Catálogo de publicaciones - libros

This paper introduces motion capture a technique of digitally recording motion for entertainment, sports and medical applications. Presented analysis of possibilities as well as some modifications is an important part of a complex identification system. The results discussed in this paper can help to determine what kinds of methods could be best applied in a given context.

In this paper we present a variational approach to accurately estimate the motion vector field in a image sequence introducing a second order Taylor expansion of the flow in the energy function to be minimized. This feature allows us to simultaneously obtain, in addition, an estimation of the partial derivatives of the motion vector field. The performance of our approach is illustrated with the estimation of the displacement vector field on the well known Yosemite sequence and compared to other techniques from the state of the art.

In this paper we describe an application of the optical flow in order to create a slow motion effect and frame rate conversion on streaming image sequences. Our results show that using the optical flow based method the image sequence shows much less artifacts than than in traditional interpolation or mixing methods.

Many methods have been developed in the last few years to self-calibrate cameras, but few works have addressed the comparison of such methods to provide the user with hints on the suitability of certain algorithms under particular circumstances. This work presents a comparative analysis of four self-calibration methods for cameras which only rotate. This paper concentrates on the stability, the accuracy in the estimation of each parameter and the computational cost. This study has been carried out with real and simulated images. The experiments have shown that the optic center is the most unstable parameter for all methods and that the greatest discrepancies among the estimated values appear with the scale factors. Also, there are no correspondence among image disparity and parameters error. Finally, the results returned by any of these methods are comparable in terms of accuracy with those provided by a well-known manual calibration method.

Nowadays time the 3D reconstruction from 2D images has become a tool of daily use for the medical diagnosis. Usually, many tools exist that can make this reconstruction, but when discovering problems in small vessels or areas, as it could be the neck, then tools that detect the borders of the objects of a precise way are needed. For that reasons, in this work, we have used the snake method, that allows to find the contour of small objects with high accuracy. A problem that presents the snake process is that it needs to start from an initial contour, which is usually introduced by hand. This becomes a big problem in medical imaging where the amount of images is very large, and the number of sections of small objects in each image also can be important. In this work we have automated the entrance of this initial contour from an inner point of the object that we want to detect.

The interest for developing annotation tools for interpretation of video sequences arises on the own necessity of conceptualizing scenes with a suitable degree of semantics for the application domain. In this paper we analyze the features that must be present in a video annotation tool for video understanding: the entities of interest that appear in each description level of the scene are analyzed and primary features (those that must be annotated initially) and derived features (those obtained automatically) are distinguished. Lastly, we present a video annotation tool based on the previous analysis, for which the design we have chosen is modular, reusable and user friendly.

The aim of this work is to propose a model for computing the optical flow in a sequence of images. We introduce a new temporal regularizer that is suitable for large displacements. We propose to decouple the spatial and temporal regularizations to avoid an incongruous formulation. For the spatial regularization we use the Nagel–Enkelmann operator and a newly designed temporal regularization. Our model is based on an energy functional that yields a partial differential equation (PDE). This PDE is embedded into a multipyramidal strategy to recover large displacements. A gradient descent technique is applied at each scale to reach the minimum.

This paper presents a design adapting the Kalman Filter to the vehicle system domain and Field Programmable Logic technology. The objective to which the system will be applied is detection of road lines from visual information, derived from a low cost monochrome camera with real time response requirements and good results for real scenarios (secondary roads, rain, damaged or occluded road lines..). The sections will describe how the original algorithm is mapped to a real time hardware vision system, which includes a low-cost FPGA processing system and a camera, for vehicle applications. The paper will also illustrate how the needed tasks have been implemented on the FPGA, with the logical architectural restrictions. It mentions also the ways in which overall performance will be increased.

This paper describes a computational framework for the fully automated detection of line segments in 2D digital images. The operation of the framework is divided in two stages, the low level directional primitive detection through Gabor wavelets and growing cell structures, and the segment detection through an efficient and very accurate combination of the fuzzy Hough transform and the Burns segment detector.

This paper proposes to use the Fisher kernel for planar shape recognition. A synthetic experiment with artificial shapes has been built. The difference among shapes is the number of vertexes, links between vertexes, size and rotation. The 2D-shapes are parameterized with sweeping angles in order to obtain scale and rotation invariance. A Hidden Markov Model is used to obtain the Fisher score which feeds the Support Vector Machine based classifier. Noise has been added to the shapes in order to check the robustness of the system against noise. Hit ratio score over 99%, has been obtained, which shows the ability of the Fisher kernel tool for planar shape recognition.