Key Point Smoothing via Frame Up-sampling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Facial key points extracted from videos often exhibit time-series errors due to frame-based extraction, leading to fluctuating results and degraded accuracy or quality in application services.

Innovation Solution

A method involving key point generation by smoothing key point extraction frames after up-sampling, which reduces time-series errors and enhances stability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If key points are extracted on a frame basis, then extraction simplicity is maintained, but time-series error increases causing fluctuating results

Engineering Contradiction:

Improveextraction simplicityVSAvoidtime-series stability

Core Design Contradiction:

Ease of manufactureVSReliability

Solution Approach 1:

The patent applies preliminary action by performing up-sampling before smoothing. The frames are up-sampled to increase the number of frames, and then smoothing is applied to reduce time-series errors. This preliminary up-sampling enables more effective smoothing without losing temporal information, resolving the contradiction between simple frame-based extraction and time-series stability.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent changes the frame rate parameter through up-sampling before smoothing. By increasing the frame rate (e.g., from 25fps to 125fps), the system creates more data points for smoothing operations, which reduces time-series errors while maintaining the simplicity of frame-based extraction. This parameter change enables both simplicity and stability.

Inventive Principle:

Principle #35Parameter changes

2Loss of time

If key points are extracted without smoothing, then processing time is reduced, but accuracy and quality of application services are degraded

Engineering Contradiction:

Improveprocessing timeVSAvoidkey point accuracy

Core Design Contradiction:

Loss of timeVSMeasurement precision

Solution Approach 1:

The patent changes the frame rate parameter through up-sampling, which enables efficient smoothing without excessive processing time. By controlling the up-sampling ratio (e.g., 5x from 25fps to 125fps), the system achieves improved accuracy while keeping processing time manageable. The parameter change optimizes the balance between speed and precision.

Inventive Principle:

Principle #35Parameter changes

3Reliability

If frame rate is increased through up-sampling, then smoothing effectiveness improves, but computational complexity increases

Engineering Contradiction:

Improvetime-series stabilityVSAvoidprocessing complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies preliminary up-sampling as a preparatory step before smoothing. This preliminary action organizes the data structure by increasing frame rate, which makes subsequent smoothing operations more effective. The preliminary action separates the complexity into a structured process, improving time-series stability while managing computational complexity through systematic processing.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250191140A1Key point smoothing method based on frame up-sampling

Publication Date: 2025.06.12 KOREA ELECTRONICS TECH INST

AI summary

There is provided a frame up-sampling-based key point smoothing method. The key point smoothing method according to an embodiment up-samples frames based on which key points are extracted, and smooths the up-sampled frames. Accordingly, key points are generated by smoothing key point extraction frames after up-sampling, so that a time-series error occurring when key points are extracted can be reduced and time-series stability can be enhanced, and quality of an application service provided subsequently can be improved.