Facial communicative signal interpretation in human-robot interaction by discriminative video subsequence selection

Lang, C. and Wachsmuth, S. and Hanheide, M. and Wersing, H. (2013) Facial communicative signal interpretation in human-robot interaction by discriminative video subsequence selection. In: IEEE International Conference on Robotics and Automation, ICRA 2013, Germany; 6 - 10 May 2013, Karlsruhe; Germany.

Full content URL: http://dx.doi.org/10.1109/ICRA.2013.6630572

Documents
06630572.pdf
[img] PDF
06630572.pdf - Whole Document
Restricted to Repository staff only

494kB
Item Type:Conference or Workshop contribution (Presentation)
Item Status:Live Archive

Abstract

Facial communicative signals (FCSs) such as head gestures, eye gaze, and facial expressions can provide useful feedback in conversations between people and also in human-robot interaction. This paper presents a pattern recognition approach for the interpretation of FCSs in terms of valence, based on the selection of discriminative subsequences in video data. These subsequences capture important temporal dynamics and are used as prototypical reference subsequences in a classification procedure based on dynamic time warping and feature extraction with active appearance models. Using this valence classification, the robot can discriminate positive from negative interaction situations and react accordingly. The approach is evaluated on a database containing videos of people interacting with a robot by teaching the names of several objects to it. The verbal answer of the robot is expected to elicit the display of spontaneous FCSs by the human tutor, which were classified in this work. The achieved classification accuracies are comparable to the average human recognition performance and outperformed our previous results on this task. © 2013 IEEE.

Additional Information:Conference Code:100673
Keywords:Active appearance models, Classification accuracy, Classification procedure, Facial Expressions, Human recognition, Negative interaction, Signal interpretation, Temporal dynamics, Feature extraction, Human computer interaction, Human robot interaction, Man machine systems, Robotics
Subjects:G Mathematical and Computer Sciences > G440 Human-computer Interaction
Divisions:College of Science > School of Computer Science
ID Code:13462
Deposited On:05 Mar 2014 17:35

Repository Staff Only: item control page