and concatenated to a feature vector. Naïve Bayesians classifier is used for classification of feature vectors. Experimental result on limited activity shows the effectiveness of our proposed activity recognition algorithm.

Keywords

Bayes methods; image segmentation; infrared imaging; object recognition; pattern classification; pose estimation; video signal processing; GEI; activity recognition; feature vector; gait energy images; invariant moments features; naïve Bayesians classifier; nonrepetitive activities; pose segmentation; repetitive activities; thermal infrared video; universal segmentation technique; Bayes methods; Cameras; Computer vision; Feature extraction; Image segmentation; Motion segmentation; Surveillance; activity recognition; principle component analysis; segmentation; thermal infrared video; tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

SoutheastCon 2015

Conference_Location

Fort Lauderdale, FL

Type

conf

DOI

10.1109/SECON.2015.7132922

Filename

7132922