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

Image classification and searching method based on geographic position characteristics and overall situation vision characteristics

A technology of visual features and geographic location, applied in still image data retrieval, still image data indexing, electrical digital data processing, etc., can solve the problems of time-consuming, low precision, unable to guarantee user location service requirements, etc., and achieve retrieval efficiency. Improves, reduces time-consuming effects

Active Publication Date: 2015-08-05
严格集团股份有限公司
View PDF3 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the low accuracy of existing outdoor images when only relying on visual features for scene classification and as the database scale continues to increase, the image retrieval process consumes a lot of time, which affects the real-time performance of the navigation and positioning algorithm, and cannot be guaranteed In view of the user's location service requirements, an image classification and retrieval method based on geographic location features and global visual features is proposed

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
  • Image classification and searching method based on geographic position characteristics and overall situation vision characteristics
  • Image classification and searching method based on geographic position characteristics and overall situation vision characteristics
  • Image classification and searching method based on geographic position characteristics and overall situation vision characteristics

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0024] Specific implementation mode one: combine figure 1 , figure 2 and image 3 To illustrate this embodiment, the image classification and retrieval method based on geographic location features and global visual features is specifically carried out in accordance with the following steps:

[0025] Step 1. Database initialization:

[0026] Collect images with geographic location information outdoors and store them as database data;

[0027] Step 2. Database image preprocessing:

[0028] Convert the image in the database into a grayscale image, extract the Gist feature as a global visual feature, and express it with a vector G, then use the position information of the grayscale image in the database as the position feature L of the grayscale image, and the fusion feature of the grayscale image in the database vector for F t ={αG,(1-α)L};

[0029] Step 3, database image clustering:

[0030] Utilize the K-means algorithm to cluster the fusion feature vector in step 2, an...

specific Embodiment approach 2

[0035] Specific embodiment 2: The difference between this embodiment and specific embodiment 1 is: the database image preprocessing in the step 2: convert the image in the database into a grayscale image, extract the Gist feature as the global visual feature, and represent it with a vector G, Then the location information of the grayscale image in the database is used as the location feature L of the grayscale image, and the fusion feature vector of the grayscale image in the database is F t ={αG,(1-α)L}; the specific process is:

[0036] (1) Scale the size of the image in the database to 300*300 pixels in proportion, and convert it into a grayscale image. The grayscale value of the grayscale image is an integer in the range of 0 to 255;

[0037] Divide the grayscale image into a 3*3 regular grid, the number of grid blocks is 9, and each grid pixel is 100*100 pixels;

[0038] Divide the gray value range into 8 scales equidistantly, the gray value range of scale 1 is 0-31, the...

specific Embodiment approach 3

[0057] Specific embodiment three: the difference between this embodiment and specific embodiment one or two is: the database image clustering in the step three: use the K-means algorithm to cluster the fusion feature vector in the step two, and calculate the clustering Center, after obtaining the clustering center, use the global visual feature vector in the vector as the visual feature of the grayscale image category in the database; the specific process is:

[0058] Step 31, randomly select p grayscale images from the database, and use the fusion feature vectors of these grayscale images as initial clustering centers;

[0059] Step 32. Calculate the Euclidean distance between the fusion feature vector of each grayscale image in the database and each initial cluster center, as shown in formula (6):

[0060] d ( F 1 , F 2 ) ...

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 relates to an image classification and searching method and provides the image classification and searching method based on geographic position characteristics and overall situation vision characteristics. The image classification and searching method aims at solving the problems that the precision is low when an existing outdoor image is subjected to scene classification by vision characteristics and a lot of time for an image searching process is spent along the gradual enlarging of a database scale, the instantaneity of a navigation positioning algorithm is influenced, and the position service requirements of a user cannot be guaranteed. The image classification and searching method is realized through the following technical scheme: step 1, initializing a database; step 2, pre-processing a database image; step 3, gathering the database image; step 4, sorting a database image type; and step 5, searching in the image type. The image classification and searching method is applied to the field of computer vision and image processing in an information technology.

Description

technical field [0001] The invention relates to image classification and retrieval methods. Background technique [0002] In outdoor visual positioning, it is necessary to collect images with geographic location information (geographical coordinates) as database images for positioning algorithms. In the vision-based positioning method, it is first necessary to search the database images according to the images collected by the user, and then determine the location of the user according to the location information of these images after obtaining the retrieved images. In the positioning process, the retrieval efficiency of database images is the key to ensure real-time positioning. As an important part of information retrieval technology, content-based image retrieval technology has become a research hotspot at home and abroad. This technology mainly uses the visual features of images such as color, texture, shape and spatial relationship to retrieve images similar to the qu...

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): G06F17/30
CPCG06F16/51
Inventor 谭学治冯冠元马琳
Owner 严格集团股份有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com