3D visual model control method based on gesture recognition

Abstract

The invention relates to the field of gesture recognition, and discloses a 3D visual model control method based on gesture recognition, a hand is placed in front of an image acquisition device, a hand image is acquired through the image acquisition device, the effective detection area range of the image acquisition device is S1, when the hand is located in the S1, subsequent steps are carried out, otherwise, the subsequent steps are not carried out; after a hand in the hand image is recognized through the hand key point recognition network model, hand key points T are established, and a hand skeleton graph M is formed according to the hand key points T; wherein each key point T corresponds to a matrix in the hand recognition network model, each matrix is a probability graph of the key point T, the position of the key point T is found by searching the maximum value of the probability graph, and then the gesture and action of the hand are recognized; and then translation, selection, release, rotation and zooming of the 3D visual model are completed through a single finger or double fingers, so that people can use gestures to operate while performing presentation.

Description

technical field [0001] The invention relates to the field of gesture recognition, in particular to a 3D visualization model control method based on gesture recognition. Background technique [0002] With the advancement of science and technology, human-computer interaction has become an important part of people's daily life. The ultimate goal of human-computer interaction is to realize the natural communication between man and machine. [0003] Now more and more management systems will be put on the big screen for display. For example, some management systems will include 3D visualization models. The traditional method is that the manager operates the 3D visualization model through the mouse, such as: zooming the 3D visualization model, moving the 3D visualization model, rotating the 3D visualization model, etc. When visualizing the model, while explaining through words, gestures are used at the same time. If you then operate the mouse, it will bring more inconvenience. Th...

AI Technical Summary

Problems solved by technology

The traditional method is that managers use the mouse to operate the 3D visualization model, such as: zooming the 3D visualization model, moving the 3D visualization model, rotating the 3D visualization model, etc. When visualizing the model, while explaining through words, gestures are used at the same time. If you then operate the mouse, it will bring more inconvenience. The way of human-computer interaction is not natural enough, and the overall experience of visitors is poor.

Images