Hand swing motion direction judging method based on direction motion historigram and competition mechanism

Abstract

The invention discloses a hand swing motion direction judging method based on direction motion historigram and competition mechanism. The method comprises the following steps of: A1. obtaining the current motion image from video stream, establishing a skin color probability model, and obtaining four light stream directional diagrams; A3. respectively calculating four direction motion historigrams according to the four light stream directional diagrams in step A2; A4. obtaining four direction motion energy diagrams according to a gesture motion historigram; A5. calculating and encoding the motion direction of each frame of image; A6. judging the motion direction of the whole motion sequence; and an interested region is extracted by frame difference and skin color cooperatively to reduce the interference of background and the skin color of a human face. The integral motion direction is calculated by the four motion historigrams and the energy diagrams in a statistic mode to effectively overcome the motion coverage problem. The motion direction is determined by the action competition mechanism to greatly reduce the noise effect and improve the judging accuracy and stability of the motion direction.

Description

technical field [0001] The invention relates to the technical field of computer vision gesture recognition, in particular to a hand-waving motion direction determination method based on a direction motion history graph and a competition mechanism. Background technique [0002] Gesture interaction is a natural and intuitive way of human-computer interaction. Gestures are directly used as computer input, and communication between humans and computers will no longer require a medium. Gesture recognition is the technical basis of gesture interaction. Visual gesture recognition is currently the mainstream of gesture recognition technology because of its simplicity. [0003] Although visual gesture recognition is the main development direction of gesture recognition, there are still many problems, such as being easily affected by background changes, lighting changes, and motion noise, and the hand itself is prone to non-rigid body deformation. There are many redundant and unnecess...

AI Technical Summary

Problems solved by technology

The 3D camera obtains the 3D information of gestures. For example, the kinect launched by Microsoft can collect 3D gesture information, but its high cost is not conducive to popularization

The main problems of this method are: it cannot overcome the problem of motion coverage when waving the hand; it is easily affected by motion noise, resulting in direction judgment and its instability

[0009] 1. The direction judgment depends on the effect of gesture tracking, and the tracking is easily affected by changes in lighting, skin color of the face and hand deformation, and the effect is poor and unstable;

[0010] 2. The tracking algorithm is complex and slow, and cannot quickly determine the direction of the hand wave

[0012] 1. Unable to overcome the problem of motion coverage when waving the hand;

[0013] 2. Easily affected by motion noise, resulting in inaccurate direction judgment

Images