Device and extraction method for extracting invariant characteristics of local rotation of image

A technology of rotation-invariant features and extraction methods, which is applied in the field of image local rotation-invariant feature extraction devices, can solve problems such as large memory usage and long training process, and achieve improved processing speed, less memory space, and reduced computational complexity Effect

Inactive Publication Date: 2011-08-17
张小军 +1
View PDF1 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is very fast at runtime, but the disadvantage is that it r

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
  • Device and extraction method for extracting invariant characteristics of local rotation of image
  • Device and extraction method for extracting invariant characteristics of local rotation of image
  • Device and extraction method for extracting invariant characteristics of local rotation of image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] like figure 2 As shown, a device for extracting local rotation-invariant features of an image includes a feature point positioning unit 5 for locating feature points in the image; a neighborhood division unit 6 for dividing the neighborhood of feature points into several concentric rings area, and further divide the annular area into several fan-shaped areas; the histogram statistical unit 7 is used to count local binary features in the fan-shaped area respectively, and construct a histogram.

[0033] like figure 1 As shown, the application of the present invention in the object positioning system: the object positioning system includes: a camera 1, which is used to capture image information; a local rotation invariant feature extraction device 2, which extracts the local rotation of the image according to the image information captured by the camera 1 Invariant feature; feature matching device 3, used to match the template image and the feature of the image to be det...

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 device and extraction method for extracting invariant characteristics of the local rotation of an image. The device is characterized by comprising a characteristic point positioning unit, a neighborhood dividing unit and a histogram statistical unit, wherein the characteristic point positioning unit is used for positioning a characteristic point in the image; the neighborhood dividing unit is used for dividing the neighborhood of the characteristic point into a plurality of concentric annular areas and further dividing the annular areas into a plurality of sectorial areas; and the histogram statistical unit is used for performing statistics of local binary characteristics in the sectorial areas respectively so as to establish a histogram. As the means for extracting the invariant characteristics of the local rotation is adopted, the computational complexity is greatly reduced, less memory space is occupied, therefore the speed of a computer for processing the image is improved under the condition that the positioning accuracy is ensured.

Description

technical field [0001] The invention relates to an image processing technology, in particular to an extraction device and an extraction method for local rotation-invariant features of an image. Background technique [0002] Image local invariant features refer to a set of numerical values ​​that are used to describe an image and can remain unchanged under a specific transformation. Image local invariant features have a wide range of applications in computer vision, such as object detection, localization, image retrieval, 3D reconstruction and so on. [0003] At present, the most widely used image local invariant features in academia and industry are Sift, Surf, etc. The Sift disclosed in US6711293 can guarantee a good matching rate under various lighting and viewing angle changes, and is the most effective image local invariant feature proved by practice. However, Sift is born with high computational complexity, which largely limits its wide application, especially on embe...

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): G06K9/46G06T7/00
Inventor 张小军宋金龙
Owner 张小军
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