Accurate 3D human pose reconstruction from a single RGB image remains challenging due to scale ambiguity and perspective distortions. Current single-view methods primarily rely on learned priors or kinematic constraints, but they often struggle to maintain geometric consistency with the physical scene. This results in horizon alignment drift and instability when rendered in metric environments. To overcome these limitations, this study introduces a vanishing-point-driven framework that integrates scene geometry into the pose correction process. Under the Manhattan-world assumption, dominant vanishing points are detected to estimate the ground plane and recover the camera orientation with high precision. A lightweight 3D pose estimation network generates initial joint coordinates in camera-centric space. These coordinates are then refined through a VP-based ground-alignment transformation, which resolves scale ambiguity and minimizes geometric drift. The corrected poses are normalized to physical scale and streamed to NVIDIA OmniverseTM for real-time digital-twin visualization. Experiments conducted on indoor scenes from the NYU Depth V2 dataset demonstrate sub-pixel accuracy in vanishing-point localization and significant improvements in geometric alignment between the reconstructed poses and the true scene layout. This confirms the effectiveness of the proposed approach for single-view digital-twin human modeling.
Belt-pulley looseness is a crucial factor in ensuring the safe operation of machinery used in industrial applications, such as compressors and fans. Traditionally, belt looseness has been inspected using contact-based current and vibration sensors. However, these methods are time-consuming and require manual attachment of the sensors. In order to overcome the limitations of these traditional methods, we propose a remote diagnosis method for detecting belt looseness using a smartphone. By utilizing a four-mirror system, the smartphone can construct a stereo system that enables 3D reconstruction of the object. This allows us to reconstruct the 3D trajectory of the belt and diagnose the level of looseness. To further enhance the accuracy of our proposed system, we have developed a calibration algorithm specifically designed for the four-mirror system. In our actual experiment, we successfully diagnosed four levels of belt looseness. As the level of looseness increased, we observed a curved shape in the 3D trajectory of the belt, along with noticeable quantitative differences. To quantitatively analyze these differences, we introduced a measure called the residual, which reflects the curvilinearity of the 3D trajectory. Our findings confirmed a significant correlation between the residual and the level of belt looseness.
First
Prev
