Global Calibration of Two Cameras with Optical Filter with non-Overlapping Views Using 1D Square Serrated Target

Many multi-vision measurement systems like outdoor industrial engineering utilize optical filter to filter unexpected light which makes it impossible to use traditional planar pattern for calibration. In this paper, we propose a stereo vision global calibration method for non-overlapping views that comprises two cameras, an optical line laser whose wave band within the optical filter's and 1D square serrated target. Vertex-points coordinates in the camera coordinate frame (CCF) are obtained based on the cross ratio invariance theory and vanishing points. Initial rotation vector and translation vector are confirmed by flexibly moving the target to at least three different positions. After a nonlinear refinement, external parameters are precisely determined. Experimental results show that the measurement accuracy reaches to 0.06 mm within the cameras' FOV of 450mm*370mm.

I. Introduction

Multi-vision sensor (MVS) measurement systems have been widely used in the outdoor industry area. At present, the calibration of multi-visual sensor measurement systems is facing two major challenges. Firstly, the interference of complex environmental condition such as rain, snow, dust which make the target objects’ background difficult to identify; Secondly, there is no common field of view(FOV) especially in the area of large-space vision measurement. General solution of the first problem in the industrial field is to select a optical filter whose wavelength is consistent with the laser’s to filter out other light; Moreover, in narrow measurement space like underside of the railway track, it is restricted to conduct calibration of non-overlapping view, which means many calibration methods are invalid. Therefore, non-overlapping FOV global calibration for complex environments is still very significant.