Handbook on Ontologies (International Handbooks on Information Systems)
Handbook on Ontologies (International Handbooks on Information Systems)
Description of interest regions with local binary patterns
Pattern Recognition
An ontology based approach for activity recognition from video
MM '08 Proceedings of the 16th ACM international conference on Multimedia
Human activity analysis: A review
ACM Computing Surveys (CSUR)
Local binary patterns for multi-view facial expression recognition
Computer Vision and Image Understanding
A survey of semantic image and video annotation tools
Knowledge-driven multimedia information extraction and ontology evolution
Real-time human pose recognition in parts from single depth images
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Efficiently Scaling up Crowdsourced Video Annotation
International Journal of Computer Vision
| Hi-index | 0.00 |
In this paper we introduce the current results of an ongoing three-year research and development project on automatic annotation of human nonverbal behavior. The present output of the project is a tool that provides algorithms and graphical user interface for the generation of ground-truth data about the subset of facial and body activities. These data are essential for the experts who are committed to unraveling the complexity of the linkage between the psychophysiological state and the nonverbal behavior of a human. Our work relied on a Kinect sensor, which computes depth maps together with the coordinates of the body joints and facial points. Local binary patterns are then extracted from the regions of interests of a facial video, which are either spatio-temporally aligned with the depth maps or calculated using the Active Shape Model. Another key idea of the proposed tool is that the extracted feature vector is semantically associated with ontological concepts in perspective providing annotations for most of the nonverbal activities.