3results about How to "Reduce angle error" patented technology

The utility model relates to steel plate reinforcing structure technical field especially is a kind of anchoring steel plate reinforcing structure, including multilayer foundation, steel plate assembly, first reinforcing steel, second reinforcing steel and positioning assembly, the right side of multilayer foundation is equipped with steel plate assembly, the steel plate assembly includes and the inside lining steel plate of the right side of multilayer foundation, the left side of the inside lining steel plate is fixedly connected with multiple groups of anchoring steel plate group, in the utility model, by the support frame, positioning frame, first positioning casing and second positioning casing being set, the device can be through support frame and positioning frame and make first positioning casing and second positioning casing present specific inclination angle, by first positioning casing and second positioning casing to the location of first reinforcing steel and second reinforcing steel, it can be quickly positioned that first reinforcing steel and second reinforcing steel, not only more time-saving and labor-saving, but also can reduce the angle error of first reinforcing steel and second reinforcing steel placement.

This invention proposes a polarization 3D reconstruction method and system based on a prior-guided fusion network. The invention is implemented using a dual-branch architecture and includes a feature correction module that mutually corrects defects in the channel and spatial dimensions. Furthermore, a feature fusion module based on an effective cross-attention mechanism is proposed to fuse polarization and shadow prior features, achieving high-precision surface normal vector estimation and thus reconstructing high-quality 3D targets. Experimental results show that the fusion of polarization and shadow priors significantly improves the reconstruction quality of surface normals, especially for objects or scenes illuminated by complex light sources. In addition, by introducing specular confidence, the angular error of specular reflection regions can be reduced. Finally, because the network can effectively extract and fuse information from different priors, our proposed method outperforms existing deep learning-based polarization 3D reconstruction methods.