Gameplay Video Event Detection Using Perceptual Hash Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
It is difficult for users to simultaneously play video games and selectively record exciting or surprising content while also summarizing game progress, as identifying key events within the generated gameplay footage is challenging due to the vast amount of user-directed content.
Innovation Solution
An apparatus and method for video tracking that uses perceptual hashing to detect scene cuts and identify notable events in gameplay by generating and comparing image hashes, utilizing a database of hashes for notable events, and employing key points to confirm matches, optimizing computational efficiency through database organization and resource management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If users manually monitor and record gameplay footage, then they can capture exciting content, but they cannot simultaneously play the game and selectively record content
Solution Approach 1:
The patent replaces manual mechanical monitoring with automated perceptual hashing algorithms. Image hashes are generated and compared automatically to detect scene cuts and notable events, eliminating the need for manual gameplay monitoring while reducing system complexity through algorithmic automation.
Solution Approach 2:
The system performs self-service by automatically generating perceptual hashes of gameplay images, comparing them against databases of notable events, and identifying matches without external intervention. This enables autonomous event detection and recording trigger generation.
2Productivity
If users review all generated gameplay footage to identify key events, then they can find notable content, but they cannot efficiently summarize progress within many hours of game content
Solution Approach 1:
The patent extracts key identifying features from gameplay images by generating perceptual hashes that capture essential visual characteristics. These hashes are then compared against databases of notable events, extracting only the most relevant moments from hours of gameplay without requiring full footage review.
Solution Approach 2:
The system transforms images into a different parameter space using perceptual hashing, converting visual data into compact hash values that can be efficiently compared. This parameter transformation enables rapid matching against event databases, dramatically improving identification efficiency.
3Measurement precision
If the system compares every image against all database items, then it can identify all notable events, but it generates excessive computational overhead
Solution Approach 1:
The patent segments the comparison process into two stages: first comparing image hashes against event database hashes to identify candidate matches, then using key point detection to confirm matches. This segmentation reduces computational overhead by avoiding exhaustive comparisons while maintaining detection accuracy.
Solution Approach 2:
The system performs partial comparison by first matching perceptual hashes and then applying key point verification only to candidate matches rather than all database items. This partial action approach maintains high detection accuracy while significantly reducing computational resource consumption.
Data Source
AI summary
A method of identifying a predetermined event within a sequence of images comprises the steps of obtaining a database of data items each representing one of a plurality of predetermined events, identifying candidate event images within the sequence of images, comparing data representing at least a first a candidate event image with one or more data items in the database, and identifying that a predetermined event has occurred within the sequence of images if a candidate event image matches a data item in the database to a predetermined matching threshold degree.