Virtual keyboard system for smart glasses

Abstract

The invention discloses virtual keyboard system used for Google glasses. The virtual keyboard system is characterized in that a hand tracking system and a self-positioning system are integrated in a Google glasses body; the hand tracking system is used for detecting three-dimensional positioning information and spatial position and angle of the hand; the self-positioning system is fixedly connected onto the Google glasses body and used for acquiring real-time natural movement data of the head and calculating spatial direction, displacement and speed of real-time movement of the head; the Google glasses body collects the information of the hand tracking system and the positioning system and calculating real-time relative movement data. Error responses of an interactive system can be effectively avoided through dependence mapping of a physical plane and a screen; feeling of fatigue resulted in dangling arm operation can be effectively relieved through hand operation on the physical plane; similar to a traditional one, an interactive operating interface is satisfactory to operation habit of an operator and convenient to use; by the introduction of the self-positioning system, the operation displacement problem caused by head movement of a wearer can be effectively removed.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a virtual keyboard system for smart glasses. Background technique [0002] In recent years, the development of smart wearable devices has become more and more popular. Smart wearable devices include smart watches, smart glasses, smart bracelets and other products. Among them, smart glasses are similar to smartphones and have an independent operating system. Users can install programs provided by software service providers such as software and games, and complete adding schedules, map navigation, interacting with friends, taking photos and other activities through voice or motion control. It is a general term for a class of glasses that have functions such as video and video calls with friends, and can realize wireless network access through mobile communication networks. [0003] Google Glass is an "augmented reality" glasses released by Google in April 2012. It has the sa...

AI Technical Summary

Problems solved by technology

[0010] The above method has the following disadvantages: 1. The human body will have a certain degree of natural swing. For example, the human head is not absolutely still in the natural posture, but has some shaking in real time. The amplitude and direction of this shaking are Unpredictably, when the human hand performs an operation in the air, if the human head shakes in a specific direction at this time, but the human hand does not move, the binocular infrared device may track the "click" action of the hand relative to the head , the binocular device recognizes the click action of the relative movement between the glasses projected screen and the hand, and cannot determine whether it is caused by the movement of the hand or the natural swing of the human head, which may easily cause false triggers and affect the quality of control. High concentration, keeping the head as still as possible to ensure precise input can easily cause fatigue and trance

[0011] 2. Since the hand needs to be suspended in the air for three-dimensional operation, the problem of fatigue caused by long-term operation cannot be avoided. In the actual experience of personal products, using the three-dimensional gesture operation method similar to the Leap Motion device, usually the arm will produce obvious fatigue after 10 minutes. soreness

[0012] 3. It does not provide a universal and precise operation interface, cannot meet the diverse interaction requirements, and can only provide auxiliary operation input

[0014] The existing smart glasses on the market usually respond through voice interaction or human eye motion capture, which has the following disadvantages: 1. Voice interaction has limitations, and can only perform intermittent input operations, and cannot perform fast and accurate input; 2. Voice interaction It is prone to fatigue and cannot adapt to long-term interaction requirements; 3. Voice interaction is suitable as a supplementary interaction method, and it is difficult to perform independent pure voice interaction; 4. Human eye motion capture is prone to misoperation, and human eyes have Involuntary movements are generated, which can easily cause false triggers; 5. Human eye motion capture is easy to cause fatigue, which is not conducive to long-term interaction; 6. Human eye motion capture has fewer modes, which is not conducive to complex manipulation

Images