Composite Video Thumbnail Generation via Subject Extraction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing image processing technologies fail to effectively represent the overall contents of a video image using a single thumbnail, as each thumbnail image corresponds to a single frame, making it difficult for users to determine the video's contents.

Innovation Solution

An image processing apparatus and program that select multiple frames from a video, recognize and extract specific subject images, and create a still image containing these subject images, optionally using a panoramic background, with priority rankings and decision-making to determine inclusion and positioning of subject images.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If a single frame is used to create a thumbnail image, then the thumbnail can be generated quickly and simply, but it is difficult to determine the overall contents of the video image

Engineering Contradiction:

Improvethumbnail generation timeVSAvoidvideo contents representation

Core Design Contradiction:

Loss of timeVSLoss of information

Solution Approach 1:

The video image is divided into multiple frames, and multiple thumbnail images are generated from different frames. Each thumbnail represents a segment of the video content, allowing users to grasp overall contents by viewing multiple thumbnails rather than relying on a single frame

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Multiple thumbnail images are combined into a single composite thumbnail image that displays multiple frames simultaneously. This merging approach preserves the brevity of a single thumbnail while incorporating information from multiple frames to represent overall video contents

Inventive Principle:

Principle #5Merging (Combining)

2Loss of information

If multiple frames are selected and processed to create a composite thumbnail, then the video contents can be represented more accurately, but the processing complexity increases

Engineering Contradiction:

Improvevideo contents representationVSAvoidimage processing complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

Frames are pre-selected from the video image based on predetermined criteria (such as key frames or evenly distributed frames) before composite thumbnail generation. This preliminary selection reduces the number of frames that need to be processed, simplifying the overall processing complexity while maintaining accurate video contents representation

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Instead of processing and combining all video frames, representative copies (thumbnails) are created from selected frames. These thumbnail copies capture the essential visual information from each frame, allowing accurate video representation without the computational burden of processing every frame

Inventive Principle:

Principle #26Copying

3Loss of information

If multiple subject images are extracted and included in the still image, then the video contents are represented more comprehensively, but the clarity and focus of individual subjects may be reduced

Engineering Contradiction:

Improvevideo contents completenessVSAvoidsubject image clarity

Core Design Contradiction:

Loss of informationVSMeasurement precision

Solution Approach 1:

Different regions or areas within the composite thumbnail image are allocated to different subject images, with each subject given appropriate visual weight and clarity in its designated area. This local quality approach ensures that while multiple subjects are represented comprehensively, each subject maintains sufficient clarity and focus in its own space within the composite image

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS8897603B2Image processing apparatus that selects a plurality of video frames and creates an image based on a plurality of images extracted and selected from the frames

Publication Date: 2014.11.25 NIKON CORP

AI summary

An image processing apparatus includes a selection device that selects a plurality of frames from a video image constituted with a group of frames, an extraction device that recognizes a specific subject image in the plurality of frames having been selected and extracts the recognized subject image, and an image creation device that creates a still image containing a plurality of subject images having been extracted by the extraction device.