Automated projection-keyboard calibration method of utilizing four manually selected points

A technology of projection keyboard and calibration method, which is applied in the input/output process of data processing, image data processing, instruments and other directions, can solve the problems of inconsistent fingertip coordinate extraction, different calibration results, errors, etc., to eliminate different calibration results, The effect of saving manual operations and saving labor costs

Active Publication Date: 2018-02-02
哈尔滨拓博科技有限公司
View PDF3 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Input devices (keyboards, mice) are important tools for human-computer interaction of computer devices or other smart devices. With the miniaturization of computer devices or wearable smart devices, many products in the electronic field will miniaturize or even miniaturize input devices. , but the smaller the input device, the trouble of inconvenient input is caused to people, but it still cannot meet the needs of mobility and portability. At present, some computer devices or wearable smart devices have adopted projection keyboards as input devices.
[0003] However, there are still many problems in the calibration of the projection keyboard. At present, manual calibration is basically used for the calibration of the projection keyboard. In the actual calibration process, manual calibration is used, and each key on the projection keyboard needs to be manually Calibration, and the calibration by different personnel will definitely make the calibration results different, bringing errors, which will affect the accuracy of the keyboard calibration
For example, each person's finger size is different, which will lead to inconsistencies in the extraction of fingertip coordinates, which will lead to a decrease in the accuracy of the calibration results

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
  • Automated projection-keyboard calibration method of utilizing four manually selected points
  • Automated projection-keyboard calibration method of utilizing four manually selected points
  • Automated projection-keyboard calibration method of utilizing four manually selected points

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0044] Specific implementation mode one: combine Figure 6 To describe this embodiment,

[0045] An automatic calibration method using a manually selected four-point projection keyboard, comprising:

[0046] Step 1. Camera calibration:

[0047] Camera calibration is the calibration of the recognition camera. The recognition camera and the projection device of the projection keyboard are integrated for fingertip area recognition and positioning;

[0048] The calibration uses a customized LED small light board with known distribution size as the LED calibration board, and uses the recognition camera to take a picture of the LED calibration board, such as figure 1 As shown, the threshold segmentation algorithm is used to detect each light point on the LED calibration board, and the centroid of the light point is calculated as the coordinate of the calibration point in the image, that is, the image coordinates of the calibration point; at the same time, since the size of the LED...

specific Embodiment approach 2

[0055] An automatic calibration method using a manually selected four-point projection keyboard, comprising:

[0056] Step 1. Camera calibration:

[0057] Camera calibration is the calibration of the recognition camera. The recognition camera and the projection device of the projection keyboard are integrated for fingertip area recognition and positioning;

[0058] The calibration uses a customized LED small light board with known distribution size as the LED calibration board, and uses the recognition camera to take a picture of the LED calibration board, such as figure 1 As shown, the threshold segmentation algorithm is used to detect each light point on the LED calibration board, and the centroid of the light point is calculated as the coordinate of the calibration point in the image, that is, the image coordinates of the calibration point; at the same time, since the size of the LED calibration board is known, the LED The world coordinates of each light point on the calib...

specific Embodiment approach 4

[0094] The recognition camera described in step 1 of this embodiment is a 120-degree wide-angle camera.

[0095] Other steps and parameters are the same as those in the first to third specific embodiments.

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 invention discloses an automated projection-keyboard calibration method of utilizing four manually selected points, and aims to solve the problem that larger calibration errors of current calibration methods exist. According to the method disclosed by the invention, firstly, a recognition camera is utilized to shoot a picture of an LED calibration board, and an internal parameter matrix of therecognition camera and distortion coefficients of a distortion model are calculated; then the calibration reference points of a projection keyboard are manually selected, and image coordinates of thecalibration reference points are calculated; a relative position relationship of the recognition camera and the projection keyboard is calculated according to a camera imaging model, and world coordinates of the calibration reference points are determined; a transformation equation of the calibration reference points from a camera coordinate system to a world coordinate system is established according to a projection transformation relationship, and a projection transformation matrix is obtained; and then world coordinates of each key are calculated according to a projected-keyboard size andthe world coordinates of the four calibration reference points, and a keyboard table is generated. The method is suitable for use in automated projection-keyboard calibration.

Description

technical field [0001] The invention relates to an automatic calibration method for a projection keyboard. Background technique [0002] Input devices (keyboards, mice) are important tools for human-computer interaction of computer devices or other smart devices. With the miniaturization of computer devices or wearable smart devices, many products in the electronic field will miniaturize or even miniaturize input devices. , but the smaller the input device, the trouble of inconvenient input is caused to people, but it still cannot meet the needs of mobility and portability. At present, some computer devices or wearable smart devices have adopted projection keyboards as input devices. [0003] However, there are still many problems in the calibration of the projection keyboard. At present, manual calibration is basically used for the calibration of the projection keyboard. In the actual calibration process, manual calibration is used, and each key on the projection keyboard n...

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 Applications(China)
IPC IPC(8): G06F3/041G06F3/042G06T7/80G06T7/11G06T7/136
CPCG06F3/0418G06F3/0425G06T7/11G06T7/136G06T7/80
Inventor 李祝强冯大志窦振龙赵雪洁
Owner 哈尔滨拓博科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products