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

Image tracking method and system thereof

A technology of image tracking and tracking area, which is applied in the field of image tracking and can solve the problems of poor real-time tracking and large amount of calculation

Active Publication Date: 2009-03-25
中星智能系统技术有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since each window area is searched, the above-mentioned process of calculating the histogram must be repeated, and because in the exhaustive search, the calculation of many pixels is repeated, so the amount of calculation is large, such as in the size of 100×100 When searching for a 20×20 target in the search window of , if three scale changes are considered, at least about 3×80×80×20×20=7680000 calculations are required, which shows that the amount of calculation is relatively large, so in the prior art, The real-time tracking performance of the target tracking algorithm based on global search is poor

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 tracking method and system thereof
  • Image tracking method and system thereof
  • Image tracking method and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0084] see figure 1 , figure 1 It is a flow chart of the image tracking method in Embodiment 1 of the present invention. Such as figure 1 As shown, the process includes the following steps:

[0085] Step 101, setting a tracking area in the current frame image.

[0086] In this step, there are many ways to set the tracking area. One of them may be: first obtain the predicted position of the target through position prediction, and then set the entire tracking area of ​​the target according to the maximum moving speed of the target based on the predicted position of the target.

[0087] For example: the following position prediction method can be used to obtain the predicted position of the target:

[0088] If the tracked target’s position at time t is (x t ,y t ), at time t-Δ t The position is (x t-1 ,y t-1 ), then the velocity of the current target can be simply estimated as v x =(x t -x t-1 ) / Δ t , v y =(y t -y t-1 ) / Δ t .

[0089] Considering the irregular ...

Embodiment 2

[0165] The image tracking method in this embodiment is roughly the same as the image tracking method in Embodiment 1, the difference is that:

[0166] exist figure 1 In step 102 of the shown method flow, the first embodiment uses a color histogram, but in this case, when there is an object with a color similar to the target in the tracking area, since the color histogram is only a description of the color , so it is easy to be interfered by objects with similar colors to the target, making the tracking inaccurate. Therefore, in step 102 of this embodiment, on the basis of using the color histogram, another histogram is added, that is, the gradient direction histogram picture.

[0167] The gradient direction histogram refers to: determine the angle interval of the gradient direction according to the number of histogram groups; calculate the angle interval to which the gradient direction of each pixel belongs, and obtain the histogram group to which the pixel belongs. The spec...

Embodiment 3

[0181] The image tracking method in this embodiment may adopt steps 101 to 106 in Embodiment 1, or may adopt Steps 101 to 106 in Embodiment 2. The difference between this embodiment and embodiment one or embodiment two is:

[0182] The first point: In order to reflect the edge characteristics and spatial position characteristics of the target, the target is divided into blocks according to the preset number of blocks in advance, and the block histogram of the target is calculated. Then the standard histogram of the target also includes the block histogram.

[0183] Wherein, the standard histogram of the target in Embodiment 1 and Embodiment 2 is the global histogram of the target, and the standard histogram of the target in this embodiment includes not only the global histogram of the target, but also the block histogram of the target. Assuming that the target is divided into M×N blocks, and the histogram includes the histogram and gradient direction histogram of each color c...

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 an image tracking method comprising: calculating histograms of all regions, which use a predetermined corner of a whole tracking region as a starting point, in the whole tracking region by an integral operation, to obtain a region integral histogram; calculating histograms of every search windows, where a target may be appeared, in the whole tracking region, matching the calculated histograms of the search windows with a standard histogram of the target, obtaining a matching result, and determining a tracking position of the target according to the matching result. In addition, the invention also discloses an image tracking system. The image tracking method and system provided in the invention can ensure tracking effect and increase tracking speed.

Description

technical field [0001] The invention relates to image tracking technology, in particular to an image tracking method and system. Background technique [0002] In the current image tracking technology, the target tracking algorithm based on histogram matching is usually used to track the target, that is, to search for the best matching corresponding target in the area where the target may appear in a new frame of image, as the new position of the target. Among them, considering that the size of the target in each frame of image may be different due to the distance movement of the target during the shooting process of each frame of image, that is, the scale of the target in each frame of image may be different, therefore, in In addition to the areas of different positions in the tracking area, the areas where the target may appear in the new frame of image also include areas formed by scaling the same position at different scales. [0003] In the target tracking algorithm bas...

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): G06T7/20
Inventor 曾志王耀辉
Owner 中星智能系统技术有限公司
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