Digital Human Model Visual Measurement for Testing Efficiency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current digital human modeling methods suffer from low efficiency in the testing process due to inefficient feature extraction and alignment of pedestrian bounding boxes and face recognition, particularly in pedestrian tracking and face detection models.
Innovation Solution
A visual measurement method and system based on a digital human model, involving constructing a digital human model from 3D data, performing pose estimation using deep learning, preprocessing data, aligning and matching key feature points through computer vision, and optimizing these points to obtain morphological parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional pedestrian tracking and face recognition models are used for feature extraction and alignment, then measurement functionality is achieved, but testing efficiency is low
Solution Approach 1:
The patent creates a digital human model as a virtual copy of the actual human subject. This digital twin can be tested repeatedly without involving the real person, dramatically improving testing efficiency while reducing the time loss associated with repeated real-world testing sessions.
Solution Approach 2:
The patent performs preliminary actions by pre-extracting and aligning feature points on the digital human model before actual measurement testing. This preparation work is done in advance on the virtual model, so when real measurements are needed, the system already has optimized parameter sets ready, reducing overall testing time.
2Measurement precision
If comprehensive feature extraction and alignment procedures are performed, then measurement precision is improved, but processing complexity increases
Solution Approach 1:
The patent segments the measurement system into distinct modules: digital human model construction, feature point extraction, feature point alignment, and parameter calculation. Each module handles a specific aspect of the process, making the overall complex system more manageable and maintainable while achieving high measurement precision through coordinated operation of all segments.
Solution Approach 2:
The digital human model serves as an intermediary between the raw input data and the final measurement results. It provides a standardized virtual representation that simplifies the transformation process, acting as a mediator that bridges the complexity of feature extraction and alignment while maintaining measurement accuracy.
Data Source
AI summary
The present application provides a visual measurement method and system based on a digital human model. The visual measurement method includes the following steps: data acquisition, data matching, and data optimization. According to the present application, a digital human model is constructed from obtained 3D data, pose estimation is performed on the digital human model using a deep learning algorithm to obtain first data, and the first data is preprocessed to obtain second data. Then, the second data is matched and aligned with the digital human model, and a correspondence between the second data and the digital human model is established through key feature point matching and shape registration, to obtain third data. Finally, key feature points are extracted from the third data and optimized through a computer vision algorithm and image processing, and morphological parameters are obtained according to the optimized key feature points.