A 3D reconstruction method combining polarization and binocular vision

Abstract

The invention proposes a three-dimensional reconstruction method combining polarization and binocular vision. In view of the complementarity of the characteristics of the polarization three-dimensional reconstruction results and the binocular vision reconstruction results, the azimuth error of the polarization reconstruction results is corrected based on the registered binocular depth data, and the unevenness of the polarization reconstruction is solved. Under the premise of assuming a linear relationship, spatial fitting is performed on the polarization initial reconstruction result and the registered binocular depth map, and the missing part of the binocular depth map is completed with the surface data of polarization reconstruction. The idea of ​​cross-iteration, cyclic correction process and completion process is adopted to solve the impact of the lack of data in the binocular depth map on the reconstruction results. The reconstruction result has high surface resolution, accurate shape information, high degree of surface detail texture restoration, and the final reconstruction result has a more realistic depth.

Description

technical field [0001] The invention belongs to the field of three-dimensional reconstruction of object surfaces, relates to a three-dimensional reconstruction method combining polarization and binocular vision, and is applicable to various resource-limited three-dimensional reconstruction application scenarios. Background technique [0002] Compared with two-dimensional images, three-dimensional data on the surface of objects can provide more comprehensive feature information. Three-dimensional reconstruction technology has been applied in many fields such as surveying and mapping navigation, identification, unmanned systems and cultural relics protection. [0003] As a new type of three-dimensional imaging technology, polarization three-dimensional imaging technology uses the polarization state information of the reflected light on the surface of the object to estimate the three-dimensional depth data of the target object, which can reflect the physical and chemical charact...

AI Technical Summary

Problems solved by technology

The binocular depth map solves the problems of ambiguity in direction angle and unreal depth in polarization 3D imaging results, and obtains 3D reconstruction results with accurate shape and high detail texture reconstruction

And a solution is proposed for the influence of the lack of regional data in binocular vision depth images on the correction process of polarization reconstruction results

Images