Learn More
Although a considerable amount of work has been published on material classification, relatively little of it studies situations with considerable variation within each class. Many experiments use the exact same sample, or different patches from the same image, for training and test sets. Thus, such studies are vulnerable to effectively recognising one(More)
Classifying materials from their appearance is a challenging problem, especially if illumination and pose conditions are permitted to change: highlights and shadows caused by 3D structure can radically alter a sample’s visual texture. Despite these difficulties, researchers have demonstrated impressive results on the CUReT database which contains many(More)
0262-8856/$ see front matter 2009 Elsevier B.V. A doi:10.1016/j.imavis.2009.05.005 * Corresponding author. Address: IDIAP Research In Marconi 19, Martigny, Switzerland. Tel.: +41 277 217 E-mail addresses: bcaputo@idiap.ch (B. Caputo), Hayman), fritz@mis.tu-darmstadt.de (M. Fritz), joe@n URLs: http://www.idiap.ch/bcaputo (B. Caputo), h darmstadt.de/mfritz(More)
In this paper we describe the theory and practice of self-calibration of cameras which are fixed in location and may freely rotate while changing their internal parameters by zooming. The basis of our approach is to make use of the so-called infinite homography constraint which relates the unknown calibration matrices to the computed inter-image(More)
1 Background This document provides a brief Users' Guide to the KTH-TIPS2 image database (KTH is the abbreviation of our university, and TIPS stands for Textures under varying Illumination, Pose and Scale). The KTH-TIPS2 provides a considerable extension to our previous database of images of materials — KTH-TIPS. The guide describes which materials are(More)
A powerful and popular approach for estimating radial lens distortion parameters is to use the fact that lines which are straight in the scene should be imaged as straight lines under the pinhole camera model. This paper revisits this problem using the division model to parameterise the lens distortion. This turns out to have significant advantages over the(More)
Main difficulty: affine reconstruction, i.e. locating the plane at infinity ( 1 ) in the projective frame (an inherently non-linear problem). Once we have located 1 the remainder of the problem is equivalent to the self-calibration of a rotating camera with varying intrinsics. Recently a couple of methods to achieve this goal have emerged, including a fast(More)
We present a method for self-calibration of a camera which is free to rotate and change its intrinsic parameters, but which cannot translate. The method is based on the so-called infinite homography constraint which leads to a non-linear minimisation routine to find the unknown camera intrinsics over an extended sequence of images. We give experimental(More)
This paper describes techniques for fusing the output of multiple cues to robustly and accurately segment foreground objects from the background in image sequences. Two different methods for cue integration are presented and tested. The first is a probabilistic approach which at each pixel computes the likelihood of observations over all cues before(More)