Non Parametric Classification of Human Interaction

Authors:
Scott Blunsden;Ernesto Andrade;Robert Fisher
Affiliations:
Institute of Perception Action and Behaviour, School of Informatics, University of Edinburgh, UK;Institute of Perception Action and Behaviour, School of Informatics, University of Edinburgh, UK;Institute of Perception Action and Behaviour, School of Informatics, University of Edinburgh, UK
Venue:
IbPRIA '07 Proceedings of the 3rd Iberian conference on Pattern Recognition and Image Analysis, Part II
Year:
2007

Citing 5
Cited 2

A Bayesian Computer Vision System for Modeling Human Interactions

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Recognition of Human Movement Using Temporal Templates

IEEE Transactions on Pattern Analysis and Machine Intelligence
Tracking and Recognizing Two-Person Interactions in Outdoor Image Sequences

WOMOT '01 Proceedings of the IEEE Workshop on Multi-Object Tracking (WOMOT'01)
Recognition of Group Activities using Dynamic Probabilistic Networks

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Recognizing Interaction Activities using Dynamic Bayesian Network

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 01

Recognition of long-term behaviors by parsing sequences of short-term actions with a stochastic regular grammar

SSPR'12/SPR'12 Proceedings of the 2012 Joint IAPR international conference on Structural, Syntactic, and Statistical Pattern Recognition
A survey of video datasets for human action and activity recognition

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a non parametric method for classifying interactions between two people as taken from a video camera. A nearest neighbour classifier that uses trajectory matching in feature space is introduced and shown to be superior to regular nearest neighbour classification for this problem.