A video object tracking method based on compressed regularized block difference

A target tracking and video technology, applied in image analysis, image enhancement, instruments, etc., can solve the problems of single pixel value noise interference, NPD feature susceptible to noise interference dimension, NPD feature vector unreliability and other problems, and achieve the Noise interference, the effect of promoting rapidity

Active Publication Date: 2021-11-02
YUNNAN UNIV +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] (2) NPD features are susceptible to noise interference and the dimension is too high
However, due to the limitation of imaging equipment or digitization process, single pixel value is easily disturbed by noise, if it is directly introduced into the video target tracking process, it will lead to the unreliability of NPD feature vector
Furthermore, the high dimensionality of NPD features will affect the speed of video target tracking

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 video object tracking method based on compressed regularized block difference
  • A video object tracking method based on compressed regularized block difference
  • A video object tracking method based on compressed regularized block difference

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0118] The technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments:

[0119] like figure 1 As shown, according to the technical solution of the present invention, the target in a video frame sequence Basketball is tracked as follows, and the scene features are perspective changes, similar interference, occlusion, etc.

[0120] Step 1. Select the tracking area

[0121] The video frame width and height are W=576 and H=432 respectively. The rectangular area (198, 214, 34, 81) of the target to be tracked in the first frame, that is, the coordinates of the upper left corner are (198, 214), and the width and height are (34, 81).

[0122] Step 2. Initialize the measurement matrix

[0123] Compression Measurement Matrix The number of rows, that is, the dimension of the CNBD feature vector is m=100, the number of columns, that is, the dimension of the NBD feature vector is n=1.6519...

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 video target tracking method based on compressed regularized block difference. The implementation steps are as follows: Step 1. Select the tracking area; Step 2. Initialize the measurement matrix; Step 3. Initialize the target classifier; Step 4. Update the target Classifier; Step 5. Input new video frame; Step 6. Generate a rough candidate target set; Step 7. Calculate the CNBD feature vectors of all candidate targets in the rough candidate target set; Step 8. Discriminate rough tracking results; Step 9. Generate detailed Candidate target set; Step ten. Calculate the CNBD feature vectors of all candidate targets in the detailed candidate target set; Step eleven. Discriminate the tracking result of this frame; Step twelve. If the current frame is the last frame, the tracking ends; otherwise, go to Step four. In this method, the tracked target or candidate target is expressed by compressed regularized block difference features, and a set of candidate targets is generated by a sliding window method from coarse to fine.

Description

technical field [0001] The invention relates to the field of video target tracking methods, in particular to a video target tracking method based on compressed regularized block difference. Background technique [0002] Video object tracking is to use discriminative features to track moving objects in video frame sequences to analyze their motion parameters and trajectories. However, factors such as object deformation, illumination changes, occlusion, and background chaos in actual scenes have brought great challenges to video object tracking technology. Many applications such as intelligent video surveillance, robot navigation, and human-computer interaction require video object tracking methods to be both accurate and fast. [0003] In the whole process of the video target tracking method, prior art 1Wang N, Shi J, Yeung D Y, et al. Understanding and diagnosing visual tracking systems[C] / / Proceedings of the IEEE International Conference on Computer Vision.2015:3101-3109. ...

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): G06T7/246G06T7/223
CPCG06T2207/10016G06T7/223G06T7/246
Inventor 高赟张登卓周浩张晋林宇兰戈
Owner YUNNAN 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