A cost-benefit analysis of a third camera for stereo correspondence
International Journal of Computer Vision
Surface Reflection: Physical and Geometrical Perspectives
IEEE Transactions on Pattern Analysis and Machine Intelligence
Stereo vision for planetary rovers: stochastic modeling to near real-time implementation
International Journal of Computer Vision
3-D stereo using photometric ratios
ECCV '94 Proceedings of the third European conference on Computer Vision (Vol. II)
ECCV '94 Proceedings of the third European conference on Computer Vision (Vol. II)
ACM Computing Surveys (CSUR)
IEEE Transactions on Pattern Analysis and Machine Intelligence
Ordinal Measures for Visual Correspondence
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
On the Motion and Appearance of Specularities in Image Sequences
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Shape and View Independent Reflectance Map from Multiple Views
International Journal of Computer Vision
Color Subspaces as Photometric Invariants
International Journal of Computer Vision
Stereo Image Analysis of Non-Lambertian Surfaces
International Journal of Computer Vision
Joint Estimation of Shape and Reflectance using Multiple Images with Known Illumination Conditions
International Journal of Computer Vision
Simulation of automated visual inspection systems for specular surfaces quality control
PSIVT'07 Proceedings of the 2nd Pacific Rim conference on Advances in image and video technology
Correspondence search in the presence of specular highlights using specular-free two-band images
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part II
Image-based rendering for scenes with reflections
ACM Transactions on Graphics (TOG) - SIGGRAPH 2012 Conference Proceedings
Image-based rendering in the gradient domain
ACM Transactions on Graphics (TOG)
Infrared system for 3D scanning of metallic surfaces
Machine Vision and Applications
| Hi-index | 0.00 |
The problem of accurate depth estimation using stereoin the presence of specular reflection is addressed. Specularreflection, a fundamental and ubiquitous reflection mechanism, is viewpoint dependent and can cause large intensitydifferences at corresponding points,resulting in significant depth errors.We analyze the physics of specular reflectionand the geometry of stereopsis which lead to arelationship between stereo vergence, surface roughness, and thelikelihood of a correct match. Given a lower bound onsurface roughness, an optimal binocular stereo configurationcan be determined which maximizes precision in depthestimation despite specular reflection. However, surface roughness is difficult to estimate in unstructured environments. Therefore, trinocular configurations, independent of surface roughness are determined such that at each scene point visible to all sensors, at least one stereo pair can produce correct depth. We have developed a simple algorithm to reconstruct depth from the multiple stereo pairs.