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

Target tracking method based on twin network

A technology of target tracking and twin network, which is applied in the field of target tracking based on twin network, can solve the problem of reducing tracking and achieve the effect of high efficiency and simple structure

Active Publication Date: 2020-02-18
NANJING UNIV +1
View PDF11 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In order to solve the above problems, the present invention discloses a twin-network-based and anchor-free single-target tracking method, which can significantly improve the tracking efficiency without greatly reducing the tracking effect. Guaranteed to run quickly even when the hardware environment is not ideal

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
  • Target tracking method based on twin network
  • Target tracking method based on twin network
  • Target tracking method based on twin network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0071] In order to verify the effectiveness of the method of the present invention, video and picture sequences including different lighting and scenes are actually collected for example verification, the images of each frame are processed, and the position of the target in each frame is obtained by tracking. In this embodiment, a picture sequence in the VOT2015 data set is taken as an example, and the tracking is performed according to the following steps:

[0072] 1. Use ImageNetVID and GOT datasets to generate training and validation sets;

[0073] 2. Use the generated training set and verification set to train the feature extraction network N 1 , convolution kernel K 1 、K 2 、K 3 and a fully connected layer C 1 ;

[0074] 3. Read in the first frame of the sequence, and specify the position L of the target to be tracked by means of box selection 1 ,Such as Figure 5a shown;

[0075] 4. Record the position L of the tracking target in the first frame 1 , and put the i...

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 target tracking method based on a twin network, and the method comprises the steps: 1, reading a to-be-tracked image sequence or a first frame of a to-be-tracked video, and specifying the position of a to-be-tracked target in a box selection mode; 2, recording the position of the to-be-tracked target, and inputting the RGB image of the target into the network to obtain a feature map; 3, reading in the next frame of the image sequence or the video, and selecting a part of images around the target position of the previous frame to be input into the network to obtain a feature map; 4, performing convolution operation on the two feature maps to obtain a new feature map; 5, convolution is performed on the new feature map by using a small convolution kernel, so that a more abstract feature map can be obtained; 6, enabling the final feature map to pass through a full connection layer, and outputting the coordinate of the target in the current frame, the offset of thecenter of the image and the aspect ratio; and 7, drawing the position of the target in the current frame according to the output in the step 6.

Description

technical field [0001] The invention relates to a target tracking method based on twin networks. Background technique [0002] Object Tracking technology aims to determine the position of the target in a continuous picture sequence or video through computer vision. Object tracking can connect different frames to make more full use of the information of video or image sequences. Different from object detection, object tracking not only obtains the current position of the object, but also analyzes the movement and trajectory of the object, which also makes object tracking have very important research value. Target tracking can be applied to unmanned driving, analyzing the movement of vehicles or pedestrians, and judging whether there are potential safety hazards by predicting trajectories; and monitoring areas with high traffic density, judging whether there are suspicious persons by analyzing the walking paths of pedestrians, etc. In addition, in single target tracking, the...

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): G06T7/246
CPCG06T7/246G06T2207/10016G06T2207/20081G06T2207/20084
Inventor 申富饶姜少魁李俊赵健
Owner NANJING UNIV
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