Game Video Tagging via Key Frame Indexing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing game video retrieval systems face performance issues due to the inability to adequately express complex or unique game content through single-frame thumbnail images, leading to suboptimal selection performance.
Innovation Solution
An information processing apparatus that includes a storage section for tags and tagging conditions, where the apparatus attaches tags to playback data based on specific conditions met during gameplay, serving as indices for game videos.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single-frame thumbnail image is used to represent game playing video, then the system complexity is reduced and processing is simplified, but the retrieval performance deteriorates when game content is complex or unique
Solution Approach 1:
The patent segments the game playing video into multiple key frames rather than using a single thumbnail. The extracting section identifies and extracts multiple key frames that represent different important moments or scenes in the video, thereby providing more comprehensive representation of complex game content while maintaining manageable system complexity
Solution Approach 2:
The patent transitions from a single two-dimensional thumbnail image to a sequence of multiple key frames, adding the temporal dimension. This allows the system to represent the dynamic nature of game playing videos through multiple snapshots taken at different time points, improving retrieval accuracy without excessive complexity increase
2Measurement precision
If multiple key frames are extracted and synthesized to represent game playing video, then retrieval performance is improved, but the processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary action by extracting and synthesizing key frames in advance during the video processing stage. The key frames are extracted and synthesized before retrieval operations, so that when retrieval is needed, the pre-processed key frame images are already available for quick comparison and matching, reducing real-time processing time
Solution Approach 2:
The patent extracts only the essential key frames that contain important game events or characteristic moments, rather than processing every frame of the video. This selective extraction approach maintains high retrieval performance by focusing on critical moments while significantly reducing the total number of frames that need to be processed and stored
Data Source
AI summary
Retrieval performance when selecting a game playing video can be improved. An information processing apparatus {12(n)} includes: a storage section (66) in which at least one tag and a tagging condition of the tag are stored in association with each other; and an attaching section (74) which, when playback data to be used to play back a game playing video of a game has been generated and an event during the play of the game satisfies the tagging condition, attaches the tag, which is associated with the tagging condition, to the playback data as an index of the game playing video.