Human Presence Detection Using Adaptive Skin Range Correction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for determining human presence in images based on skin color ranges are unreliable due to variations caused by lighting conditions, leading to inaccurate human presence detection.

Innovation Solution

A method involving extraction of a human area, calculation of representative feature values, correction of skin ranges using a conversion function, and determination of human presence based on corrected skin ranges, utilizing a conversion function to enhance precision.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a predetermined skin color range is used for human presence determination, then the determination process is simple, but the accuracy deteriorates under varying lighting conditions

Engineering Contradiction:
Improvesimplicity of determination processVSAvoidaccuracy of human presence detection
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent applies preliminary action by extracting a human area from the image before performing skin color range determination. This preprocessing step isolates the region of interest, allowing subsequent color analysis to focus only on relevant pixels, thereby improving accuracy without significantly increasing overall complexity

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent applies local quality by using different color ranges for different parts of the human area. Specifically, it distinguishes between skin color regions and non-skin color regions (such as clothing) within the detected human area, and applies appropriate color determination criteria to each, thereby improving overall detection accuracy

Inventive Principle:
Principle #3Local quality

2Productivity

If a fixed skin color range is applied to all pixels, then the processing is efficient, but false determination occurs under different lighting conditions

Engineering Contradiction:
Improveprocessing efficiencyVSAvoidreliability of human presence determination
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent applies segmentation by dividing the image into distinct regions: human area and non-human area. Within the human area, it further segments into skin color regions and non-skin color regions. This segmentation allows different processing strategies to be applied to different regions, improving reliability while maintaining reasonable processing efficiency through targeted analysis

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4089639B1Information processing device, information processing method, and program
Publication Date: 2026.03.18 RAKUTEN GROUP INC
  • EP4089639B1 patent drawingFigure 1
  • EP4089639B1 patent drawingFigure 2
  • EP4089639B1 patent drawingFigure 3

AI summary

To facilitate setting of an appropriate question by an administrator in advance, an information processing device extracts, from an image taken by an imaging device, a human area in which it is determined that a human is present, acquires a representative value of first feature values, the first feature values being calculated by inputting, to a conversion function, each color of pixels included in a part of the human area, corrects, based on the representative value, a skin range indicating that a color indicated by a feature value acquired with the conversion function is a color of human skin, and determines whether a human is present in a part of the image acquired by the imaging device, based on whether a second feature value calculated with the conversion function for each of a plurality of pixels forming the part of the image is within the corrected skin range.