A measurement system based on internal cooperation of cameras in binocular vision

Abstract

In this paper, a measurement system based on internal cooperation of cameras in binocular vision is proposed. In terms of the hardware structure, the system is composed of a binocular vision module, a controllable platform and an electronic gradienter, which can be used to collect binocular images and measure horizontal and vertical angles between the binocular vision module and objects. In terms of data processing, a new measurement method based on the cooperation of monocular and binocular vision (MBC) is put forward. Firstly, the depth values of some effective points are obtained according to feature point matching results. Then, a depth propagation algorithm based on MBC is adopted to compute other depth information of the object region. After that, the actual size of unit pixels is computed on the basis of the corresponding disparity value, and it is corrected according to the horizontal and vertical angles. Finally, accurate size measurement of the object is achieved by accumulating the number of pixels. Experimental results show that the proposed system can achieve more accurate measurement results compared to the traditional binocular vision measurement method. For all the experimental objects, the absolute relative measurement errors with our method are all lower than 3.5%.