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

A Target Tracking Method Based on Statistical Features of Orientation Gradient

A technology of directional gradients and statistical features, which is applied in computing, image analysis, image enhancement, etc., can solve the problems of large amount of algorithm calculation and difficulty in ensuring real-time performance of the algorithm, so as to reduce calculation time, improve image processing speed, and improve real-time performance Effect

Active Publication Date: 2021-09-07
NO 27 RES INST CHINA ELECTRONICS TECH GRP
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Because this algorithm uses the global information of the target, such as color, texture, etc., it has high reliability, but at the same time it has obvious limitations, such as being susceptible to changes in the light and shade of the image background, the distance scale transformation of the target, and the rotation and other factors, and the calculation load of the algorithm is very large. Although there are many simplified and optimized search algorithms, in special cases (high-resolution images or targets with relatively large areas), the real-time performance of the algorithm hard to guarantee

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 Target Tracking Method Based on Statistical Features of Orientation Gradient
  • A Target Tracking Method Based on Statistical Features of Orientation Gradient
  • A Target Tracking Method Based on Statistical Features of Orientation Gradient

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] like figure 1 As shown in A of the present invention, a gradient direction of the target tracking method based on statistical characteristics, comprising the steps of:

[0042] Direction A, to select a first tracking target captured video frame image, taken according to the target track position of the manual where the rectangular block diagram of a suitable size as the initial target template image, and extracts an initial target template image gradients statistical feature.

[0043] B, a gradient statistical characteristics of the two-dimensional Fourier transform of the direction of the initial target template image, wherein the frequency domain to obtain the initial target template image.

[0044] C, select the next frame tracking target captured image of the video, the original image as the angle and scale size of the image transformation, the original image and the image size obtained by the conversion as the search area image.

[0045]The search area image centers of...

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 present invention provides a target tracking method based on directional gradient statistical features, comprising the following steps: selecting an initial target template image and extracting directional gradient statistical features; calculating the frequency domain features of the initial target template image; acquiring search area images and extracting directional gradient statistics Features; calculate the frequency domain features of the image in the search area; obtain the update position, scaling and rotation angle of the tracking target through the frequency domain response; select the current target template image and extract the direction gradient statistical features; calculate the frequency domain features of the current target template image; use the current target The frequency domain feature of the template image updates the frequency domain feature of the initial target template image, and performs target tracking on the next frame image. The invention effectively weakens the interference of factors such as image brightness, contrast, target deformation, target rotation, etc., realizes precise tracking of the target, and simultaneously improves the operation processing speed, thereby improving the real-time performance of target tracking.

Description

Technical field [0001] The present invention relates to target tracking feature, and in particular relates to a method of tracking a target direction based on the statistical characteristics of the gradient. Background technique [0002] Characteristics of the target complex background has been the difficulty of tracking the image tracking. Typically, there is a contrast area associated tracking and tracking method based on image matching based tracking algorithm. [0003] Tracking method to track contrast, the use of contrast difference between the target and background to identify and extract the target signal, so as to achieve target automatic tracking method. This method of tracking according to the tracking reference points can be divided into: edge tracking, centroid tracking peak tracking, can quickly track the target, the target posture change adaptability, but the difference in the ability to identify the target, it is difficult to track complex background the target app...

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): G06T7/246G06T7/262G06T7/269
CPCG06T2207/10016G06T7/248G06T7/262G06T7/269
Inventor 郑耀锋武林伟孙必慎赵晓杰潘璠郭会娜张秀霞王小军熊卫兵柴淑清李博曹玉东候志恒杜光伟马宝峰秦刚李世伟
Owner NO 27 RES INST CHINA ELECTRONICS TECH GRP
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