Paper Info
Title
Online pedestrian group walking event detection using spectral analysis of motion similarity graph
Abstract
A method for online identification of group of moving objects in the video is proposed in this paper. This method at each frame identifies group of tracked objects with similar local instantaneous motion pattern using spectral clustering on motion similarity graph. Then, the output of the algorithm is used to detect the event of more than two object moving together as required by PETS2015 challenge. The performance of the algorithm is evaluated on the PETS2015 dataset.
Year
DOI
Venue
2015
10.1109/AVSS.2015.7301744
2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
Keywords
Field
DocType
online pedestrian group walking event detection,spectral analysis,motion similarity graph,moving object group identification,object tracking,local instantaneous motion pattern,spectral clustering,PETS2015 dataset
Spectral clustering,Pedestrian,Computer science,Artificial intelligence,Cluster analysis,Trajectory,Computer vision,Graph,Pattern recognition,Kalman filter,Spectral analysis,Hidden Markov model,Machine learning
Conference
Citations 
PageRank 
References 
1
0.35
12
Authors
4
Name
Order
Citations
PageRank
Vahid Bastani1191.79
Damian Campo2166.41
Lucio Marcenaro340166.21
Carlo S. Regazzoni4609101.09