Automated Action Shot Generation via Motion-Based Frame Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional techniques for generating action shots are tedious and time-consuming, requiring manual selection and editing of frames, and fail to automatically capture the best frames, especially when objects exhibit both fast and slow motions.

Innovation Solution

A computing device automatically selects frames based on the motion of an object within video data, using modules for object tracking, motion analysis, and frame selection to generate an action shot by overlaying the object onto a background, eliminating the need for manual intervention and photographic editing skills.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional manual frame selection techniques are used, then the user can select ideal frames for the action shot, but the process becomes tedious, laborious, and time-consuming

Engineering Contradiction:

Improveframe selection qualityVSAvoidtime to generate action shot

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs automatic frame selection, object extraction, and action shot generation without requiring manual user intervention. The computing device autonomously analyzes video frames, identifies objects of interest, and creates the final action shot, eliminating the need for users to manually search and filter through numerous frames.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical process of frame selection with an automated computational system. Instead of users manually examining and selecting frames, the system uses algorithms to automatically analyze video data, detect objects, and select appropriate frames based on motion and other criteria.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If conventional techniques reduce the total number of frames to speed up manual search, then the processing time decreases, but the selected frames may fail to capture the best action moments

Engineering Contradiction:

Improveframe processing speedVSAvoidaction moment capture accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system analyzes motion characteristics of objects across video frames and uses this feedback to intelligently select frames that capture meaningful action moments. By monitoring object motion and identifying significant changes in position or state, the system ensures that selected frames represent key moments in the action sequence rather than arbitrary intervals.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent dynamically adjusts frame selection criteria based on object motion parameters. Instead of using a fixed interval between selected frames, the system varies the selection density according to the speed and significance of object movement, selecting more frames during fast motion and fewer during slow motion to optimize both capture accuracy and processing efficiency.

Inventive Principle:

Principle #35Parameter changes

3Ease of operation

If conventional techniques select frames at fixed intervals, then the selection process is simple and fast, but redundant overlapping instances are captured during slow motion

Engineering Contradiction:

Improveframe selection simplicityVSAvoidnumber of redundant frames

Core Design Contradiction:

Ease of operationVSQuantity of substance

Solution Approach 1:

The system dynamically adjusts the frame selection strategy based on the detected motion characteristics of objects in the video. During periods of slow motion, the system reduces the frequency of frame selection to avoid capturing redundant overlapping instances, while during fast motion it increases selection frequency to capture all significant moments.

Inventive Principle:

Principle #15Dynamics

4Measurement precision

If manual frame selection and editing is performed, then the user can create professional-quality action shots, but the process requires photographic editing skills and is labor-intensive

Engineering Contradiction:

Improveaction shot qualityVSAvoiduser skill requirement

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The system autonomously performs all tasks previously requiring manual user expertise, including frame selection, object extraction, and composition. The computing device automatically creates professional-quality action shots without requiring users to possess photographic editing skills or manually manipulate individual frames.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual photographic editing process with an automated computational system that performs object recognition, frame selection, and image composition. This substitution eliminates the need for users to have specialized editing skills while maintaining professional output quality.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS10467788B2Automated action shot generation in a digital medium environment

Publication Date: 2019.11.05 ADOBE INC

AI summary

Automatic frame selection and action shot generation techniques in a digital medium environment are described. A computing device identifies an object in a foreground of video data. A determination is then made by the computing device as to motion of the object exhibited between frames of the video data. A subset of frames is then selected by the computing device based on a determined motion of the identified object depicting an action sequence. An action shot is generated by the computing device by overlaying the identified objects in the selected frames on a background.