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

A Method of Image Feature Point Description

A technology of image feature points and pixel points, which is applied in the field of video processing to ensure the effect of rotation invariance

Active Publication Date: 2021-10-22
深圳市兴海物联科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to provide a method for describing image feature points, which aims to solve the problem that the existing video characterization method only uses part of the information of the video to perform one-sided characterization of the video

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 Method of Image Feature Point Description
  • A Method of Image Feature Point Description
  • A Method of Image Feature Point Description

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0026] figure 1 The basic flow chart of the method for describing the spatiotemporal feature points of video images provided in this embodiment, the method includes:

[0027] S101. Determine the main direction of the video image according to the spatio-temporal feature points on the integrated video.

[0028] The specific steps of this S101 are: constructing a cylindrical area centered on the spatio-temporal feature points on the integrated video of the video image, and performing wavelet calculation on the integrated video in the preset area of ​​the cylindrical area, to obtain each preset area of ​​the integrated video in the cylindrical area. Set the wavelet calculation value of the area, compare the wavelet calculation value of each preset area, and determine the direction corresponding to the preset area with the largest wavelet calculation value as the main direction θ of the spatiotemporal feature point.

[0029] It should be understood that the aforementioned cylindri...

no. 2 example

[0063] This embodiment also provides an image spatiotemporal feature point description device, see figure 2 As shown, it includes a processor 21, a memory 22 and a communication bus 23, wherein:

[0064] The communication bus 23 is used to realize connection and communication between the processor 21 and the memory 22;

[0065] The processor 21 is used to execute the program stored in the memory 22, so as to realize the steps of the method for describing the spatio-temporal feature points of the video image in the above-mentioned first embodiment.

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 method for describing image feature points, because in the method, the descriptor of the spatio-temporal feature points contains the grayscale information and motion information of the video image; at the same time, the method rotates the wavelet operation value to ensure the description The rotation invariance of the descriptor; and the wavelet response value used to obtain the descriptor is not only the wavelet response value of the spatiotemporal feature point, but also includes the wavelet response value of each pixel in the area centered on the spatiotemporal feature point. Based on the above three points, the descriptor obtained by the method disclosed in the present invention can characterize the video image more accurately, thereby avoiding the problem of one-sided video representation.

Description

technical field [0001] The present invention relates to the technical field of video processing, and more specifically, relates to an image feature point description method. Background technique [0002] In the existing video characterization methods, a video is often decomposed into multiple single-frame images, and the video is represented by obtaining the grayscale information of the pixels on the video image and based on the grayscale information of the pixels, but a video contains The information is not only the grayscale information of the pixels, but also includes the pixel correlation between the video time series, so the method of characterizing the video is one-sided, and it does not characterize the video according to the time information contained in the video. [0003] Referring to the method of extracting feature points in image pixels in the prior art, and describing the feature points to realize the method of characterizing the image, it can be considered to ...

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): G06K9/46
CPCG06V10/44
Inventor 李岩山杨从柱张力范雷东李庆腾谢维信
Owner 深圳市兴海物联科技有限公司
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