The present Master Thesis describes a new Pose Estimation method based on Convolutional Neural Networks (CNN). This method divides the three-dimensional space in several regions and, given an input image, returns the ...

Traditional shape from silhouette methods compute the 3D shape as the intersection of the back-projected silhouettes in the 3D space, the so called visual hull. However, silhouettes that have been obtained with background ...

Simulation is essential in robotics to evaluate models and techniques in a controlled setting before conducting experiments on tangible agents. However, developing simulation environments can be a challenging and time-consuming ...

In this work, a comparative study between Elliptic Fourier and B-spline descriptors is carried out for comparing their efficiency in characterizing the contour shape of image objects. In both cases, the goal is to obtain ...

The appearance of the city is strongly linked to many aspects such as climate, culture and sociological background. In cities with a prevalence of clear skies, one of the determining aspects is the climatic condition, which ...

Artificial Intelligence (AI) is one of today's fastest growing technologies, and has been evolving for decades. It allows machines to have the ability to "learn", and self-correct. This technology is used in many fields, ...

In recent years, the introduction of Machine Learning together with the use of conventional image processing techniques has given a boost to the generation of images. However, as these models are getting better their ...

In this paper we propose a new contour descriptor for reconstructing fish otolith contours that uses half the number of coefficients needed by the classical elliptical Fourier descriptors (EFDs) for the same accuracy. ...

Magnetic resonance imaging is commonly used as a complement to the ultrasound gold-standard to investigate equivocal patterns in the developing fetal brain. However, stochastic motion of the fetus may alter the image quality ...