Projection enhancement-oriented gesture interaction method based on machine vision

Abstract

The invention discloses a projection enhancement-oriented gesture interaction method based on machine vision. The method comprises the following steps:1, performing joint calibration on a projector and a camera; step 2, opening a camera to acquire a gesture-free image; 3, converting the gesture-free image into a background image and preprocessing the background image; step 4, eliminating background information of the current image by adopting a frame difference method to obtain a gesture image, and then performing edge contour detection on the gesture information by utilizing a Canny operatorto obtain a gesture contour; step 5, traversing the obtained gesture contour to obtain fingertip point coordinates; step 6, performing position and time judgment on the fingertip point coordinates, and then transmitting a judgment result to a computer; and step 7, analyzing a judgment result, and executing corresponding operation by the computer. According to the invention, on an assembly site, anassembly worker can realize interaction only by a simple gesture without wearing equipment, so that natural interaction is truly realized, and the practicability of the system is improved.

Description

technical field [0001] The invention belongs to the technical field of human-computer interaction, and in particular relates to a gesture interaction method based on machine vision for projection enhancement. Background technique [0002] With the rapid development of information technology, the interaction between human and various computer systems has become inevitable, so human-computer interaction technology has received more and more attention. New technologies and devices such as VR have sprung up like mushrooms after rain. At the same time, efficient and humanized operation with these devices has become a technical difficulty and an important research direction. Compared with the mouse, keyboard and touch screen, gestures are flexible, intuitive and non-contact; gesture recognition not only plays an important role in VR, but also in many fields such as AR, drone control, smart home and sign language recognition. applications and are playing an increasingly important ...

AI Technical Summary

Problems solved by technology

The gesture segmentation in the above-mentioned prior art is based on the skin color model. When the human hand overlaps with the face or the skin-like area, the segmentation will be inaccurate, which will seriously affect the feature extraction and gesture recognition in the later stage. At the same time, the recognized static gesture and dynamic There are relatively few gestures and many restrictions. It can only simulate some functions of the mouse, and it cannot interact with the machine in the most natural way.

Images