Unlock instant, AI-driven research and patent intelligence for your innovation.

An interactive method and device

An interaction method and character technology, applied in the field of human-computer interaction, can solve the problems of being easily disturbed by the on-site environment, poor player experience, and low hardware cost

Active Publication Date: 2021-06-15
深圳市同维通信技术有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method has low hardware cost, but the player’s experience effect is poor, and it is easily disturbed by the on-site environment. For example, after the player’s body is temporarily covered, it reappears in the image, and the somatosensory game cannot re-recognize the player’s body movement information.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An interactive method and device
  • An interactive method and device
  • An interactive method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Such as figure 1 As shown, in this embodiment, an interactive method includes:

[0057] S10. Identifying the coordinate set of key point coordinates of human skeletons of all people in the images collected by the camera;

[0058] S20. Obtain coordinate data of the target person from the human skeleton key point coordinate set;

[0059] S30. Track the target person, and perform interaction according to the real-time coordinate data of the target person.

[0060] In this embodiment, the speed and accuracy of human-computer interaction are improved through the convolutional neural network algorithm based on deep learning, and the effect of automatically tracking the target person is achieved, and only ordinary cameras are needed to collect images, and the cost is low. Strong compatibility.

[0061]In this embodiment, the key points of human skeleton generally refer to eyes, nose, neck, left shoulder, left elbow, left wrist, right shoulder, right elbow, right wrist, left...

Embodiment 2

[0088] Such as Figure 5 As shown, in this embodiment, an interactive device includes:

[0089] Recognition module 10, is used for recognizing the human skeleton key point coordinate set of all people in the camera acquisition image;

[0090] The interaction module 20 is used to obtain the coordinate data of the target person from the coordinate set of key points of the human skeleton;

[0091] The tracking module 30 is configured to track the target person and perform interaction according to the real-time coordinate data of the target person.

[0092] In this embodiment, the speed and accuracy of human-computer interaction are improved through the convolutional neural network algorithm based on deep learning, and the effect of automatically tracking the target person is achieved, and only ordinary cameras are needed to collect images, and the cost is low. Strong compatibility.

[0093] In this embodiment, the key points of human skeleton generally refer to eyes, nose, nec...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention relates to the technical field of human-computer interaction, and discloses an interaction method and device. The method includes: identifying the human skeleton key point coordinate set of all people in the image collected by a camera; Coordinate data; track the target person, and interact according to the real-time coordinate data of the target person; through the convolutional neural network algorithm based on deep learning, the speed and accuracy of human-computer interaction are improved, and the automatic tracking of the target person is achieved. Effect, and only need ordinary camera to collect images, low cost, strong compatibility.

Description

technical field [0001] The present invention relates to the technical field of human-computer interaction, in particular to an interaction method and device. Background technique [0002] Somatosensory games refer to new games in which players interact with smart devices by changing their body movements. Compared with traditional games that rely on buttons or touch, somatosensory games can enhance players' sense of participation and are more and more popular among gamers. and market recognition. [0003] As the importance of artificial intelligence becomes increasingly prominent, various technologies and applications emerge in endlessly. As a popular research direction in the field of artificial intelligence, deep learning can enable machines to imitate the learning mechanism of the human brain to process data such as images and sounds. In terms of images, the processing effect based on deep learning algorithms is significantly better than traditional image processing algor...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F3/01G06K9/00
CPCG06F3/011G06V40/16G06V40/20
Inventor 陈圆黄亮彭中兴
Owner 深圳市同维通信技术有限公司