Direct Estimation Method of Pose with High Accuracy for Calibration Area Array Camera Image

An area scan camera, pose estimation technology, applied in the direction of photo interpretation, etc., can solve the problems of difficult technology development, high basic requirements, and complex application scope.

Inactive Publication Date: 2019-07-30
LIAONING TECHNICAL UNIVERSITY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are also many literatures on camera attitude estimation in the field of computer vision. Two effective linear attitude calculation methods proposed by FIORE and LEPETIT, among which the EPnP algorithm proposed by LEPETIT has been highly evaluated, and has been used in later panoramic image attitude estimation. Continuous improvements have been made. These algorithms are based on complex advanced algebraic theories, which have high requirements for researchers, which makes the technology difficult to develop. In addition, some scholars convert the solution of image pose parameters into three-dimensional geometric corner relations, and the implementation of this algorithm is also relatively complicated. and has a certain scope of application

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
  • Direct Estimation Method of Pose with High Accuracy for Calibration Area Array Camera Image
  • Direct Estimation Method of Pose with High Accuracy for Calibration Area Array Camera Image
  • Direct Estimation Method of Pose with High Accuracy for Calibration Area Array Camera Image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] An embodiment of the present invention will be further described below in conjunction with the accompanying drawings.

[0061] In the embodiment of the present invention, a method for directly estimating the pose of a calibration area camera image with high precision, the flow chart of the method is as follows figure 1 shown, including the following steps:

[0062] Step 1. Determine the coordinates of a group of high-level object space points, and use the calibration camera to obtain images containing the above object space points;

[0063] Step 2. Select the convex hull image points corresponding to the object space points in the image data to participate in image pose estimation;

[0064] In the embodiment of the present invention, select 7 pieces of image data, such as figure 2 As shown; select the convex hull points in all image points in each experimental image data to participate in the estimation, the number of points with the same name participating in the es...

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 proposes a method for directly estimating the pose of a calibration area camera image with high precision, which belongs to the technical field of computer vision and photogrammetry. The invention selects the object space points corresponding to the three image points with the largest triangle area among the convex hull points As a base point group, image depth and translation vectors are obtained, and then the image pose estimation is transformed into the problem of obtaining the rotation matrix by the vector, and the high-precision estimation of the rotation matrix is ​​completed by using the Procrustes method; Compared with the current mainstream method, it has been greatly improved. At present, my country is in a new stage of rapid development in aerospace and geospatial information technology. The method of the present invention is applied to aviation (including low-altitude) remote sensing mapping or aerospace remote sensor space positioning. The field of attitude measurement has a good development prospect, which will effectively enhance the core competitiveness of attitude estimation technology in this field, with great theoretical value and considerable economic benefits.

Description

technical field [0001] The invention belongs to the technical field of computer vision and photogrammetry, and in particular relates to a method for directly estimating poses with high precision for calibration area array camera images. Background technique [0002] Image pose estimation is an important direction in the research fields of computer vision and photogrammetry. It runs through the entire discipline of aerospace surveying and mapping. It is of great value to study image pose estimation methods with high precision and fast speed. Attitude estimation often uses two methods: iterative solution and direct solution. The iterative solution method is widely used in the field of photogrammetry. It has high calculation accuracy and good geometric meaning. The accuracy of the solution results is relatively uniform. The initial value of posture. In the absence of an initial value, the direct solution method can directly solve the pose parameters, mainly referring to the d...

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): G01C11/04
CPCG01C11/04
Inventor 李艳焕徐振亮邵良杉刘冰
Owner LIAONING TECHNICAL UNIVERSITY
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