Stereo image stitching method based on content of images

A technology for stereoscopic images and image content, which is applied in the field of image processing and can solve the problems of comfortable 3D visual experience and inability to transmit

Inactive Publication Date: 2016-06-15
TIANJIN UNIV
View PDF3 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As researchers dig deeper, more challenges and constraints emerge in creating comfortable 3D experiences
Ordinary extensions to existing 2D stitching algorithms often fail to deliver a comfortable 3D visual experience, so new techniques are needed to adapt to new constraints and to better utilize new information from stereoscopic media

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
  • Stereo image stitching method based on content of images
  • Stereo image stitching method based on content of images
  • Stereo image stitching method based on content of images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The present invention proposes a hybrid transformation model for stereoscopic image mosaic by combining projection transformation and content preservation transformation. First, an iterative method to find a consistent homography matrix method is proposed. This homography matrix pre-transforms the non-reference stereo image to ensure the consistent transformation of the left and right images in the stereo image. Afterwards, a content-preserving warping method is introduced to locally improve connectivity and reduce vertical parallax. Finally, a seam-based algorithm is designed to find hybrid stitching, and finally a multi-band blending algorithm is used to produce the final stitched image. The invention can effectively stitch three-dimensional pictures, avoid local deformation, and reasonably reduce vertical parallax. The specific technical scheme is divided into the following steps:

[0053] 1. Pre-transformation based on homography matrix

[0054] with Represen...

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 belongs to the technical field of image processing, and aims at effectively splicing three-dimensional pictures, avoiding local deformation, and reasonably reducing vertical parallax. The technical scheme adopted by the present invention is, the stereoscopic image mosaic method based on the image content, firstly, the left and right images are pre-transformed by using the optimized consistent homography matrix; after that, the image mosaic is optimized by using the content-based image fine-tuning and distortion method Avoid visual distortion; finally, the final image mosaic result is obtained by using the seam-based search algorithm and the multi-band blending algorithm. The invention is mainly applied to image processing.

Description

technical field [0001] The invention belongs to the technical field of image processing and relates to a stereoscopic image mosaic technology based on image content. Background technique [0002] Image stitching has received extensive attention in computer vision and cartography. It can stitch the near-field images with small scenes into a single image with a large field of view. Currently, stitching technology is integrated in well-known commercial software such as Adobe and Photoshop, which are widely used to help users organize and make photo collections. [0003] Traditionally, image stitching often synthesizes images through projective transformations with parameters. Such projective transformations are usually implemented using homography matrices. Although 2D projective transformations are stable, they can only provide accurate stitching for planar scenes or for parallax-free camera movements, i.e. the cameraman's physical position must be fixed and only rotational...

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): G06T3/00
CPCG06T3/0068
Inventor 侯春萍阎维青刘琦浦亮洲王来花
Owner TIANJIN UNIV
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