ABSTRACT
In this paper, a novel vision system is proposed to estimate attention of people from rich visual clues for social robot to perform natural interactions with multiple participants in public environments. The vision detection and recognition modules include multi-person detection and tracking, upper-body pose recognition, face and gaze detection, lip motion analysis for speaking recognition, and facial expression recognition. A computational approach is proposed to generate a quantitative estimation of human attention. The vision system is implemented on a robotic receptionist "EVE" and encouraging results have been obtained.
Supplemental Material
- X. Feng, M. Pietikäinen, and A. Hadid. Facial expression recognition with local binary patterns and linear programming. In 7th International Conference on Pattern Recognition and Image Analysis: New Information Technologies (PRIA-7), 2004.Google Scholar
- L. Li, K. E. Hoe, S. Yan, and X. Yu. Ml-fusion based multi-model human detection and tracking for robust human-robot interfaces. In IEEE Workshop on Applications of Computer Vision (WACV), 2009.Google ScholarCross Ref
- L. Li, K. E. Hoe, X. Yu, L. Dong, and X. Chu. Human upper body pose recognition using adaboost template for natural human robot interaction. In Seventh Canadian Conference on Computer and Robot Vision (CRV), 2010. Google ScholarDigital Library
- X. Yu, W. Han, L. Li, J. Y. Shi, and G. Wang. An eye detection and localization system for natural human and robot interaction without face detection. In 12th Conference Towards Autonomous Robotic Systems (TAROS), 2011. Google ScholarDigital Library
Index Terms
- Vision-based attention estimation and selection for social robot to perform natural interaction in the open world
Recommendations
Attention-based addressee selection for service and social robots to interact with multiple persons
WASA '12: Proceedings of the Workshop at SIGGRAPH AsiaFor robots to perform interaction with multiple persons, they have to be able to identify the addressees to interact with. We classify the methods of addressee detection and selection into two categories, namely, passive and active approaches. For ...
Designing social greetings in human robot interaction
DIS '14: Proceedings of the 2014 conference on Designing interactive systemsWe designed and operationalized a greetings model for human robot interaction as a state machine, derived from a subset of social behaviors as detailed by Kendon's observations of greetings and augmented by Hall's proxemics theory. Our premise is that ...
Multi-party interaction with a virtual character and a human-like robot
VRST '13: Proceedings of the 19th ACM Symposium on Virtual Reality Software and TechnologyResearch on interactive virtual characters and social robots focuses mainly on one-to-one interactions and multi-party interactions concept are rather less explored. As we are developing these characters to be helpful to us in our daily lives as guides, ...
Comments