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

Visual target tracking method of full-convolution integral type and regression twin network structure

A technology of target tracking and network structure, which is applied in the field of visual target tracking of full-volume classification and regression twin network structure, can solve the problem that the tracking effect is greatly affected, achieve good tracking accuracy, improve accuracy and speed, and have a simple network structure Effect

Pending Publication Date: 2020-05-19
ZHEJIANG UNIV OF TECH
View PDF3 Cites 46 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The tracking method based on the region proposal network uses anchor frames for region proposals. Although this approach can effectively use deep feature information and avoid time-consuming repeated calculations, the setting of parameters such as the number, size, and aspect ratio of anchor frames is difficult. have a great influence on the final tracking effect
In addition, because the parameters such as the size and aspect ratio of the anchor box are kept fixed during tracking, the tracking method based on the region proposal cannot successfully track the object with large deformation.

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
  • Visual target tracking method of full-convolution integral type and regression twin network structure
  • Visual target tracking method of full-convolution integral type and regression twin network structure
  • Visual target tracking method of full-convolution integral type and regression twin network structure

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] In order to make the present invention easier to understand and its advantages clearer, the technical solutions in the embodiments of the present invention will be described in detail below in conjunction with the drawings and specific embodiments.

[0034] refer to figure 1 and figure 2 , a visual target tracking method of full convolution classification and regression Siamese network structure, including the following steps:

[0035] (1) Select the visual target tracking training set, and cut out the target template image and the search area image in the original training set according to the position of the target in the image, and the cropped image pair constitutes the training data set;

[0036] (2) Build a fully convolutional twin network to extract image features. The fully convolutional twin network includes two branch networks with the same architecture, which are respectively a branch network for extracting target template image features and a branch network...

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

A visual target tracking method of a full convolution class and regression twin network structure comprises the following steps: (1) according to the position of a target in an image, cutting a targettemplate image and a search area image in an original training set, and forming a training data set by cut image pairs; (2) establishing a full convolution twin network to extract image features; (3)establishing a classification regression network; (4) in response to the fact that each pixel point on the image has a corresponding foreground score and a predicted bounding box, calculating the total score of each pixel point by combining the information of the foreground score and the information of the bounding box, wherein the pixel point with the highest total score is the center of the tracking target; and (5) training the full convolution twin network and the classification regression network by using the training data set to obtain the trained full convolution twin network and the classification regression network, calculating a score graph of a target in the to-be-tested image sequence by using the trained networks, and performing target positioning based on the score graph. According to the invention, the tracking precision and speed are improved.

Description

technical field [0001] The method relates to the field of visual object tracking, and more specifically, relates to a visual object tracking method with full convolution classification and regression Siamese network structure. Background technique [0002] Visual object tracking is a basic research problem in the field of machine vision, which is widely used in intelligent monitoring, human-computer interaction and unmanned driving and other fields. Although the research of object tracking has made great progress, however, object tracking is still a very challenging task in practical applications. Because in practical applications, the tracked target will inevitably encounter illumination changes, scale changes, background interference, target occlusion and target deformation. [0003] Traditional object tracking methods can be divided into two types: generative-based tracking and discriminative-based tracking. The generative tracking algorithm constructs a model that can ...

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): G06T7/246G06K9/62
CPCG06T7/248G06T2207/10016G06T2207/20081G06T2207/20084G06F18/214G06F18/24
Inventor 郭东岩邵燕燕王俊崔滢王振华陈胜勇
Owner ZHEJIANG UNIV OF TECH
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