Back Shape Modeling for Accurate Posture Measurement Through Clothing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing posture evaluation systems struggle to accurately measure the shape of a subject's back when clothing obstructs the view, leading to inaccurate posture assessments.

Innovation Solution

A posture measurement apparatus and method that utilizes a shape model and optimization techniques to estimate the back shape by minimizing an objective function using constraint conditions, even when clothing is present.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If the back shape is measured directly from the image, then the measurement is simple, but the measurement accuracy deteriorates when clothing is present

Engineering Contradiction:
Improvemeasurement simplicityVSAvoidback shape measurement accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent introduces a shape model as an intermediary between the image data and the back shape measurement. The shape model represents the back shape as a function of multiple parameters and serves as a mediator that allows accurate measurement even when clothing obscures the actual back shape. The optimization process adjusts the model parameters to find the best fit, effectively using the model as a mediator to overcome the clothing interference problem.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent represents the back shape using a shape model with multiple adjustable parameters. By changing and optimizing these parameters (such as control point positions, curvature values, etc.), the system can accurately represent the back shape even when the visual appearance is distorted by clothing. This parameter-based approach allows the system to maintain measurement accuracy while keeping the operation simple.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If a shape model with multiple parameters is used to represent the back shape, then the measurement accuracy is improved, but the calculation complexity increases

Engineering Contradiction:
Improveback shape measurement accuracyVSAvoidcalculation complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent performs preliminary actions by pre-defining the shape model structure and its parameters before the actual measurement process. The shape model is prepared in advance with a known mathematical form and parameter set, which reduces the computational complexity during the actual optimization phase. This preliminary setup allows the system to handle the multiple parameters efficiently without excessive calculation complexity.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements a feedback mechanism through the optimization process that adjusts the shape model parameters based on the objective function value. The system continuously evaluates how well the current parameters represent the observed data and provides feedback to guide the parameter adjustment. This feedback loop enables the system to converge to an accurate solution while managing the complexity of having multiple parameters by systematically reducing the search space.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS20260026740A1Posture measurement apparatus, posture measurement method, and non-transitory computer readable medium
Publication Date: 2026.01.29 NEC CORP
  • US20260026740A1 patent drawing
  • US20260026740A1 patent drawing
  • US20260026740A1 patent drawing

AI summary

A posture measurement apparatus includes at least one memory configured to store instructions, and at least one processor configured to execute the instructions to hold a shape model representing a shape of a back of a subject as a function of a plurality of parameters, execute calculation processing of calculating a value of a predetermined objective function using a candidate point cloud as a candidate of a point cloud indicating the shape of the back of the subject and the shape model as inputs, and execute an optimization processing of correcting the parameters in such a way as to minimize the value of the predetermined objective function using a constraint condition of the parameters and the shape model as inputs.