Unlock instant, AI-driven research and patent intelligence for your innovation.

Feature decomposition method and system for multi-modal image block matching

A multi-modal image and feature decomposition technology, applied in the field of image processing, can solve problems such as decomposition without considering features, achieve the effect of improving accuracy, good matching effect, and shortening the training cycle

Active Publication Date: 2021-08-06
XIDIAN UNIV
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But both of these methods do not take into account the decomposition of features

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
  • Feature decomposition method and system for multi-modal image block matching
  • Feature decomposition method and system for multi-modal image block matching
  • Feature decomposition method and system for multi-modal image block matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0073] It should be understood that when used in this specification and the appended claims, the terms "comprising" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude one or Presence or addition of multiple other features, integers, steps, operations, elements, components and / or collections thereof.

[0074] It should also be understood that the terminology 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
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a feature decomposition method and system for multi-modal image block matching. The method comprises the following steps: making a different-source image block data set; preprocessing the image; performing feature extraction by using an encoder; performing feature decomposition; reconstructing the image block with a decoder; sending the features to a discriminator; optimizing the network; predicting the matching probability; and finally evaluating the network performance. It is shown that the features of the image blocks are decomposed into public features and private features, adversarial training is introduced to optimize an encoder, reconstruction loss is utilized to ensure that the encoder can extract information features, the original image is reconstructed based on the public features and the private features, and a final image block matching result is obtained. According to the method and system, the four loss functions are used for joint optimization, so that the accuracy of different-source image matching is greatly improved, and the training period of the network is shortened.

Description

technical field [0001] The invention belongs to the technical field of image processing, and specifically relates to a feature decomposition method and system for multi-modal image block matching, which can be used for target tracking, heterogeneous image registration, image retrieval, etc., and can effectively improve the accuracy of heterogeneous images. Matching accuracy. Background technique [0002] The purpose of image patch matching is to establish local correspondence between image patches. It has important applications in various remote sensing image processing such as remote sensing image registration, change detection, image stitching, and image fusion. In recent years, it has become a trend to utilize images from different sensors to obtain richer information. However, multimodal images such as optical images and SAR images have large differences in appearance and texture, which brings great difficulties to image stitching and matching. [0003] Traditional im...

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
IPC IPC(8): G06K9/46G06N3/04G06N3/06G06N3/08
CPCG06N3/061G06N3/08G06V10/443G06V10/50G06V10/462G06N3/045
Inventor 王爽魏慧媛李毅段宝瑞权豆雷睿琪杨博武焦李成
Owner XIDIAN UNIV