Robust reconstruction of high-resolution 3D shapes based on a single light pattern
基于单幅光模板的高分辨率可靠3维形貌重建

It is an increasingly important topic to reconstruct 3D shape from images by structured light vision. However, their practical applications are mainly limited to low resolution, texture and sensitivity of environment illumination. This paper proposes a new color coded structured light technique for robustly reconstructing shapes from a single image. This technique works by projecting a pattern based on De Bruijn stripes with white gaps. The correspondence problem is solved using a color classification algorithm. The statistical cluster parameters of the captured image are adopted so that it is adaptive to different scenes and contexts. In this paper, the stripe boundary is located accurately by local a searching method. Additionally, a scheme is presented to achieve dense shape reconstruction by shifting the same pattern. Practical experimental results are provided to demonstrate the performance of the proposed method.