Fuensanta Torres

  • Citations Per Year
Learn More
Man-made environments contain many weakly textured surfaces which are typically poorly modeled in sparse point reconstructions. Most notable, wiry structures such as fences, scaffolds, or power pylons are not contained at all. This paper presents a novel approach for generating line-based 3D models from image sequences. Initially, camera positions are(More)
This article focuses on the detection of a brain tumor location in magnetic resonance images. The aim of this work is not the precise segmentation of the tumor and its parts but only the detection of its approximate location. It will be used in future work for more accurate segmentation. For this reason, it also does not deal with detecting of the images(More)
Real-time 3D pose estimation from monocular image sequences is a challenging research topic. Although current methods are able to recover 3D pose, they require a high computational cost to process high-resolution images in a video sequence at high frame-rates. To address that problem, we introduce the new concept of check-points. They are the minimum number(More)
Shape is an important feature of many object categories. In this paper we propose a Bayesian framework for detection of unknown number of objects based on their shape. The task is formulated as a minimization of Bayesian risk. The loss function is designed in such a way that the number of objects need not to be known or even bounded. We introduce a(More)
A novel system is presented for predicting the pose, the position and the appearance of 3D rigid objects in video sequences. We consider rigid objects which can be approximately modeled by a convex polyhedral shape. Our approach works in monocular videos and where the position of the camera is fixed. To address this, we propose a two-step approach, first a(More)
A histogram-like model is suggested for the representation of multi-dimensional distributions such as RGB colors of subjects in tracking and segmentation tasks. Unlike the normal 3-D histogram it can be estimated from the limited amount of training data without the need to reduce the precision of the measured data. The proposed hierarchical histogram model(More)
The initialization process of a 3D model-based tracking method with an extremely fast checking time is presented. One initialized, the algorithm will execute a 3D model-based tracking with pose determination. The tracking method is a two-steps approach, a prediction-correction method. We are studying the possibility of finding the minimum group of interest(More)