A Gesture Interaction Method Based on Visual Attention Model

Abstract

The invention relates to a gesture interaction method based on a visual attention model, and the distribution rule of user vision attention in a gesture interaction interface is studied for the first time. Firstly, the human eye sight changing process is accurately tracked through an eye tracker; secondly, data output by the eye tracker are analyzed, the common rule of vision attention is disclosed, and the vision attention model of an operator is built; thirdly, the model is described through a quintic Gauss formula; finally, the vision attention model is applied to gesture tracking algorithm design. The gesture interaction method based on the visual attention model has the advantages that the model is kept strongly in a small area, obviously improves the efficiency of gesture interaction, improves speed, also improves accuracy, and truly simulates the visual characteristics of careful observation of human beings in a certain area.

Description

Technical field [0001] The invention relates to a gesture interaction method based on a visual attention model. Background technique [0002] In the current human-computer interaction system, gestures can be tracked accurately and in real time, which plays an important role in subsequent processing. At present, commonly used gesture tracking algorithms are: MeanShif algorithm is an image feature analysis method based on kernel function density estimation. This algorithm is widely used because of its simple calculation and good real-time performance; CamShif algorithm is an improvement of MeanShift algorithm. It is an algorithm that uses the color probability model, which is called the continuous adaptive MeanShift algorithm; the Kalman filter algorithm is mainly to predict and estimate the next moment position of the target, and to optimize the estimation of the next state, thus improving the system Stability and accuracy; In 2007, Raskin combined the Gaussian dynamic model and ...

AI Technical Summary

Problems solved by technology

In 1980, Treisman and Gelade proposed the influential feature integration theory (feature integration theory), and divided the attention selection into two stages; in 1985, Koch and Ullman extended Treisman's feature integration theory model, and proposed the significant The concept of graph; L.Itti and C.Koch proposed a bottom-up visual attention calculation model in 1998, which was established on the basis of Treisman and Koch et al. The model has a small amount of calculation and fast speed, but it is for Sensitive to noise and less robust

Images