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

Feature extraction method for identifying and tracking moving target

A moving target and feature extraction technology, applied in the field of image processing, can solve the problems of large difference between matching templates, mismatch, loss, etc., to achieve fast feature extraction, improve extraction efficiency, and improve the effect of robustness

Active Publication Date: 2019-09-10
CHINA UNIV OF MINING & TECH
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Before identifying and tracking the moving target, it is first necessary to extract the features of the target and use the extracted features as a matching template to complete the identification and tracking of the target. In a real environment, the moving target will enter from a bright place under natural light In the shadow, the imaging results of the image are very different from those in the bright area, which seriously affects the image acquisition quality and finally leads to the wrong identification and tracking loss of the moving target. When multiple imaging conditions occur at the same time, the traditional moving target The feature extraction method for recognition and tracking is only robust to one or two of illumination, rotation, scale, and non-rigid deformation, but when these four external conditions change at the same time, it will seriously affect the moving target. image quality and recognition accuracy, especially in the case of non-rigid deformation, such as when the moving target is a person, people often rise, squat, run, jump or bend over when they are in motion, which will lead to During recognition, there is a big difference between the feature matching template and false matching occurs. In addition, during the movement process, due to the influence of the shooting angle of the video acquisition device, the target that may be collected is the result of imaging under different viewing angles, which provides automatic recognition of the target. and tracking have brought a great impact, which seriously restricts the effect of moving target recognition and tracking in practical applications. Therefore, the present invention proposes a feature extraction method for moving target recognition and tracking to solve the problems of existing technologies. inadequacies in

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
  • Feature extraction method for identifying and tracking moving target
  • Feature extraction method for identifying and tracking moving target
  • Feature extraction method for identifying and tracking moving target

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In order to deepen the understanding of the present invention, the present invention will be further described below in conjunction with the examples, which are only used to explain the present invention, and do not constitute a limitation to the protection scope of the present invention.

[0038] according to figure 1 As shown, the present embodiment proposes a feature extraction method for moving target recognition and tracking, including the following steps:

[0039] Step 1: Image input and preprocessing of the input image, first convert the image to be preprocessed into a grayscale image sequence, then use histogram equalization to perform low-light image enhancement on the converted grayscale image, and enhance The final image is subjected to image noise reduction based on wavelet threshold;

[0040] Step 2: Construct the scale space, use the Gaussian kernel convolution function to generate the scale space pyramid, and perform convolution operation on a grayscale ...

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 provides a feature extraction method for identifying and tracking a moving target. The method comprises the following steps: inputting an image and preprocessing the input image; using aGaussian kernel convolution function to generate a scale space pyramid; detecting feature points by adopting a Hessian matrix, roughly positioning the feature points, accurately positioning the feature points, extracting the main direction and the main curvature of the geometric surface of the image, calculating the gradient and the direction of the feature points according to the main curvature,and counting and labeling the obtained gradient amplitude and direction information by utilizing a method similar to HOG. According to the method, through using the Gaussian convolution function to construct the scale space, the scale invariant characteristic of the extracted feature points can be improved. The feature points of accurate positioning can be accurately acquired, gradient amplitudeand direction information of the acquired feature points can be guaranteed, good robustness on illumination can be realized, and good robustness on illumination, rotation, scale, visual angle, non-rigid deformation and other changes is realized.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a feature extraction method for moving target recognition and tracking. Background technique [0002] Artificial intelligence (AI) is the hottest research field in the world today, and computer vision, as an important research hotspot in artificial intelligence technology, plays a vital role in promoting the development and progress of artificial intelligence. At present, computer vision has Widely used in target recognition and tracking, scene understanding, medical image analysis and product quality inspection and other fields; [0003] Before identifying and tracking the moving target, it is first necessary to extract the features of the target and use the extracted features as a matching template to complete the identification and tracking of the target. In a real environment, the moving target will enter from a bright place under natural light In the shadow, the im...

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): G06K9/00G06K9/40G06K9/46G06T7/246
CPCG06T7/246G06V40/20G06V10/30G06V10/507
Inventor 寇旗旗程德强李腾腾付新竹刘钊袁永龚飞李海翔
Owner CHINA UNIV OF MINING & TECH
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