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

Remote sensing image retrieval method with integration of spatial direction relation semanteme

An image and orientation technology, applied in the field of remote sensing image retrieval, which can solve the problems of subjectivity and uncertainty of manual annotation, large workload of manual annotation, and lack of consideration of image space orientation semantics.

Inactive Publication Date: 2012-05-02
NANJING NORMAL UNIVERSITY
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This kind of method mainly has the following problems: 1) the workload of manual annotation is too large; 2) manual annotation is subjectivity and uncertainty
This method uses the semantics of the topological relationship of the image to assist image retrieval, and has high retrieval accuracy, but it does not consider the spatial orientation semantics of the image.

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
  • Remote sensing image retrieval method with integration of spatial direction relation semanteme
  • Remote sensing image retrieval method with integration of spatial direction relation semanteme
  • Remote sensing image retrieval method with integration of spatial direction relation semanteme

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0115] Data preparation: The experimental data consists of 300 SPOT-5 and ALOS images with a size of 1024×1024 and a resolution of 10 meters. They are all multispectral images with 4 bands.

[0116] offline processing part

[0117] (1) Principal component transformation

[0118] Perform PCA transformation on all images to obtain corresponding PCA images.

[0119] (2) Image decomposition and visual feature extraction based on pentary tree

[0120] The PCA image is decomposed into a five-point tree, and the image is divided into a series of sub-images. There are two main purposes of image segmentation, one is to obtain remote sensing images of different sizes and a certain degree of image overlap. These are the basis of the image database that makes up the search. The second is to divide the image into a series of smallest-scale sub-images for feature extraction, and each large-scale image feature is described by these small-scale sub-images. The sub-images for feature ext...

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 remote sensing image retrieval method with the integration of spatial direction relation semanteme, which mainly comprises the following steps: 1) the step of preparing off-line data: comprising image segmentation and visual feature extraction; obtaining segmentation patches trough the image segmentation, obtaining object semanteme of an image based on SVM classification of the patches, and obtaining the spatial direction relation semanteme by utilizing the new direction description method of the invention on the basis; and putting features into a base; and 2) the step of on-line image retrieval: comprising semanteme rough retrieval and fine retrieval combining the object semanteme, the spatial direction relation semanteme and visual features. The method is used for constructing the link between the low-layer visual features and high-layer semanteme information through the object-oriented SVM classification, thereby obtaining the image semanteme information. The visual features, the object semanteme and the spatial relation semanteme features of the remote sensing image are integrated in the retrieval, thereby improving the accuracy of the retrieval. The method can reduce the retrieval range and improve the retrieval efficiency through the semanteme rough retrieval and the further fine retrieval.

Description

technical field [0001] The invention relates to a remote sensing image retrieval method, in particular to a remote sensing image retrieval method that integrates spatial orientation relationship semantics and image visual features, and belongs to the field of remote sensing image processing and information extraction. technical background [0002] Remote sensing image retrieval (or called remote sensing image query) is the process of querying and returning the image or image sequence that the user is interested in from the remote sensing image database. With the rapid increase of remote sensing image data, how to effectively manage the huge image database and quickly and accurately query and retrieve image information has become an urgent problem to be solved. Summarizing the current research progress, there are mainly three methods for remote sensing image retrieval: [0003] (1) Text-Based Image Retrieval (TBIR): This retrieval method adds certain annotations or descripti...

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): G06F17/30
Inventor 汪闽万其明张大骞张青峰宋腾义顾礼斌
Owner NANJING NORMAL UNIVERSITY