Fast Projective Image Rectification for Planar Objects with Manhattan Structure

摘要

This paper presents a method for metric rectification of planar objects that preserves angles and length ratios. Aninner structure of an object is assumed to follow the laws of Manhattan World i.e. the majority of line segments arealigned with two orthogonal directions of the object. For that purpose we introduce the method that estimates theposition of two vanishing points corresponding to the main object directions. It is based on an original optimizationfunction of segments that estimates a vanishing point position. For calculation of the rectification homography with twovanishing points we propose a new method based on estimation of the camera rotation so that the camera axis isperpendicular to the object plane.The proposed method can be applied for rectification of various objects such as documents or building facades. Alsosince the camera rotation is estimated the method can be employed for estimation of object orientation (for example,during a surgery with radiograph of osteosynthesis implants). The method was evaluated on the MIDV-500 datasetcontaining projectively distorted images of documents with complex background. According to the experimental resultsan accuracy of the proposed method is better or equal to the-state-of-the-art if the background occupies no more than halfof the image. Runtime of the method is around 3ms on core i7 3610qm CPU.