tld video moving object tracking method using gpu hardware

A moving target and video technology, applied in the computer field, can solve problems such as large amount of calculation and the inability of TLD algorithm to achieve real-time tracking of moving targets, and achieve the effect of improving filtering speed and speed.

Active Publication Date: 2020-04-07
XIDIAN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The train of thought that realizes the object of the present invention is, aim at the defect that TLD algorithm can't realize the real-time tracking of the moving object in the video, use GPU hardware, improve at the part with large amount of computation in TLD algorithm, have developed the TLD video moving object based on GPU hardware The tracking system achieves the effect of real-time tracking of moving targets in video on ordinary PCs

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
  • tld video moving object tracking method using gpu hardware
  • tld video moving object tracking method using gpu hardware
  • tld video moving object tracking method using gpu hardware

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] refer to figure 1 , to further describe the specific steps of the present invention.

[0040] Step 1, get the grayscale image.

[0041] Load any frame image in the video to be tracked into the computer memory and convert it into a grayscale image.

[0042] Step 2, determine whether the grayscale image is the first frame image in the video to be tracked, if so, perform step 3, otherwise, perform step 5.

[0043] Step 3, determine the rectangular frame of the initial moving target position.

[0044] From the grayscale image of the first frame in the video to be tracked, the rectangular frame containing the moving target to be tracked is taken as the position rectangular frame of the moving target.

[0045] Step 4, obtain the grayscale image element.

[0046] Step (9) is performed after dividing the grayscale image into image elements with a step size of 15 pixels.

[0047] Step 5, tracking the element feature points of the grayscale image.

[0048] In the rectangula...

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 TLD video moving object tracking method by using GPU hardware, and solves the problems that the prior art is not high in tracking performance and has no real-time processing capability. The method includes the following steps of obtaining a gray image, determining whether the gray image is a first frame image in a to-be-tracked video, determining a initial moving object position rectangular frame, obtaining gray image primitives, tracking the feature points of the gray image primitives, screening the image primitives of the gray image, conducting wave filtering on the image primitives of the gray image, determining a moving object position rectangular frame, training a classifier, judging whether all the frame images in the to-be-tracked video are loaded or not, and completing object tracking. The method can achieve real-time tracking of a moving object in the video in a universal computer.

Description

technical field [0001] The invention belongs to the technical field of computers, and further relates to a tracking learning detection TLD (Tracking-Learning-Detection) video moving target tracking method using computer graphics processor GPU (Graphics Processing Unit) hardware in the technical field of computer video target tracking. The invention can realize the acceleration of the tracking algorithm of the tracking-learning-detection TLD (Tracking-Learning-Detection) video moving object, and can realize real-time tracking of the moving object in the video on a general-purpose computer. Background technique [0002] Object tracking method with high speed and high performance is the core technology in the field of computer vision. The current target tracking methods are divided into two categories: one is the tracking method based on feature matching, which mainly constructs the features that can represent the target, and then judges the position of the target through the m...

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): G06T7/246
CPCG06T2207/10016G06T2207/20016
Inventor 雷杰闫旭伟李云松王柯妍张静郭杰刘凯吴宪云
Owner XIDIAN UNIV
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