Method and system for determining eye movement fixation point based on density

Abstract

The invention provides a method and a system for measuring eye movement fixation points based on density. The method comprises a trajectory point classification stage and a trajectory point clustering stage; at the trajectory point classification stage, the eye movement trajectory point data of a test picture are input, and the trajectory points belonging to fixation points are classified into different categories; the trajectory point clustering stage comprises executing each category, calculating the Euclidean distances between the trajectory points to form a distance matrix, counting the accumulated concern time density of each point, confirming a serial number set of trajectory points having the density equal to the maximum density value, and calculating the central position of the fixed points by solving the center of mass of the set of trajectory points having the density equal to the maximum density value. The clustering center generated by use of the method is more fitted with a user concern center and the emphasis of user concern is taken into full account; besides, the method is simple and efficient, and has higher anti-interference capability.

Description

technical field [0001] The invention relates to the field of eye movement data analysis and the field of visual perception, in particular to a density-based method and system for measuring eye movement fixation points. Background technique [0002] The eye tracker is used to record the characteristics of the eye movement track when people process visual information. It records the eye movement information when the user pays attention to the visual information at a fixed frequency, such as observation time, eyeball position, gaze position, pupil radius and other data. After eye movement data analysis, important information about people's physiological and behavioral performance in the process of visual information extraction can be extracted, so it is widely used in psychology, TV business, industrial design, advertising, usability of real equipment and other research. In recent years, with the continuous development of eye tracking technology, the scope of application of eye...

AI Technical Summary

Problems solved by technology

In the field of clustering methods in eye movement data processing, traditional clustering methods generally use the centroid as the best center point of eye movement fixation. This method cannot take the density information into consideration. When hovering over the data, the generated gaze center will deviate from the area that the user pays most attention to. This method is highly sensitive to noise

[0005] Saccade points in raw eye movement data are often useless for practical research. In addition, small eye movements are not beneficial for high-level eye movement analysis.

Images