Unlock instant, AI-driven research and patent intelligence for your innovation.

A Scale Adaptive Target Tracking Method Based on Log-Likelihood Images

A scale-adaptive, log-likelihood technique used in instruments, character and pattern recognition, computer components, etc., to solve problems such as no robust method

Active Publication Date: 2017-02-01
ZHEJIANG UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the above tracking algorithms have achieved certain results in dealing with the problem of target scale changes, there is no effective and robust method so far.

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 Scale Adaptive Target Tracking Method Based on Log-Likelihood Images
  • A Scale Adaptive Target Tracking Method Based on Log-Likelihood Images
  • A Scale Adaptive Target Tracking Method Based on Log-Likelihood Images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0063] The present invention proposes a scale-adaptive target tracking method based on the log-likelihood image. First, the log-likelihood image is established according to the color difference between the target and the background, and the image is subjected to mathematical morphology processing; secondly, the obtained Ellipse fitting is performed on the logarithmic graph of the target to obtain the scale of the target; finally, the target model of the Mean-Shift algorithm and the window width of the kernel function are updated according to the target scale, and the target is tracked through continuous iteration.

[0064] Such as figure 1 with figure 2 As shown, the scale-adaptive target tracking method based on the log-likelihood image includes...

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 scale adaptive target tracking method based on a log likelihood image. The method comprises the following steps of firstly establishing a log likelihood image according to the color difference between a target and a background and carrying out mathematical morphology processing on the image, secondly calculating the second-order central moment of the previously obtained log likelihood image and carrying out ellipse fitting to obtain the scale and rotation direction of the target, and finally updating the object model and kernel bandwidth of the Mean-Shift algorithm according to the target scale and carrying out target tracking through continuous iteration. According to the method, the ellipse fitting of the target can be rapidly carried out on the log likelihood image, thus the real scale of the target is accurately calculated, and a Mean-Shift tracking algorithm model is updated. The method has the advantages that the realization of the algorithm is simple, the whole process is automatically completed, and the real-time scale adaptive target tracking can be realized.

Description

technical field [0001] The invention belongs to the field of computer vision and pattern recognition, and relates to a method for performing scale adaptive tracking on a video target. Background technique [0002] Object tracking is a very challenging research topic in the field of computer vision, and has broad application prospects in intelligent video surveillance, augmented reality, gesture recognition, and automatic driving. In the past two decades, many institutions and experts at home and abroad have done a lot of related work and proposed many algorithms and technologies. According to the different methods used to model the target performance, tracking algorithms can be divided into two categories: target tracking algorithms based on generative models and target tracking algorithms based on discriminant models. [0003] Tracking algorithms based on generative models first learn an object representation model, and then search for objects most similar to this model on...

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): G06K9/62
Inventor 于慧敏曾雄
Owner ZHEJIANG UNIV