Reference Tomm a s Svoboda and Peter Sturm. A badly calibrated camera in ego-motion estimation, propagation of uncertainty. Abstract. This paper deals with the ego-motion estimation (motion of the camera) from two views. To estimate an ego-motion we have to nd correspondences and we need a calibrated camera. In this paper we solve the problem how to propagate known camera calibration errors int...

I propose a novel co-training method for statistical machine translation. As co-training requires multiple learners trained on views of the data which are disjoint and sufficient for the labeling task, I use multiple source documents as views on translation. Co-training for statistical machine translation is therefore a type of multi-source translation. Unlike previous mutli-source methods, it ...

In this paper, we present a multiple active camera assignment for high fidelity 3D video of a moving object, mainly an acting human body. The camera system is made up of cameras with long focal length lenses for high resolution input images. However, such cameras can capture only partial views of the object. Our goal is to assign the camera set to the different parts of the moving object so as ...

This paper deals with critical motion sequences, i.e. sequences of camera motions that lead to inherent ambiguities in uncalibrated Euclidean reconstruction or self-calibration. Concretely, we focus on how to deal with ambiguous reconstructions. We show that the ambiguous Euclidean reconstructions from a critical motion sequence are conjugated in a special sense. We discuss how these conjugacie...

We present a new method for synthesizing novel views of a 3D scene from few model images in full correspondence. The core of this work is the derivation of a tensorial operator that describes the transformation from a given tensor of three views to a novel tensor of a new configuration of three views. By repeated application of the operator on a seed tensor with a sequence of desired virtual ca...

The goal of automated 3-D measurement of arbitrary objects using photogrammetric methods is a long way from being achieved, but significant progress is being made. However, automated measurement of small objects using inexpensive CCD cameras and frame grabbers is becoming increasingly common. A number of such systems have been developed both for commercial use and for academic research. It is w...

We present a method for tracking objects in 3D by comparing views from multiple video cameras against a 3D model. Camera-based object tracking is a vast field that until recently has been limited to the 2D (image) domain. With the falling cost of sensors in recent years, the research community has been shifting its focus to 3D tracking using networks of calibrated cameras. The standard approach...

We describe the prototype of an image retrieval system used for mobile guide applications. It allows users to send image queries of urban scenes using camera phones. The system uses a database of views of scenes to determine the poses of query views provided by the users. Information are then mapped onto the query views. Our approach is based on a fully affine invariant descriptor, coined PRIUS...

The assignment of multiple person tracks to a set of candidate person locations in overlapping camera views is potentially computationaly intractable, as observables might depend upon visibility order, and thus upon the decision which of the candidate locations represent actual persons and which do not. In this paper, we present an approximate assignment method which consists of two stages. In ...