A real-time attitude recognition by eye-tracking

Authors:
Yanpeng Lv;Shangfei Wang;Peijia Shen
Affiliations:
University of Science and Technology of China, Hefei, Anhui, P. R. China;University of Science and Technology of China, Hefei, Anhui, P. R. China;University of Science and Technology of China, Hefei, Anhui, P. R. China
Venue:
Proceedings of the Third International Conference on Internet Multimedia Computing and Service
Year:
2011

Citing 3
Cited 0

Real-Time Detection of Nodding and Head-Shaking by Directly Detecting and Tracking the "Between-Eyes"

FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Towards robot incremental learning constraints from comparative demonstration

The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 3
A Natural Visible and Infrared Facial Expression Database for Expression Recognition and Emotion Inference

IEEE Transactions on Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

Attitude, which is the outward manifestation of human psychology information, is inevitable in everyday situation. Attitude recognition by artificial intelligence has become a hotspot and produced promising results in recent years. In this paper, we propose an attitude recognition method based on eye-tracking. We first improve the eye location algorithm in OpenCV and assume that the trajectory of eyes-center is the same with that of head. Then using eye location method, the center of eyes is calculated. By analysis of displacement of eyes' centers in each two successive frames, sub-result is obtained. The final result is determined by voting algorithm. Experimental results indicate that this method could recognize positive and negative attitudes in real time. We applied our method to "KeJia", an intelligent service robot and it worked well.