Human action recognition in table-top scenarios: an HMM-based analysis to optimize the performance

Authors:
Pradeep Reddy Raamana;Daniel Grest;Volker Krueger
Affiliations:
Computer Vision and Machine Intelligence, Copenhagen Institute of Technology, Aalborg University, Denmark;Computer Vision and Machine Intelligence, Copenhagen Institute of Technology, Aalborg University, Denmark;Computer Vision and Machine Intelligence, Copenhagen Institute of Technology, Aalborg University, Denmark
Venue:
CAIP'07 Proceedings of the 12th international conference on Computer analysis of images and patterns
Year:
2007

Citing 7
Cited 3

Human motion analysis: a review

Computer Vision and Image Understanding
Sensory-motor primitives as a basis for imitation: linking perception to action and biology to robotics

Imitation in animals and artifacts
Recognition of human body motion using phase space constraints

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Optimizing the Number of States, Training Iterations and Gaussians in an HMM-based Handwritten Word Recognizer

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
A survey of advances in vision-based human motion capture and analysis

Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Using hidden Markov models for recognizing action primitives in complex actions

SCIA'07 Proceedings of the 15th Scandinavian conference on Image analysis
Single view motion tracking by depth and silhouette information

SCIA'07 Proceedings of the 15th Scandinavian conference on Image analysis

View-invariant gesture recognition using 3D optical flow and harmonic motion context

Computer Vision and Image Understanding
Learning the semantics of object-action relations by observation

International Journal of Robotics Research
Tracking in object action space

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

Hidden Markov models have been extensively and successfully used for the recognition of human actions. Though there exist well-established algorithms to optimize the transition and output probabilities, the type of features to use and specifically the number of states and Gaussian have to be chosen manually. Here we present a quantitative study on selecting the optimal feature set for recognition of simple object manipulation actions pointing, rotating and grasping in a table-top scenario. This study has resulted in recognition rate higher than 90%. Also three different parameters, namely the number of states and Gaussian for HMM and the number of training iterations, are considered for optimization of the recognition rate with 5 different feature sets on our motion capture data set from 10 persons.