Robust workflow recognition using holistic features and outlier-tolerant fused hidden Markov models

Authors:
Athanasios Voulodimos;Helmut Grabner;Dimitrios Kosmopoulos;Luc Van Gool;Theodora Varvarigou
Affiliations:
School of Electrical & Computer Engineering, National Technical University of Athens, Greece;Computer Vision Laboratory, ETH Zurich, Switzerland;Institute of Informatics and Telecommunications, N.C.S.R. Demokritos, Greece;Computer Vision Laboratory, ETH Zurich, Switzerland and ESAT-PSI, IBBT, K.U. Leuven, Belgium;School of Electrical & Computer Engineering, National Technical University of Athens, Greece
Venue:
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part I
Year:
2010

Citing 11
Cited 2

Recognition of Visual Activities and Interactions by Stochastic Parsing

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

IEEE Transactions on Pattern Analysis and Machine Intelligence
Beyond Tracking: Modelling Activity and Understanding Behaviour

International Journal of Computer Vision
On-line Boosting and Vision

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Statistical Analysis of Dynamic Actions

IEEE Transactions on Pattern Analysis and Machine Intelligence
Free viewpoint action recognition using motion history volumes

Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Detecting abnormal human behaviour using multiple cameras

Signal Processing
Robust Sequential Data Modeling Using an Outlier Tolerant Hidden Markov Model

IEEE Transactions on Pattern Analysis and Machine Intelligence
Audio-visual speech modeling for continuous speech recognition

IEEE Transactions on Multimedia
Audio–Visual Affective Expression Recognition Through Multistream Fused HMM

IEEE Transactions on Multimedia
Automatic video-based human motion analyzer for consumer surveillance system

IEEE Transactions on Consumer Electronics

Bayesian filter based behavior recognition in workflows allowing for user feedback

Computer Vision and Image Understanding
2011 Special Issue: Online classification of visual tasks for industrial workflow monitoring

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Monitoring real world environments such as industrial scenes is a challenging task due to heavy occlusions, resemblance of different processes, frequent illumination changes, etc. We propose a robust framework for recognizing workflows in such complex environments, boasting a threefold contribution: Firstly, we employ a novel holistic scene descriptor to efficiently and robustly model complex scenes, thus bypassing the very challenging tasks of target recognition and tracking. Secondly, we handle the problem of limited visibility and occlusions by exploiting redundancies through the use of merged information from multiple cameras. Finally, we use the multivariate Student-t distribution as the observation likelihood of the employed Hidden Markov Models, in order to further enhance robustness.We evaluate the performance of the examined approaches under real-life visual behavior understanding scenarios and we compare and discuss the obtained results.