Effective fixation point detection method and device, electronic equipment and storage medium

Abstract

The invention discloses an effective fixation point detection method and device, electronic equipment and a storage medium. The method comprises the steps that original model training is carried out based on collected eye movement information, an effective fixation point detection model is obtained, and a speed threshold value used for determining an effective fixation point in the effective fixation point detection model is adaptively adjusted according to information input into the effective fixation point detection model, the collected eye movement information comprises a position sequence and a time sequence; the effective fixation point detection model obtains an effective fixation point corresponding to the eye movement information based on the collected eye movement information; and aggregating the effective fixation points to obtain aggregated effective fixation points. By utilizing the method, the detection of the effective fixation points corresponding to the eye movement information can be realized according to the established effective fixation point detection model, and meanwhile, the effective fixation points are aggregated to obtain the aggregated effective fixation points, so that the detection accuracy of the effective fixation points is improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of eye control, and in particular, to an effective gaze point detection method, device, electronic equipment, and storage medium. Background technique [0002] Eye tracking technology is a technology that records the movement of the eyes by receiving infrared rays reflected by the cornea and pupils through optical receivers. [0003] Usually, the eye movement position of each frame collected by an optical receiver (such as an eye tracker) does not identify a valid fixation point, and the valid fixation point will affect the interpretation of the gaze trajectory map, heat map and raw data in the visualization availability. Therefore, the accurate identification of effective fixation points is extremely important for the study of psychological and cognitive problems. [0004] In existing algorithms, the detection of effective gaze points is mainly based on a fixed threshold. In many sc...

AI Technical Summary

Problems solved by technology

In many scenarios, such as infant eye movement test scenarios, there are problems such as low accuracy of the original fixation point, low stability, large noise, and greater individual differences. At this time, if the traditional algorithm with a fixed threshold is used for processing, it is easy Causes wrong division of effective fixation points, thus affecting the research results; in addition, many infant eye movement studies or inspections usually use dynamic stimulation methods, such as video, animation, etc. At this time, if the traditional algorithm with a fixed threshold is used for processing, it may There will be situations where the detection performance is greatly degraded due to excessive changes in the gaze pattern

Images