EPI-based light field image key position detection method

A key position, light field image technology, used in instruments, character and pattern recognition, computer parts and other directions, can solve problems such as instability of feature points, and achieve the effect of increasing stability and improving accuracy

Active Publication Date: 2019-12-17
XIAN UNIV OF TECH
View PDF5 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for detecting key positions of light field images based on EPI, which overcomes the unstable problem of feature points detected by existing light field image feature detection methods

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
  • EPI-based light field image key position detection method
  • EPI-based light field image key position detection method
  • EPI-based light field image key position detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0057] An EPI-based light field image key position detection method of the present invention is specifically implemented according to the following steps:

[0058] Step 1. Decode the original light field image name_LensletRaw.bmp to obtain a four-dimensional light field matrix LF[u, v, s, t];

[0059] Step 2, using MATLAB to extract the four-dimensional light field matrix LF[u, v, s, t], and then grayscale the extracted central row and central column sub-aperture images;

[0060] Step 3, extracting 3D horizontal EPI cubes and 3D vertical EPI cubes on the central row and central column sub-aperture images after grayscale processing;

[0061] Step 4. Perform multi-scale Harris feature point detection on the gray-scaled central row and central column sub-aperture images, and determine the feature points detected on multiple scales on the light ...

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 EPI-based light field image key position detection method. The method comprises the steps of 1, decoding a light field image to obtain a four-dimensional light field matrix;2, obtaining central row and central column sub-aperture images of the light field image; 3, extracting a 3D horizontal EPI cube and a 3D vertical EPI cube; 4, determining feature points which are detected in multiple scales; 5, processing to obtain a key position line; 6, determining stable feature points, namely light field key positions, on the light field image; and 7, deleting repeated lightfield key positions, and finally obtaining all key positions on the light field image. According to the EPI-based light field image key position detection method, the problem that the feature pointsdetected by the existing light field image feature detection method are unstable is solved, the stable key position on the light field image can be accurately detected, and the method has robustness and low time complexity and is suitable for different scenes.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, and in particular relates to an EPI-based method for detecting a key position of a light field image. Background technique [0002] Since the light field camera is based on the principle of recording the beam direction data information, the imaging can use the position information and angle information to obtain the real information of the entire space, which overcomes the shortcomings of traditional imaging such as occlusion and loss of depth, and describes the scene more comprehensively and widely. It is used in the field of stereoscopic image display and security monitoring of multiple viewpoints. [0003] The feature detection of light field images is a current research hotspot. The existing light field image feature detection methods include the cross-view repeated sift feature detection method and the LIFF light field feature point detection method: the cross-view repeated ...

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): G06K9/46
CPCG06V10/44G06V10/60
Inventor 金海燕边敏艳肖照林蔡磊李秀秀
Owner XIAN UNIV OF 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