Binocular parallax stereo imaging based on correlation matching algorithm

TL;DR

This paper presents a binocular parallax stereo imaging system using correlation matching of pseudo-thermal light intensity fluctuations, achieving high feature point matching precision for objects with less distinctive surface features.

Contribution

It introduces a correlation matching algorithm-based BPSI system that improves feature matching accuracy and demonstrates its effectiveness on real objects with uniform surface characteristics.

Findings

Matching precision reaches one pixel

System performs well on objects with constant surface reflectivity

Experimental results validate the proposed method

Abstract

The intensity fluctuation correlation of pseudo-thermal light can be utilized to realize binocular parallax stereo imaging (BPSI). With the help of correlation matching algorithm, the matching precision of feature points can reach one pixel authentically. The implementations of the proposed BPSI system with real objects were demonstrated in detail. And the experimental results indicated that the proposed system performs better when the object's superficial characteristics are not obvious, for example its surface reflectivity is constant.