Online Pedestrian Group Walking Event Detection Using Spectral Analysis of Motion Similarity Graph
Computer Vision and Pattern Recognition
2019-09-04 v1 Image and Video Processing
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.
Keywords
Cite
@article{arxiv.1909.01258,
title = {Online Pedestrian Group Walking Event Detection Using Spectral Analysis of Motion Similarity Graph},
author = {Vahid Bastani and Damian Campo and Lucio Marcenaro and Carlo S. Regazzoni},
journal= {arXiv preprint arXiv:1909.01258},
year = {2019}
}
Comments
Published in: 2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)