Activity Recognition Based on Multiple Motion Trajectories

Authors:
Junghye Min;Rangachar Kasturi
Affiliations:
The Pennsylvania State University, University Park, PA;The University of South Florida, Tampa, FL
Venue:
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
Year:
2004

Citing 0
Cited 6

Flexible signature descriptions for adaptive motion trajectory representation, perception and recognition

Pattern Recognition
Extraction and temporal segmentation of multiple motion trajectories in human motion

Image and Vision Computing
Motion trajectory reproduction from generalized signature description

Pattern Recognition
Event analysis based on multiple interactive motion trajectories

IEEE Transactions on Circuits and Systems for Video Technology
Recognition of human activities using SVM multi-class classifier

Pattern Recognition Letters
Real-time monitoring of water quality using temporal trajectory of live fish

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose an method for activity recognition based on multiple motion trajectories. Motion trajectotires generated from body parts (hand, feet, and joints) are used as features. We not only recognize each activity but also temporally locate the start and end point of its duration. Input sequences are divided into separate temporal segments based on the number of detected trajectories. Segments with same number of trajectories are temporally segmented using the HMM model for each movement (activity). The experimental results show that our approach can successfully locate each activity in continuous video sequences.