Authors:
Lisa Gutzeit
1
and
Elsa Andrea Kirchner
2
Affiliations:
1
Universität Bremen, Germany
;
2
German Research Center for Artificial Intelligence (DFKI) and Universität Bremen, Germany
Keyword(s):
Human Movement Analysis, Behavior Segmentation, Behavior Recognition, Manipulation, Motion Tracking.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Collaboration and e-Services
;
Computer Vision, Visualization and Computer Graphics
;
Data Manipulation
;
e-Business
;
Enterprise Information Systems
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Methodologies and Methods
;
Motion and Tracking
;
Motion, Tracking and Stereo Vision
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Observation, Modeling and Prediction of User Behavior
;
Pattern Recognition
;
Physiological Computing Systems
;
Physiology-Driven Computer Interaction
;
Sensor Networks
;
Soft Computing
;
Software Engineering
;
Usability
;
Usability and Ergonomics
;
Web Information Systems and Technologies
;
Web Interfaces and Applications
Abstract:
Understanding human behavior is an active research area which plays an important role in robotic learning and human-computer interaction. The identification and recognition of behaviors is important in learning from demonstration scenarios to determine behavior sequences that should be learned by the system. Furthermore, behaviors need to be identified which are already available to the system and therefore do not need to be learned. Beside this, the determination of the current state of a human is needed in interaction tasks in order that a system can react to the human in an appropriate way. In this paper, characteristic movement patterns in human manipulation behavior are identified by decomposing the movement into its elementary building blocks using a fully automatic segmentation algorithm. Afterwards, the identified movement segments are assigned to known behaviors using k-Nearest Neighbor classification. The proposed approach is applied to pick-and-place and ball-throwing move
ments recorded by using a motion tracking system. It is shown that the proposed classification method outperforms the widely used Hidden Markov Model-based approaches in case of a small number of labeled training examples which considerably minimizes manual efforts.
(More)