Spinal Line Detection for Posture Evaluation through Train-ing-free 3D Human Body Reconstruction with 2D Depth Images

2025-12-14

AI Summary

Existing 3D human reconstruction and spinal centerline estimation methods face dual bottlenecks: multi-view depth imaging requires expensive hardware and complex calibration, while single-view approaches suffer from occlusion and viewpoint ambiguity, hindering accurate recovery of internal spinal geometry. To address this, we propose a training-free, unsupervised framework that reconstructs 3D human meshes from four orthographic 2D depth images. Our method innovatively integrates hierarchical rigid–nonrigid registration, adaptive vertex reduction, and multi-scale level-of-detail fusion, enabling global–local co-optimization to jointly preserve mesh fidelity and spinal centerline geometric stability. Experiments demonstrate that—without neural networks, annotated data, or anatomical priors—our approach significantly improves 3D spinal localization accuracy and angular estimation robustness, exhibiting strong resilience to noise and partial occlusion. This work establishes a new paradigm for low-cost, high-precision posture assessment.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Learning with Manifolds
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The spinal angle is an important indicator of body balance. It is important to restore the 3D shape of the human body and estimate the spine center line. Existing mul-ti-image-based body restoration methods require expensive equipment and complex pro-cedures, and single image-based body restoration methods have limitations in that it is difficult to accurately estimate the internal structure such as the spine center line due to occlusion and viewpoint limitation. This study proposes a method to compensate for the shortcomings of the multi-image-based method and to solve the limitations of the sin-gle-image method. We propose a 3D body posture analysis system that integrates depth images from four directions to restore a 3D human model and automatically estimate the spine center line. Through hierarchical matching of global and fine registration, restora-tion to noise and occlusion is performed. Also, the Adaptive Vertex Reduction is applied to maintain the resolution and shape reliability of the mesh, and the accuracy and stabil-ity of spinal angle estimation are simultaneously secured by using the Level of Detail en-semble. The proposed method achieves high-precision 3D spine registration estimation without relying on training data or complex neural network models, and the verification confirms the improvement of matching quality.

Problem

• Detects spinal line for posture evaluation using depth images.
• Reconstructs 3D human body without training or complex neural networks.
• Overcomes occlusion and viewpoint limits in single-image methods.

Innovation

• Training-free 3D reconstruction from 2D depth images
• Hierarchical global and fine registration for noise and occlusion
• Adaptive Vertex Reduction with Level of Detail ensemble