Human action recognition by conceptual features
Loading...
Other Title
Authors
Shamsipour, G.
Shanbehzadeh, J.
Sarrafzadeh, Hossein
Shanbehzadeh, J.
Sarrafzadeh, Hossein
Author ORCID Profiles (clickable)
Degree
Grantor
Date
2017-03
Supervisors
Type
Conference Contribution - Paper in Published Proceedings
Ngā Upoko Tukutuku (Māori subject headings)
Keyword
computer vision
human activity recognition
Convolutional Neural Network (CNN)
support vector machine
human activity recognition
Convolutional Neural Network (CNN)
support vector machine
ANZSRC Field of Research Code (2020)
Citation
Shamsipour, G., Shanbehzadeh, J., & Sarrafzadeh, A. (2017, March). Human action recognition by conceptual features. S. I. Ao., O. Castillo., C. Douglas., D. D. Feng & A. M. Korsunsky (Ed.), International MultiConference of Engineers and Computer Scientists 2017 (IMECS2017) (pp.online). 1.
Abstract
Human action recognition is the process of labeling a video according to human behavior. This process requires a large set of labeled video and analyzing all the frames of a video. The consequence is high computation and memory requirement.
This paper solves these problems by focusing on a limited set rather than all the human action and considering the human-object interaction. This paper employs three randomly selected video frames instead of employing all the frames and, Convolutional Neural Network extracts conceptual features and recognize the video objects. Finally, support vector machine determines the relation between these objects and labels the video. The proposed method have been tested on two popular datasets ; UCF Sports Action and Olympic Sports. The results show improvements over state-of-the-art algorithms.
This work is the outcome of Shamsipour's M.Sc thesis at Kharazmi University.
Publisher
Newswood and International Association of Engineers
Permanent link
Link to ePress publication
DOI
Copyright holder
Authors
Copyright notice
All rights reserved