Scale Estimation of Monocular SfM for a Multi-modal Stereo Camera

Abstract

This paper proposes a novel method of estimating the absolute scale of monocular SfM for a multi-modal stereo camera. In the fields of computer vision and robotics, scale estimation for monocular SfM has been widely investigated in order to simplify systems. This paper addresses the scale estimation problem for a stereo camera system in which two cameras capture different spectral images (e.g., RGB and FIR), whose feature points are difficult to directly match using descriptors. Furthermore, the number of matching points between FIR images can be comparatively small, owing to the low resolution and lack of thermal scene texture. To cope with these difficulties, the proposed method estimates the scale parameter using batch optimization, based on the epipolar constraint of a small number of feature correspondences between the invisible light images. The accuracy and numerical stability of the proposed method are verified by synthetic and real image experiments.

Video-Based Camera Localization Using Anchor View Detection and Recursive 3D Reconstruction

“…Whereas most SLAM methods assume a sequential images input and obtain a camera trajectory in timeorder, SfM in a recursive manner [17][18][19][20] has also been developed to provide a temporal 3D reconstruction in a real-time processing. Since they originally obtain a scale-indeterminate 3D model, several works also estimate cameras in a real-scale by using auxiliary sensors [7,8,[21][22][23] or adjusting the model with a known property of the scene [6,9,10]. When a pre-constructed 3D model of the targeted scene is also available, camera poses can be further accurately estimated by registering images directly to the model [9][10][11][12][13].…”