Super-resolution reconstruction method based on camera array depth estimation

A technique of super-resolution reconstruction and depth estimation, applied in the field of super-resolution reconstruction based on camera array depth estimation

Pending Publication Date: 2022-03-22
NAT UNIV OF DEFENSE TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for an important branch of the field of multi-image super-resolution, research on super-resolution reconstruction based on camera arrays is still insufficient.

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
  • Super-resolution reconstruction method based on camera array depth estimation
  • Super-resolution reconstruction method based on camera array depth estimation
  • Super-resolution reconstruction method based on camera array depth estimation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further described below in conjunction with the accompanying drawings, but the present invention is not limited in any way. Any transformation or replacement based on the teaching of the present invention belongs to the protection scope of the present invention.

[0032] First select a camera in the camera array as the reference camera, and mark it as camera No. 1. The high-resolution image to be reconstructed is actually a 2D projection of a 3D scene onto a high-resolution grid of selected reference cameras. Let u denote the 1D vector (in lexicographical order) of the high-resolution images acquired by the selected reference camera high-resolution grid that needs to be estimated. The purpose is to consist of a collection of low-resolution images {y p} (p corresponds to camera number p) to estimate the high-resolution image u. The imaging model is as follows:

[0033] the y p =DW p Huθ+e p ,p=1,2,...,m (1)

[0034] Here the displacem...

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 super-resolution reconstruction method based on camera array depth estimation. The method comprises the following steps: selecting a camera in a camera array as a reference camera; a scene accurate depth map is obtained through depth estimation, and image registration work is completed by using the scene accurate depth map; estimating a fuzzy high-resolution image z from the low-resolution image set {yp} by using an image fusion super-resolution method guided by depth information; and respectively updating the high-resolution image u, the blurring kernel h and the angle theta by using an ADMM algorithm, and reconstructing the'blurred 'high-resolution image z to obtain a final high-resolution image. According to the method, the PSNR value and the SSIM value are the highest, the MSE value is the lowest, and the reconstruction result is better than that of an existing latest model.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a super-resolution reconstruction method based on camera array depth estimation. Background technique [0002] The super-resolution reconstruction problem based on camera array is actually a multi-view super-resolution reconstruction problem, and the camera array of the research object takes a set of multi-view images at the same time. [0003] According to the distance of the shooting scene by the camera array system, the captured images can be divided into close-range images and distant-view images. For the close-range image group captured by the camera array system, the internal and external parameters of the system obtained in advance and the information of the image itself can be fully utilized to first obtain the accurate depth information of the scene, and then use the depth information to guide the super-resolution reconstruction work. [0004] Tsai and Huang st...

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): G06T3/40G06T7/55G06T7/33G06T5/00G06T7/90
CPCG06T3/4053G06T7/55G06T7/337G06T5/003G06T7/90G06T3/4023G06T2207/10028
Inventor 曾向荣钟志伟刘衍张政
Owner NAT UNIV OF DEFENSE TECH
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