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

A target tracking algorithm based on kernel correlation filtering and frame difference method

A technology of kernel correlation filtering and tracking algorithm, applied in the field of computer vision, can solve the problems of target tracking algorithm tracking failure, low resolution, and few pixels occupied by the target

Inactive Publication Date: 2019-04-02
武汉嫦娥信息科技有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But among many target tracking algorithms, there is still no method suitable for satellite video data tracking
This is because in the target tracking process of satellite video data, in addition to the factors that often occur in traditional target tracking data, such as the target being blocked by obstacles, illumination changes, imaging blur, and fast moving targets, the unique characteristics of satellite video data Influencing factors such as large image files, few pixels occupied by the target, low resolution and high background similarity lead to the failure of many target tracking algorithms

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 algorithm based on kernel correlation filtering and frame difference method
  • A target tracking algorithm based on kernel correlation filtering and frame difference method
  • A target tracking algorithm based on kernel correlation filtering and frame difference method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0019] The present invention provides a broad framework for tracking algorithm fusion using ensemble learning [1] The theory of the two tracking algorithms can be fused into a strong tracker, while absorbing the advantages of the two tracking algorithms. In the process of multi-algorithm fusion, the distance between the candidate frame and the target is mainly measured by calculating the attractiveness a of the candidate frame. And use parallel technology to improve the time performance of the fusion algorithm. The fusion algorithm can outperform the single tracking algorithm in accuracy.

[0020] [1] Dietterich T G. Ensemble learning [J]. The handbook of brain theory and neural networks, 2002, 2: 110-125.

[0021] Attraction a is introduced to measure the distance between the candidate box and the target. The present invention sets a param...

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 belongs to the field of computer vision, and particularly relates to a target tracking algorithm based on kernel correlation filtering and frame difference method fusion. According to the invention, an integrated learning theory is used; aiming at the characteristics of more target tracking pixels, small target and low pixel of satellite video data, a kernel correlation filtering (KCF) algorithm and a frame difference method are selected to be fused, the two tracking algorithms are fused into a strong tracker, and the advantages of the two tracking algorithms are absorbed at thesame time, so that a target tracking task is completed according to the characteristics of the satellite video data. In the multi-algorithm fusion process, the distance between a candidate box and a target is measured mainly by calculating the attraction a of the candidate box, and the time performance of the fusion algorithm is improved by using a parallel technology. According to the invention,tracking can be carried out on satellite video data and a good tracking result can be obtained.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to a target tracking algorithm based on fusion of kernel correlation filtering and frame difference method. Background technique [0002] Object tracking is a branch of computer vision with wide applications. With the popularity of video capture equipment and the improvement of imaging quality, object tracking technology is widely used in intelligent transportation systems, object recognition, video retrieval and human-computer interaction and other fields. Scholars at home and abroad have made a lot of contributions to the research on target tracking. In some specific fields, such problems have been perfectly solved. For example, research on tracking algorithms for gestures and research on tracking algorithms for vehicles. But among many target tracking algorithms, none of them can be applied to satellite video data tracking. This is because in the target tracking pro...

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/48G06F18/241G06F18/25
Inventor 杜博
Owner 武汉嫦娥信息科技有限公司
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