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

All-focus synthetic aperture imaging method based on automatic target extraction

A target extraction and synthetic aperture technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of poor imaging accuracy, wrong transmission of visible pixels, poor accuracy, etc.

Active Publication Date: 2018-08-31
SHAANXI NORMAL UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the shortcomings of poor imaging accuracy of existing all-focus synthetic aperture imaging methods, the present invention provides a full-focus synthetic aperture imaging method based on automatic target extraction
The all-focus synthetic aperture imaging is regarded as a joint imaging problem of the focused target and the non-focused plane. Through the estimation of the non-focused area and the focused target, the target and the estimated non-focused area are naturally mosaiced by using the target extraction method to achieve no dispersion. Focus blurred all-focus synthetic aperture imaging, solving the technical problem of poor precision caused by iterative calculation of visual pixel errors that are easy to transfer

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
  • All-focus synthetic aperture imaging method based on automatic target extraction
  • All-focus synthetic aperture imaging method based on automatic target extraction
  • All-focus synthetic aperture imaging method based on automatic target extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] The specific steps of the all-focus synthetic aperture imaging method based on automatic target extraction in the present invention are as follows:

[0060] 1. Non-focus area estimation.

[0061] The out-of-focus regions are reconstructed using information captured simultaneously by the camera array from different viewpoints by selecting appropriate pixel values ​​from different viewpoints through image segments. The non-focus area estimation problem is equivalent to the optimal labeling problem and calculated by energy minimization, where the label represents the camera number used to reconstruct the pixels of the non-focus area.

[0062] W 1 ,...W k ,...W N Indicates the images captured by N camera angles, M indicates the pixel set in the image acquired by a certain camera angle, m indicates the pixels in the image captured by the kth camera, k is the camera serial number, m∈M, W k (m) is its pixel value. F={f m} m∈M Indicates the set of output pixel labels, in...

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 all-in-focus synthetic aperture imaging method based on automatic target extraction, which is used to solve the technical problem that the existing all-in-focus synthetic aperture imaging method is of poor imaging precision. According to the technical scheme, all-in-focus synthetic aperture imaging is taken as a problem of joint imaging of a focusing target and a non-focusing plane, a target is naturally embedded into an estimated non-focusing area through estimation of the non-focusing area and the focusing target and by use of a target extraction method to realize all-in-focus synthetic aperture imaging without defocus blur, and the technical problem that error in iterative calculation of visible pixels is easy to transmit and results in poor precision is solved. According to the invention, multi-view information is fully utilized, all-in-focus synthetic aperture imaging is taken as a problem of joint imaging of a focusing target and a non-focusing plane, a target is naturally embedded into a background through estimation of the non-focusing area and the focusing target and by use of a target extraction technology, and therefore, all-in-focus synthetic aperture imaging without defocus blur is realized, and the imaging precision is high.

Description

technical field [0001] The invention relates to an all-focus synthetic aperture imaging method, in particular to an all-focus synthetic aperture imaging method based on automatic target extraction. Background technique [0002] The literature ", All-in-focus Synthetic Aperture Imaging, ECCV, p1–15, 2014" discloses an all-in-focus synthetic aperture imaging method, which is used to solve the problem of non-focus plane caused by focusing on a focal plane during synthetic aperture imaging. The problem of defocused and blurred objects. This method is based on the idea of ​​layer-by-layer visible pixel marking. Firstly, a certain camera angle of view is selected as a reference angle of view. By calculating the maximum color discrimination of pixels corresponding to each angle of view, the unobstructed visible pixels of the current layer are marked, and then used in the next layer. Iterative operation of visible pixels. After repeated iterative operations layer by layer, an all-...

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): G06T7/215G06T7/90
CPCG06T2207/10044
Inventor 裴炤陈希达马苗刘侍刚彭亚丽
Owner SHAANXI NORMAL UNIV
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