Automated Attack Scene Extraction from Sports Footage

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing sports game footage distribution systems lack efficient methods for extracting and identifying highlight scenes, particularly those involving team attacks, which are crucial for live and on-demand video services.

Innovation Solution

A footage distribution system that includes an extraction device capable of detecting camera movement and team direction, extracting frames corresponding to team attacks, and generating metadata to identify attack scenes, enabling the automatic extraction and metadata appending of attack scenes in soccer matches.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual identification of highlight scenes is performed, then accuracy of scene identification is improved, but labor cost and time consumption increase

Engineering Contradiction:

Improvescene identification accuracyVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system enables automatic extraction of attack scenes by having the computer execute the extraction program that autonomously analyzes captured images, identifies portions where images change toward a goal direction, and extracts attack scenes based on this analysis, eliminating the need for manual identification while maintaining high accuracy

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The manual mechanical process of scene identification is replaced by an automated computational system that uses image analysis algorithms to detect camera movement patterns and identify attack scenes, substituting human labor with machine-based automated processing

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If automatic extraction of attack scenes is implemented, then productivity is improved, but device complexity increases

Engineering Contradiction:

Improveextraction efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The extraction process is divided into distinct functional modules: a captured image acquisition unit that obtains sports game footage, a movement detection unit that identifies portions where images change toward the goal direction, and an extraction unit that extracts attack scenes based on the detected portions, allowing each module to perform its specific function independently and efficiently

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The extraction program is designed to be universally applicable to various sports games with match styles involving attacks toward goals, enabling the same system to handle different types of sports footage without requiring specialized equipment for each sport

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS9892320B2Method of extracting attack scene from sports footage

Publication Date: 2018.02.13 FUJITSU LTD

AI summary

An extraction device includes a processor that executes a procedure. The procedure includes: from captured images obtained by capturing a sports game having a match style of attack toward a goal provided in territory of an opposing team, identifying a portion of captured images in which the captured images change over time toward a direction of one or other goal; and extracting a scene in which one or other team is attacking based on the portion of captured images.