A feature point recognition method and device for human-computer interaction

Abstract

The present invention provides a feature point recognition method and equipment for human-computer interaction, the method comprising: the computing board obtains the reading material required by the user based on the user's input, and projects the reading material on the user operation interface through a projection unit for use The wide-angle camera captures the scene image on the current user interface in real time, and transmits the scene image to the computing board in real time, and the computing board intercepts the sub-picture at the corresponding reading place; the sub-picture intercepted by the computing board Send to the cloud server, and the cloud server identifies the sub-picture to obtain the feature points. It uses the cloud server to identify the feature points, which improves the recognition accuracy, and stores the feature points in the cloud in a certain order to form a feature point data set, so that the real-time update of the content uploaded by the user facilitates the retrieval and acquisition of the content. Ability to automatically update projected marker content for smarter display, smarter marker tracking.

Description

technical field [0001] The invention relates to the technical field of human-computer interaction, in particular to a feature point recognition device method and device for human-computer interaction. Background technique [0002] Human-computer interaction is a study of the interactive relationship between the system and the user. A system can be a variety of machines, or it can be computerized systems and software. The human-computer interface usually refers to the part visible to the user. [0003] With the development of human-computer interaction technology, many human-computer interaction and reality technology are combined, especially augmented reality technology has been widely used in entertainment, engineering, etc., so that people in the real world can solve some virtual things at close range, which involves The technologies obtained include multimedia, three-dimensional modeling, real-time tracking, intelligent interaction, sensing and other technical means, an...

AI Technical Summary

Problems solved by technology

[0004] In the prior art, especially in the human-computer interaction teaching system, the recognition of feature points has always been a difficult point. Due to the inaccurate recognition accuracy, the acquired learning content is wrong, which affects the learning efficiency and enthusiasm of students.

Moreover, in the prior art, generally only fixed feature points are identified, and users cannot customize detailed features. In the prior art, the identified feature points are only used to obtain corresponding content, and a part of the user’s acquired A series of feature points are stored in memory for subsequent use

Images