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

A spatial image query method and system

A technology of spatial image and query method, which is applied in the field of spatial image query and system, can solve problems such as inability to effectively expand and process multiple keywords, and inability to effectively solve spatial image query problems, and achieve the effect of processing query problems

Active Publication Date: 2017-11-21
SUZHOU UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional image query technology based on text description relies on the text annotation of the image, and the query is realized through the keyword submitted by the user. However, an image usually contains hundreds of feature points, and each feature point can be quantified into hundreds of visual words. At present, the relatively mature top-k spatial keyword query model is limited to processing queries containing a small number of keywords (generally no more than 8), and cannot effectively expand and process multiple keywords. Image query problem

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
  • A spatial image query method and system
  • A spatial image query method and system
  • A spatial image query method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] Embodiment 1 discloses a spatial image query method, refer to figure 1 , the method may include the following steps:

[0059] S101: Receive a spatial image query request submitted by a user, where the spatial image query request includes a query image carrying first location information.

[0060] Under the premise of the current popularization of mobile terminals, mobile Internet and GPS devices, users can conveniently take photos and mark their geographical locations, so image search in road network space has gradually become a popular demand in people's daily life. Based on this, this paper The application effectively solves the spatial image query problem by providing an efficient spatial image query method. For example, for the application scenario of mobile product search, assuming that a user finds a shoe in a certain shopping mall, after the user submits a spatial image query, k shoes with the same or similar style and close geographical location can be returned...

Embodiment 2

[0107] Embodiment 2 discloses a space image query system, refer to figure 2 , the system includes a receiving module 100 , a processing module 200 and a query module 300 .

[0108] The receiving module 100 is configured to receive a spatial image query request submitted by a user, where the spatial image query request includes a query image carrying first location information.

[0109]The processing module 200 is configured to perform preset processing on the query image to obtain a visual bag-of-words model of the query image.

[0110] Among them, such as image 3 As shown, the processing module 200 includes an extraction unit 201 and a bag-of-words model acquisition unit 202 .

[0111] An extraction unit 201, configured to extract each local feature of the query image;

[0112] The bag-of-words model acquisition unit 202 is used to quantify each local feature of the query image into a corresponding visual vocabulary based on the pre-trained image index visual vocabulary ...

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 spatial image query method and system of the present invention, after receiving the spatial image query request submitted by the user, performs preset processing on the query image carrying the location information included in the request to obtain the visual bag-of-words model of the query image; then , use the visual word bag model and location information of the query image to search the image data set based on image content and location information, and realize top-k images (the best k images) based on image content similarity and spatial proximity Query, for user reference. It can be seen that, unlike the traditional image query technology that performs text query based on keywords, the present invention performs query based on image content (represented by a visual bag-of-words model) based on images submitted by users, without the limitations of text queries. It can effectively deal with the query problem of spatial images.

Description

technical field [0001] The invention belongs to the technical field of image search based on road network space, and in particular relates to a space image query method and system. Background technique [0002] With the popularity of mobile terminals, mobile Internet and GPS (Global Positioning System, Global Positioning System) equipment, image search in road network space has gradually become a popular demand in people's daily life. [0003] Image search in road network space is a query technology that includes image information and spatial location constraints. By searching image datasets with location labels within the road network range, it returns to the user more interesting information in the area of ​​interest. Goods or services (images). For example, if a user is interested in a certain type of shoes in a shopping mall, he can use spatial image search to know which shopping malls in the surrounding area have shoes of the same or similar style for comparison and pur...

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): G06F17/30
Inventor 赵朋朋许佳捷吴健崔志明
Owner SUZHOU 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