基于眼动追踪的眼动位置识别

Eye Movement Location Recognition Based on Eye Movement Tracking

提出了一种基于眼动追踪的眼球运动位置识别方法。眼动线索解读理论指出,通过检测被试者在思考问题时的眼球位置,可以确定人的思考类型。实验数据为测试对象观看屏幕时采集的面部视频,在数据处理过程中将视频解析成一帧一帧的图像,首先基于眼动追踪算法进行人眼定位与跟踪,提取每一帧图像的眼动参数;然后采用粒子群优化的极限学习机来判别眼球运动方向。提出的方法在实际应用环境中有很好的鲁棒性,为眼动线索解读提供了客观的、可靠的位置参数。

This paper presents a method of position recognition based on eye movement tracking.According to the theory of eye movement cue interpretation,people’s thinking type can be determined by detecting the eye position of the subjects when they are thinking.The experimental data is the face video collected when the test object watches the screen.During the data processing,the video is analyzed into a frame-by-frame image.Firstly,eye detection is conducted.Then the particle swarm optimization limit learning machine is used to identify the direction of eye movement.