Adaptive correlation filter target tracking method and system

A correlation filter and target tracking technology, applied in the field of image processing, can solve problems such as difficulty in improving the accuracy of tracking algorithms and inability to solve interference problems.

Inactive Publication Date: 2018-09-18
CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF2 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the difficulty of improving the accuracy of the tracking algorithm in the prior art and the inability to solve the interference of various factors in the tracking process, the present invention provides an adaptive correlation filter target tracking method and system

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
  • Adaptive correlation filter target tracking method and system
  • Adaptive correlation filter target tracking method and system
  • Adaptive correlation filter target tracking method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The specific embodiments of the present invention will be described in further detail below in conjunction with the drawings and embodiments. The following examples are used to illustrate the present invention, but not to limit the scope of the present invention.

[0046] It should be noted that an adaptive correlation filter target tracking method provided by the present invention can achieve tracking of the target position in a subsequent video sequence given the target state of any frame for a target video sequence. In this embodiment, the target position in the current frame image is known, and the target position in the next frame image is now tracked according to the target position in the current frame image.

[0047] Please refer to figure 1 , figure 1 This is a schematic diagram of the overall flow of an adaptive correlation filter target tracking method according to an embodiment of the present invention, such as figure 1 As shown, the present invention provides an...

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 provides an adaptive correlation filter target tracking method and system. The method comprises: a target image in a current frame of image is inputted into a preset neural network and atarget feature inputted to each pooled layer in the preset neural network is extracted; a Gaussian function of target image distribution is constructed and a correlation filter of each channel is constructed according to a feature map and a Gaussian function of each channel in each target feature; a candidate target image is obtained from a next frame of image, the candidate target image is inputted into the preset neural network, and a candidate target feature inputted to each pooled layer in the preset neural network is extracted; according to feature maps of all channels in each candidatetarget feature and correlation filters of all channels, a response graph corresponding to each candidate target feature is calculated, and weighted operation is carried out on all response graphs to obtain a target response graph; and on the basis of the location of the largest response value in the target response graph, a target image in a next-frame of image is determined. With the method and system, the accuracy of target tracking is improved effectively.

Description

Technical field [0001] The present invention relates to the technical field of image processing, and more specifically, to an adaptive correlation filter target tracking method and system. Background technique [0002] Target tracking is an important and challenging research direction in the field of computer vision. Target tracking technology has a wide range of applications in both civil and military, including video surveillance, human-computer interaction, unmanned driving, and missile tracking and interception. The basic idea of ​​target tracking technology is to determine the position and posture of the target of interest in each frame according to the temporal and spatial correlation of the target in the video information in the sequence of images. [0003] After decades of development, target tracking technology has made considerable progress, and many tracking algorithms with different implementation methods have been proposed. However, when the existing tracking algorit...

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 Applications(China)
IPC IPC(8): G06T5/00G06N3/04
CPCG06T5/002G06N3/045
Inventor 张建明金晓康李旭东
Owner CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
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