Skating tracking method based on deep learning and uwb auxiliary positioning

A deep learning, assisted positioning technology, applied in neural learning methods, location information-based services, and specific environment-based services, etc., can solve problems such as short delays and errors, and achieve the effect of achieving accuracy and reducing IDSwitch problems.

Pending Publication Date: 2022-05-13
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the short delay between signal sending and receiving, and the top speed of skaters can reach 45-55km / h, errors occur

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
  • Skating tracking method based on deep learning and uwb auxiliary positioning
  • Skating tracking method based on deep learning and uwb auxiliary positioning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Below in conjunction with the accompanying drawings in the present invention, the technical solutions in the present invention are clearly and completely explained:

[0030] combine figure 1 As shown, a skating tracking method based on deep learning and uwb-assisted positioning includes the following steps:

[0031] s1. Obtain the data of the skating field, and manually calibrate the key point data of the field;

[0032] The 60m×30m rectangular field is divided into 8 square fields of 15m×15m, and five points are marked on each of the two long sides of the field. Fifteen meters on both sides of the point; five points are calibrated on the long axis of the site, at the two vertices of the long axis, the midpoint of the long axis, and fifteen meters on both sides of the long axis; finally, the center points of the eight squares are calibrated; A total of 23 points of position information are calibrated.

[0033] s2. Arrange uwb devices and signal receivers according to...

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 combines a deep learning algorithm and a uwb positioning technology, and particularly discloses a skating tracking method based on deep learning and uwb auxiliary positioning, and the method comprises the following steps: s1, obtaining skating site data, and carrying out the manual calibration of the site key point data; s2, according to the field data, arranging a uwb (UltraWide Band) device, and arranging a signal receiver; s3, designing a target detection network, learning characteristics of the athletes, detecting positions of the athletes, and predicting subsequent positions; s4, designing a multi-target tracking network, and realizing preliminary tracking through a matching algorithm; s5, acquiring tracking information acquired by the uwb equipment, and performing interpolation completion operation on the tracking information; and s6, performing auxiliary matching on the preliminary tracking result through the complemented uwb tracking information to obtain a final tracking result. According to the method provided by the invention, the IDSwitch problem caused by shielding or similar characteristics in the process of carrying out multi-target tracking on skating athletes is improved by using a deep learning algorithm and an auxiliary technology of uwb complementation information.

Description

technical field [0001] The invention combines deep learning algorithm and uwb positioning technology, and specifically discloses a skating tracking method based on deep learning and uwb assisted positioning. technical background [0002] With the continuous change of computer hardware, the computing power of the computer has been significantly improved compared to the past, so the computer has acquired the ability to efficiently process video. With the wide application of deep learning related technologies in the field of computer vision, multi-target tracking algorithms based on deep learning have been developed and put into use. However, the mutual occlusion between targets and the sharp deformation of targets in a short time are still the key problems that need to be solved urgently in the field of multi-target tracking. There is also such a problem in the multi-target tracking task in the skating scene. The athletes often exchange orders during the game, so as to block ...

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): H04W4/029H04W4/33H04W16/20H04W64/00G06V40/20G06N3/04G06N3/08
CPCH04W4/029H04W4/33H04W16/20H04W64/00G06N3/08G06N3/045
Inventor 崔振东李宗民李亚传王一璠王奔白云
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap