Human activity recognition with action primitives

Authors:
Zsolt L. Husz;Andrew M. Wallace;Patrick R. Green
Affiliations:
Joint Research Institute in Signal and Image Processing, School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh, UK;Joint Research Institute in Signal and Image Processing, School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh, UK;School of Life Sciences, Heriot-Watt University, Edinburgh, UK
Venue:
AVSS '07 Proceedings of the 2007 IEEE Conference on Advanced Video and Signal Based Surveillance
Year:
2007

Citing 0
Cited 5

Collaborative signal processing for action recognition in body sensor networks: a distributed classification algorithm using motion transcripts

Proceedings of the 9th ACM/IEEE International Conference on Information Processing in Sensor Networks
Structural action recognition in body sensor networks: distributed classification based on string matching

IEEE Transactions on Information Technology in Biomedicine - Special section on affective and pervasive computing for healthcare
Behavior-oriented data resource management in medical sensing systems

ACM Transactions on Sensor Networks (TOSN)
Physical activity recognition using multiple sensors embedded in a wearable device

ACM Transactions on Embedded Computing Systems (TECS) - Special issue on embedded systems for interactive multimedia services (ES-IMS)
Charting-based subspace learning for video-based human action classification

Machine Vision and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper considers the link between tracking algorithms and high-level human behavioural analysis, introducing the action primitives model that recovers symbolic labels from tracked limb configurations. The model consists of similar short-term actions, action primitives clusters, formed automatically and then labelled by supervised learning. The model allows both short actions and longer activities, either periodic or aperiodic. New labels are added incrementally. We determine the effects of model parameters on the labelling of action primitives using ground truth derived from a motion capture system. We also present a representative example of a labelled video sequence.