A space gesture control device based on machine vision

Abstract

The present invention proposes a space gesture control device based on machine vision, including a main control module, a data acquisition module, a data processing module and a communication module; the four modules are integrated and modularized, and the control device is built on an embedded platform. The main control module and the data processing module share the main control chip on the main board of the control device, and the communication module is integrated on the main board; the main control module controls the operation of other modules and monitors their operating status in real time; The data acquisition module captures the image of the user's hand through the monocular camera, and transmits it to the data processing module; the data processing module analyzes and obtains the control command, and transmits it to the communication module, and the communication module sends the control command to the controlled device; the present invention The device has accurate gesture recognition and smooth operation. The module is small in size, low in cost, high in integration, and high in modularization. It can be used as the central control of the hardware system alone or integrated into the overall platform, which is easy to build and maintain.

Description

technical field [0001] The invention belongs to the technical field of gesture control, in particular to a space gesture control device based on machine vision. Background technique [0002] Spatial gesture control based on machine vision is one of the research hotspots in the field of human-computer interaction. At present, spatial gesture control devices based on machine vision can be divided into two categories based on monocular imaging and depth imaging. Among them, the equipment based on monocular imaging collects images through a monocular camera, and mainly uses the characteristics of hand color, shape and movement to realize spatial gesture detection and recognition. Devices based on depth imaging use depth cameras to collect images, and can additionally obtain the distance between the hand and the camera as a feature, such as the Kinect controller. Compared with the method based on monocular imaging, due to the additional introduction of depth information, the ac...

AI Technical Summary

Problems solved by technology

Among the methods based on monocular imaging, most of the high-precision methods have a large amount of computation, and it is difficult to run smoothly on the embedded platform; while most of the methods suitable for the embedded platform only recognize simple hand shapes and two-dimensional moving trajectories, and cannot extract Posture information such as hand tilt and rotation

In addition, most of the existing spatial gesture control devices separate image acquisition and data processing, the degree of integration is low, and there is no modular design in the architecture

Images