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

Single-target tracking method, device and system

A single-target, to-be-tracked technology, applied in the field of computer vision, can solve the problems of poor regression box accuracy, affecting the accuracy of single-target tracking, etc.

Pending Publication Date: 2020-04-03
MEGVII BEIJINGTECH CO LTD
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, compared with the target object in the first frame, the target object in the subsequent frames often has a large deformation, resulting in poor accuracy of the regression frame predicted by the Siamese network, which directly affects the accuracy of single 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
  • Single-target tracking method, device and system
  • Single-target tracking method, device and system
  • Single-target tracking method, device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] First, refer to figure 1 An example electronic device 100 for implementing the single target tracking method, device and system of the embodiments of the present invention will be described.

[0034] Such as figure 1 Shown is a schematic structural diagram of an electronic device. The electronic device 100 includes one or more processors 102, one or more storage devices 104, an input device 106, an output device 108, and an image acquisition device 110. These components pass through a bus system 112 and / or other forms of connection mechanisms (not shown). It should be noted that figure 1 The components and structure of the electronic device 100 shown are only exemplary, not limiting, and the electronic device may have figure 1 Some components shown may also have figure 1 Other components and structures not shown.

[0035] The processor 102 may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction ...

Embodiment 2

[0042] refer to figure 2 A flowchart of a single target tracking method is shown, which is applied to a device configured with a tracking network; wherein, the tracking network includes a backbone network, an STN (Spatial Transformer Network, space transformation network) and a similarity measurement layer.

[0043] refer to figure 2 , the method specifically includes the following steps S202 to S208:

[0044] Step S202, acquiring a frame image to be tracked and a template image containing the target object; wherein, the template image and the frame image belong to the same video stream.

[0045] In practical applications, the target object can be any object that needs to be tracked, such as people, vehicles, and animals. The frame image to be tracked is an image including the target object and the surrounding environment (such as background and foreground) of the target object in the video stream. The template image is usually a pre-defined image in the video stream that...

Embodiment 3

[0094] Based on the single-target tracking method provided by the above-mentioned embodiments, this embodiment provides a single-target tracking device. The device is applied to a device configured with a tracking network; wherein, the tracking network includes a backbone network, an STN and a similarity measurement layer. see Figure 6 A structural block diagram of a single target tracking device shown, the device includes:

[0095] An image acquisition module 602, configured to acquire a frame image to be tracked and a template image containing a target object; wherein, the template image and the frame image belong to the same video stream;

[0096] The feature extraction module 604 is used to input the template image and the frame image into the backbone network, and extract the template feature map of the template image and the first feature map of the frame image through the backbone network;

[0097] A feature shift module 606, configured to perform a feature shift on ...

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 a single-target tracking method, device and system, and relates to the technical field of computer vision, and the method is applied to equipment configured with a tracking network. The tracking network comprises a backbone network, an STN and a similarity measurement layer. The method comprises the following steps: acquiring a frame image to be tracked and a template imagecontaining a target object; extracting the template feature map of the template image and the first feature map of the frame image through a backbone network; performing feature migration on the firstfeature map through the STN to obtain a second feature map; and calculating a first similarity score map between the template feature map and the second feature map through a similarity measurement layer, and determining the regression box of the target object in the frame image based on the first similarity score map. According to the invention, the accuracy of the regression box of the target object and the accuracy of target tracking can be effectively improved.

Description

technical field [0001] The present invention relates to the technical field of computer vision, in particular to a single target tracking method, device and system. Background technique [0002] The single target tracking task is to predict the regression frame of the target object in the subsequent frames of the video sequence according to the regression frame of the target object in the first frame of the given video sequence. At present, the Siamese network is mainly used to evaluate the similarity between the features in the subsequent frames and the features in the first frame, and predict the regression frame of the target object in the subsequent frames to achieve single target tracking. However, compared with the target object in the first frame, the target object in the subsequent frames often has a large deformation, resulting in poor accuracy of the regression frame predicted by the Siamese network, which directly affects the accuracy of single target tracking. ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/48G06N3/045G06F18/22
Inventor 吴晶晶邱熙
Owner MEGVII BEIJINGTECH CO LTD
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