Depth from stereo polarization in specular scenes for urban robotics
Authors:
- 1 May 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1966-1973
Abstract
3-D perception of scenes with specular surfaces is still challenging for robotics applications in urban areas, for both active and passive range sensors; there is a need for improved solutions that work without artificial illumination over a wide range of distances. The advent of cameras with microgrid polarization filter arrays, which allow acquiring four orientations of linearly polarized images simultaneously, has potential to make the use of polarization information in 3-D perception more practical. It is well-known that polarization can provide information about the orientation of specular surfaces; however, prior work with polarization for 3-D perception has had several limitations. We present the first unified formulation of depth perception with stereo and polarization by extending previous energy minimization formulations to include surface orientation constraints computed from the polarization channels. We apply an existing quadratic pseudo-boolean optimization (QPBO) method to approximate the optimal depth map. We use synthetic and real indoor/outdoor images to demonstrate that the new method achieves better results than prior methods, with fewer assumptions and limitations.Keywords
This publication has 14 references indexed in Scilit:
- Hierarchical Stereo with Thin Structures and Transparency2008
- Specular Flow and the Recovery of Surface Structure2006
- Recovery of surface orientation from diffuse polarizationIEEE Transactions on Image Processing, 2006
- Stereo matching with linear superposition of layersIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Beyond Lambert: Reconstructing Specular Surfaces Using Color2005
- Voxel carving for specular surfaces2003
- Beyond Lambert: reconstructing surfaces with arbitrary BRDFs2002
- Stereo and Specular ReflectionInternational Journal of Computer Vision, 1998
- 3D measurements from imaging laser radars: how good are they?Image and Vision Computing, 1992
- Constraining object features using a polarization reflectance modelIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991