Panorama camera lens position estimation method and panorama camera

A panoramic camera and attitude estimation technology, applied in the field of image processing, can solve problems such as poor accuracy, and achieve the effects of improved accuracy, improved accuracy, and improved stitching effect.

Active Publication Date: 2018-07-10
成都美若梦景科技有限公司
View PDF11 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method for estimating the attitude of a panoramic camera lens and a panoramic camera, which can solve the problem of poor accuracy of the attitudes of each camera acquired due to camera installation errors, and improve the accuracy of each acquisition in the presence of camera installation errors. The effect of the accuracy of the attitude of the camera, thus effectively improving the stitching effect of panoramic images

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
  • Panorama camera lens position estimation method and panorama camera
  • Panorama camera lens position estimation method and panorama camera
  • Panorama camera lens position estimation method and panorama camera

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] The first aspect of the present invention provides a method for estimating the pose of a panoramic camera lens, such as figure 1 As shown, the panoramic camera has N fisheye lenses, and N is an integer not less than 2, and the method includes:

[0056] S101, using N fisheye lenses to acquire N fisheye images at the same time;

[0057] S102. Select M pairs of fisheye images from the N fisheye images, wherein every two fisheye images with intersecting areas form a pair of fisheye images, and M is an integer not less than 1;

[0058] S103. According to the three-dimensional direction vectors of the two fisheye lenses corresponding to each pair of fisheye images, obtain two matrices for converting the two fisheye lenses in each pair of fisheye lenses to the same direction;

[0059] S104. Correct each fisheye image according to the matrix and internal parameters of each fisheye lens in each pair of fisheye lenses converted to the same direction, and obtain the corrected M p...

Embodiment 2

[0140] The second aspect of the present invention provides a panoramic image stitching method applied in a panoramic camera, the panoramic camera has N fisheye lenses, and N is an integer not less than 2, such as Figure 5 As shown, the method includes:

[0141] S501. Calculate the pose of each fisheye lens in the world coordinate system by using the method provided in the first aspect of the application, and store it in the memory;

[0142] S502. After using N fisheye lenses to acquire N fisheye images at the same time, according to the posture of each fisheye lens in the world coordinate system stored in the memory, the N fisheye images, each Intrinsic parameters of the fisheye lenses, and the N fisheye images are stitched into a panoramic image.

[0143] Wherein, the specific implementation steps of step S501 can refer to the implementation steps recorded in the first aspect of the present invention. It can be seen that the method provided by the first aspect of the presen...

Embodiment 3

[0165] The third aspect of the present invention provides a panoramic camera with N fisheye lenses, where N is an integer not less than 2, such as Figure 6 As shown, the panoramic camera also includes:

[0166] A fisheye image acquisition unit 601, configured to acquire N fisheye images at the same time using the N fisheye lenses;

[0167] An image pair selection unit 602, configured to select M pairs of fisheye images from the N fisheye images, wherein every two fisheye images with intersecting regions form a pair of fisheye images, and M is an integer not less than 1 ;

[0168] The image conversion unit 603 is used to obtain two matrices in which the two fisheye lenses in each pair of fisheye lenses are converted to the same direction according to the three-dimensional direction vectors of the two fisheye lenses corresponding to each pair of fisheye images;

[0169] The image correction unit 604 is used to correct each fisheye image according to the matrix and internal pa...

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 a panorama camera lens position estimation method and a panorama camera. The method includes the steps of selecting M pairs of fish-eye images from N fish-eye images obtained through N fish-eye lenses; on the basis of three-dimensional direction vectors of two fish-eye lenses corresponding to each pair of fish-eye images, obtaining two matrixes when each pair of fish-eye lenses turns to the same direction; on the basis of the matrixes and internal parameters when each pair of fish-eye lenses turns to the same direction, correcting each fish-eye image, performing characteristic point extraction and characteristic point matching on the obtained corrected M pairs of fish-eye images, and obtaining a matched characteristic point pair of each fish-eye image; on the basisof a two-dimensional coordinate of the matched characteristic point pair of each fish-eye image in an image coordinate system as well as the matrixes when two fish-eye lenses of each pair of fish-eyelenses turn to the same direction, obtaining a three-dimensional coordinate set of the matched characteristic point pair of each fish-eye image; and on the basis of the three-dimensional coordinate set of the matched characteristic point pair of each fish-eye image, obtaining the position of each fish-eye lens in a world coordinate system.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a panoramic camera lens attitude estimation method and a panoramic camera. Background technique [0002] The panoramic camera needs to splice the pictures of multiple cameras to form a 360-degree panoramic image. The parameters of each camera, including internal parameters and external parameters, need to be used in the stitching calculation process. The internal parameters of each camera can be estimated using a checkerboard image calibration algorithm. [0003] Most of the existing panorama stitching schemes use feature point extraction and matching directly to adjacent images, and then estimate the affine transformation parameters (or other transformations) between the images through the RANSAC algorithm, and finally optimize the global camera parameters through BA to obtain To the optimized external parameters (attitude) of each camera: rotation matrix R and displacement vect...

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): G06T3/40G06K9/62G06T5/00
CPCG06T3/4038G06T5/006G06V10/757
Inventor 曾智邓旭
Owner 成都美若梦景科技有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap