Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

MULTI‐VIEW HUMAN ACTIVITY RECOGNITION USING MOTION FREQUENCY

Abstract: 

The problem of human activity recognition can be approached using spatio-temporal variations in successive video frames. In this paper, a new human action recognition technique is proposed using multi-view videos. Initially, a naive background subtraction using frame differencing between adjacent frames of a video is performed. Then, the motion information of each pixel is recorded in binary indicating existence/nonexistence of motion in the frame. A pixel wise sum over all the difference images in a view gives the frequency of motion in each pixel throughout the clip. The classification performances are evaluated using these motion frequency features. Our analysis shows that increasing number of views used for feature extraction improves the performance as different views of an activity provide complementary information. Experiments on the i3DPost and the INRIA Xmas Motion Acquisition Sequences (IXMAS) multi-view human action datasets provide significant classification accuracies.

up
0 users have voted:

Paper Details

Authors:
Neslihan Köse, Mohammadreza Babaee, Gerhard Rigoll
Submitted On:
8 September 2017 - 4:27am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Mohammadreza Babaee
Document Year:
2017
Cite

Document Files

Poster for Paper ID 1443

(34 downloads)

Subscribe

[1] Neslihan Köse, Mohammadreza Babaee, Gerhard Rigoll, "MULTI‐VIEW HUMAN ACTIVITY RECOGNITION USING MOTION FREQUENCY", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1871. Accessed: Nov. 25, 2017.
@article{1871-17,
url = {http://sigport.org/1871},
author = {Neslihan Köse; Mohammadreza Babaee; Gerhard Rigoll },
publisher = {IEEE SigPort},
title = {MULTI‐VIEW HUMAN ACTIVITY RECOGNITION USING MOTION FREQUENCY},
year = {2017} }
TY - EJOUR
T1 - MULTI‐VIEW HUMAN ACTIVITY RECOGNITION USING MOTION FREQUENCY
AU - Neslihan Köse; Mohammadreza Babaee; Gerhard Rigoll
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1871
ER -
Neslihan Köse, Mohammadreza Babaee, Gerhard Rigoll. (2017). MULTI‐VIEW HUMAN ACTIVITY RECOGNITION USING MOTION FREQUENCY. IEEE SigPort. http://sigport.org/1871
Neslihan Köse, Mohammadreza Babaee, Gerhard Rigoll, 2017. MULTI‐VIEW HUMAN ACTIVITY RECOGNITION USING MOTION FREQUENCY. Available at: http://sigport.org/1871.
Neslihan Köse, Mohammadreza Babaee, Gerhard Rigoll. (2017). "MULTI‐VIEW HUMAN ACTIVITY RECOGNITION USING MOTION FREQUENCY." Web.
1. Neslihan Köse, Mohammadreza Babaee, Gerhard Rigoll. MULTI‐VIEW HUMAN ACTIVITY RECOGNITION USING MOTION FREQUENCY [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1871