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

Twin network video target tracking method and device

A twin network and video tracking technology, applied in the field of video analysis, can solve the problems of tracking real-time decline, target drift, etc.

Active Publication Date: 2021-02-09
NANJING UNIV OF POSTS & TELECOMM
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies in the prior art, to provide a twin network video target tracking method based on the layered attention mechanism, to solve the problem that in the video target tracking, the target is affected by complex environments such as background clutter, and there will be Target drift or tracking real-time decline, and also consider the technical problems of target scale changes

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
  • Twin network video target tracking method and device
  • Twin network video target tracking method and device
  • Twin network video target tracking method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0089] The present embodiment provides a method for tracking a twin network video object based on a layered attention mechanism. The method includes the following steps:

[0090] Step 1, read and preprocess the template image and search image input by the network;

[0091] Step 2. Input the preprocessed template image and search image into the trained Siamese network model respectively, and obtain the feature maps of the template image and search image respectively through the Inception module and the feature extraction module of the convolutional layer;

[0092] The twin network model is divided into a template branch and a search branch, the template branch and the search branch extract features respectively through the improved feature extraction module, and the attention module is added to the template branch to perform feature recalibration;

[0093] Step 3. Pass the low-level features extracted by the third layer of the template branch network and the high-level features...

Embodiment 2

[0162] This embodiment provides a twin network video target tracking method based on a layered attention mechanism. In order to make the purpose, implementation scheme and advantages of the present invention clearer, the sequence Singer1 in the public test set OTB Benchmark is taken as an example below to describe this The specific implementation of the invention is further described in detail in conjunction with the description of the accompanying drawings, specifically as follows:

[0163]The present invention proposes a Siamese network tracking method based on a hierarchical attention mechanism. This method divides the tracking process into two parts: target position estimation and target scale estimation. Convolutional neural network is used for feature extraction, and the features of the third layer and the features of the fifth layer are weighted and fused to obtain the tracking result. Then use the scale filter for scale estimation. By setting the scale pool, train the...

Embodiment 3

[0222] The embodiment of the present invention also provides a twin network video tracking device based on a layered attention mechanism, including a processor and a storage medium;

[0223] The storage medium is used to store instructions;

[0224] The processor is configured to operate according to the instructions to execute the steps of the method in the first embodiment.

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 technical field of video analysis, and discloses a twin network video target tracking method based on a hierarchical attention mechanism. According to the invention, high-level features and low-level features are fused on the basis of a twin network framework, in the feature extraction process, an attention mechanism is used for re-calibrating a feature map, and an AdaBoost algorithm is used for carrying out weighted fusion on a target feature map. In addition, the Inception module is used, on one hand, the width of the network and the adaptability of the twin network to the scale are increased, on the other hand, parameters are reduced, and the network training speed is increased. When target scale estimation is carried out, a rapid HOG feature extraction algorithm based on a region is used. Compared with the prior art, the method provided by the invention not only can accurately track the target, but also can effectively improve the tracking speed.

Description

technical field [0001] The invention relates to a twin network video target tracking method based on a layered attention mechanism, which belongs to the field of video analysis. Background technique [0002] Video target tracking is one of the research hotspots of computer vision, and has broad application prospects in many aspects such as human-computer interaction, military reconnaissance, unmanned driving, and security. [0003] Because of its fast calculation speed, the correlation filter can make the target tracking reach real-time. However, the manual features used in correlation filtering have limited target tracking capabilities in complex environments due to limited feature expression capabilities. With the rise of deep learning, researchers began to apply the features obtained by deep network learning to correlation filtering. For example, Ma et al. proposed a Hierarchical Convolutional Features (HCF) method by analyzing the network features of VGG-19. This meth...

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): G06T7/246G06K9/62
CPCG06T7/248G06T2207/20081G06T2207/20084G06T2207/10016G06T2207/20056G06F18/253Y02T10/40
Inventor 胡栋张虎邱英灿
Owner NANJING UNIV OF POSTS & TELECOMM
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