Spinal Line Detection for Posture Evaluation Through Training-Free 3D Human Body Reconstruction with 2D Depth Images

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 multi-image-based body restoration methods require expensive equipment and complex procedures, and single image-based body restoration methods struggle to accurately estimate internal structures 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 overcome the limitations of the single-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, restoration to noise and occlusion is performed. In addition, adaptive vertex reduction is applied to maintain the resolution and shape reliability of the mesh, and the accuracy and stability of spinal angle estimation are simultaneously secured using the level of detail (LOD) ensemble. 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 in matching quality.