Detecção de região saliente em imagens usando dissimilaridade de cor e amostragem por pixeis aleatórios

The purpose of this work is to demonstrate and to assess a simple algorithm for automatic estimation of the most salient region in an image, that have possible application in computer vision. The algorithm uses the connection between color dissimilarities in the image and the image’s most salient region. The algorithm also avoids using image priors. Pixel dissimilarity is an informal function of the distance of a specific pixel’s color to other pixels’ colors in an image. We examine the relation between pixel color dissimilarity and salient region detection on the MSRA1K image dataset. We propose a simple algorithm for salient region detection through random pixel color dissimilarity. We define dissimilarity by accumulating the distance between each pixel and a sample of n other random pixels, in the CIELAB color space. An important result is that random dissimilarity between each pixel and just another pixel (n = 1) is enough to create adequate saliency maps when combined with median filter, with competitive average performance if compared with other related methods in the saliency detection research field. The assessment was performed by means of precision-recall curves. This idea is inspired on the human attention mechanism that is able to choose few specific regions to focus on, a biological system that the computer vision community aims to emulate. We also review some of the history on this topic of selective attention.

Análise e modelagem do escoamento transitório de fluidos de perfuração

Drilling fluids present a thixotropic behavior and they usually gel when at rest. The sol-gel transition is fundamental to prevent the deposit of rock fragments, generated by drilling the well, over the drill bit during eventual stops. Under those conditions, high pressures are then required in order to break-up the gel when circulation is resumed. Moreover, very high pressures can damage the rock formation at the bottom of the well. Thus, a better understanding of thixotropy and the behavior of thixotropic materials becomes increasingly important for process control. The mechanisms that control thixotropy are not yet well defined and modeling is still a challenge. The objective of this work is to develop a mathematical model to study the pressure transmission in drilling fluids. This work presents a review of thixotropy and of different mathematical models found in the literature that are used to predict such characteristic. It also shows a review of transient flows of compressible fluids. The problem is modeled as the flow between the drillpipe and the annular region (space between the wall and the external part of the drillpipe). The equations that describe the problem (mass conservation, momentum balance, constitutive and state) are then discretized and numerically solved by using a computational algorithm in Fortran. The model is validated with experimental and numerical data obtained from the literature. Comparisons between experimental data obtained from Petrobras and calculated by three viscoplastic and one pseudoplastic models are conducted. The viscoplastic fluids, due to the yield stress, do not fully transmit the pressure to the outlet of the annular space. Sensibility analyses are then conducted in order to evaluate the thixotropic effect in pressure transmission.