Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Automatic geometric correction method of surface projection based on image recognition

A technology of geometric correction and curved surface projection, which is applied in image communication, image reproducer and picture reproducer using projection devices, etc., can solve the problems of difficult control, complex process and cumbersome engineering implementation, and achieves good versatility and easy implementation. Sexuality, simple operation, good effect

Active Publication Date: 2017-08-04
ZHENGZHOU J&T HI TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Manual adjustment is mainly carried out by manually dragging the control points of the projected surface. Generally, hundreds or even thousands of control points need to be repeatedly operated. The debugging process is complex, cumbersome, time-consuming, and the effect is not easy to control. It requires high experience for debugging personnel; Another method to obtain the homography matrix between the projector and the projection screen through camera calibration, through the reconstruction of the projection screen, calculate the pre-distortion matrix to achieve the purpose of geometric correction of the surface, which can automatically correct the surface of the projection screen to a certain extent However, this method needs to calibrate the camera and projector used in advance, and the whole process is more complicated, and the engineering implementation is not easy to control; therefore, there is an urgent need for the adjustment of the projected surface nonlinear geometric correction. , easy to operate and effective implementation

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
  • Automatic geometric correction method of surface projection based on image recognition
  • Automatic geometric correction method of surface projection based on image recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In conjunction with the accompanying drawings, the present invention is further described in detail through embodiments.

[0031] This embodiment utilizes opencv (computer vision development library) development library, opengl (open graphics library), webcam and infrared laser pointer on the windows operating system, first project an image with recognizable and positioned green squares through the projector, and the computer Collect images through the camera and identify and locate the position of the projected green square Calculate the homography matrix between the camera image space and the projector image space, mark the actual target projection position with an infrared laser pointer and identify the target projection control in the projection screen An automatic geometric correction method that automatically calculates the control points of the projected surface by point position. The automatic geometric correction algorithm for curved surface projection based on...

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 relates to an image-identification-based automatic geometric correction method for curved surface projection. A camera is arranged to face the center of a projection screen and is connected to a computer; a projector projects a projection image including at least four identifiable positioning green square blocks, the camera collects the image and identifies and localizes a color block position, and a homography matrix H between camera image space and projector image space is calculated; a full-black image is projected on the projector, N*N infrared laser pens are used for projection at horizontal and vertical equally-dividing points of a target projection region of the projection screen to form an N-row N-column laser dot matrix; the camera collects one frame of image, identifies the location of an infrared laser dot matrix location, and records a location set Cd{Cd1, Cd2...Cdi}; according to the homography matrix H, back calculation of a location set Ps of the intersection point location set Cd in the image space of the projector is carried out; a Bezier surface using as a projection curved surface is established in the image space of the projector by using opengl, the projection picture is mapped to the opengl Bezier surface in a texture manner, the location set Ps of the image space of the projector is used as N-row N-column control points of three-times Bezier surface to form a projection curved surface, thereby completing geometric correction. Therefore, non-linear curved surface geometric correction can be processed automatically; equipment is available; and the effect is good.

Description

technical field [0001] The invention relates to an automatic geometric correction method for curved surface projection based on image recognition, which has good signal orientation and is universal and easy to implement, and belongs to the technical field of virtual reality multi-channel projection display. Background technique [0002] Projection multi-channel fusion means that two or more projectors achieve an overall larger picture enhancement effect through edge fusion. After the projection adopts the edge fusion technology, it can be applied to the command and monitoring center, network management center, video conferencing, academic reports, technical lectures and multi-functional conference rooms, mainly suitable for specific needs of large screen, multi-color, high brightness, high resolution, etc. super large place. [0003] In the process of projection multi-channel fusion, due to the use of flat screens, ring screens and ceiling hanging projection methods, the sh...

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): H04N9/31G06F3/14
CPCG06F3/1446H04N9/3147
Inventor 赵明玥张安全朱运兰张二阳
Owner ZHENGZHOU J&T HI TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products