Spatio-temporal elastic cuboid trajectories for efficient fight recognition using Hough forests

While action recognition has become an important line of research in computer vision, the recognition of particular events such as aggressive behaviors, or fights, has been relatively less studied. These tasks may be exceedingly useful in some video surveillance scenarios such as psychiatric centers...

Full description

Saved in:
Bibliographic Details
Published in:Machine vision and applications 2018-02, Vol.29 (2), p.207-217
Main Authors: Serrano, Ismael, Deniz, Oscar, Bueno, Gloria, Garcia-Hernando, Guillermo, Kim, Tae-Kyun
Format: Article
Language:English
Subjects:
Communications Engineering
Computer Science
Computer vision
Datasets
Forests
Image Processing and Computer Vision
Networks
Original Paper
Pattern Recognition
Prisons
Recognition
Smartphones
Trajectories
Violence
Vision systems
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:While action recognition has become an important line of research in computer vision, the recognition of particular events such as aggressive behaviors, or fights, has been relatively less studied. These tasks may be exceedingly useful in some video surveillance scenarios such as psychiatric centers, prisons or even in personal camera smartphones. Their potential usability has caused a surge of interest in developing fight or violence detectors. The key aspect in this case is efficiency, that is, these methods should be computationally very fast. In this paper, spatio-temporal elastic cuboid trajectories are proposed for fight recognition. This method is based on the use of blob movements to create trajectories that capture and model the different motions that are specific to a fight. The proposed method is robust to the specific shapes and positions of the individuals. Additionally, the standard Hough forests classifier is adapted in order to use it with this descriptor. This method is compared to other nine related methods on four datasets. The results show that the proposed method obtains the best accuracy for each dataset and is also computationally efficient.
ISSN:0932-8092
1432-1769
DOI:10.1007/s00138-017-0894-7