Supercharge Your Innovation With Domain-Expert AI Agents!

Algorithm for automatically recognizing scoring of football match based on panoramic video

A panoramic video, automatic recognition technology, applied in the field of football game video recognition, can solve problems such as difficulties and failures

Inactive Publication Date: 2017-07-28
上海慧体网络科技有限公司
View PDF5 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when using ordinary cameras for unsupervised recording of football games, there are no close-up shots in the video, so the above methods often fail
Also, the soccer ball is smaller in panorama mode, which makes the problem even more difficult

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
  • Algorithm for automatically recognizing scoring of football match based on panoramic video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention will be further described below with reference to the drawings and embodiments.

[0025] The algorithm for automatically identifying goals in a football match based on panoramic video provided by the present invention includes:

[0026] 1. Generate the annotation information of the scene.

[0027] Use manual labeling or automatic algorithm learning methods to obtain some prior information of the scene (such as extracting the goal from the video).

[0028] According to the size and position of the goal, generate the area of ​​interest for each side of the game to shoot and score (the y direction can be extended to the bottom and top of the goal by a certain percentage, and the x direction can be extended to the left and right boundaries of the goal by a certain percentage).

[0029] 2. Detection of candidate footballs.

[0030] (1) Extract the area of ​​interest for shooting and scoring from the panoramic video, establish a background model, and segment the fo...

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 discloses an algorithm for automatically recognizing scoring of a football match based on a panoramic video. The method comprises five steps, namely generating mark information of a scene, selecting a candidate football, generating a football track, detecting and tracking a goalkeeper, and automatically determining scoring. The algorithm for automatically recognizing scoring of the football match based on the panoramic video realizes automatic recognition for scoring of the football match through analyzing a football match video, wherein the analyzing comprises five steps of generating mark information of the scene, selecting the candidate football, generating the football track, detecting and tracking the goalkeeper, and automatically determining scoring. The algorithm overcomes a defect caused by goal detection and close-up view for detecting scoring in the match video in prior art.

Description

Technical field [0001] The invention relates to an algorithm for recognizing a football match video, in particular to an algorithm for automatically recognizing goals in a football match based on panoramic video. Background technique [0002] At present, it is common to analyze the videos of large-scale football matches. In these videos, 5 shots are usually used to show a goal event. These 5 shots are a panoramic shot of the goal, a close-up shot of the shooting player, a spectator shot, and several players. The middle shot and playback shot. Therefore, currently, goal detection and close-up shot detection are used to determine goals in the event video. However, when an ordinary camera is used for unsupervised recording of a ball game, there is no close-up shot in the video, so the above methods often fail. In addition, the area of ​​the football is smaller in panoramic mode, which makes the problem more difficult. Aiming at these deficiencies in the prior art, the present inv...

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): G06K9/00
CPCG06V20/42
Inventor 刘剡贺岳平朱明亮
Owner 上海慧体网络科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com