Binocular stereovision has become one of the development trends of machine vision and has been widely used in robot recognition and positioning. However, the current research on omnidirectional motion handling robots at home and abroad is too limited, and many problems cannot be solved well, such as single operating systems, complex algorithms, and low recognition rates. To make a high-efficiency handling robot with high recognition rate, this article studies the problem of robot image feature extraction and matching and proposes an improved speeded up robust features (SURF) algorithm that combines the advantages of both SURF and Binary Robust Independent Elementary Features. The algorithm greatly simplifies the complexity of the algorithm. Experiments show that the improved algorithm greatly improves the speed of matching and ensures the real-time and robustness of the algorithm. In this article, the problem of positioning the target workpiece of the robot is studied. The three-dimensional (3-D) reconstruction of the target workpiece position is performed to obtain the 3-D coordinates of the target workpiece position, thereby completing the positioning work. This article designs a software framework for real-time 3-D object reconstruction. A Bayesian-based matching algorithm combined with Delaunay triangulation is used to obtain the relationship between supported and nonsupported points, and 3-D reconstruction of target objects from sparse to dense matches is achieved.

High-fidelity 3D profilometry of non-Lambertian surfaces is severely degraded by the co-occurrence of specular saturation (clipping harmonics) and global illumination (GI). Although Micro Phase Shifting (MPS) isolates low-frequency GI via narrowband projection, non-sinusoidal saturation clipping invalidates its fundamental inter-frequency amplitude consistency constraint, causing phase unwrapping collapse. To resolve this coupled dilemma without exceeding the theoretical minimum image count ($F+2$ frames), this paper proposes a physics-guided adaptive spectral decoupling framework. We demonstrate that the inherent narrowband spatial carrier of MPS establishes an analytical passband, enabling selective harmonic elimination while strictly preserving GI resilience. An adaptive Butterworth low-pass filter integrated with boundary-symmetric mirror extension is formulated, where the optimal cutoff radius is dynamically locked via a spatial correlation convergence criterion. This restores fundamental sinusoidal fidelity, reinstates MPS matrix amplitude consistency, and eliminates Gibbs boundary ringing. Simulations and physical experiments on specular metallic specimens show that our method achieves up to an 87.5% reduction in Root Mean Square Error (RMSE) and a 60.9% reduction in Mean Absolute Error (MAE) over standard MPS, while outperforming multi-exposure fusion benchmarks using 74.1% fewer images. Crucially, high metrological precision is achieved without compromising sharp geometric step edges.