Correction of shading effects in vision-based UUV localization

This paper describes the improvements achieved in our mosaicking system to assist unmanned underwater vehicle navigation. A major advance has been attained in the processing of images of the ocean floor when light absorption effects are evident. Due to the absorption of natural light, underwater vehicles often require artificial light sources attached to them to provide the adequate illumination for processing underwater images. Unfortunately, these flashlights tend to illuminate the scene in a nonuniform fashion. In this paper a technique to correct non-uniform lighting is proposed. The acquired frames are compensated through a point-by-point division of the image by an estimation of the illumination field. Then, the gray-levels of the obtained image remapped to enhance image contrast. Experiments with real images are presented

A proposal to estimate the motion of an underwater vehicle through visual mosaicking

This thesis proposes a solution to the problem of estimating the motion of an Unmanned Underwater Vehicle (UUV). Our approach is based on the integration of the incremental measurements which are provided by a vision system. When the vehicle is close to the underwater terrain, it constructs a visual map (so called "mosaic") of the area where the mission takes place while, at the same time, it localizes itself on this map, following the Concurrent Mapping and Localization strategy. The proposed methodology to achieve this goal is based on a feature-based mosaicking algorithm. A down-looking camera is attached to the underwater vehicle. As the vehicle moves, a sequence of images of the sea-floor is acquired by the camera. For every image of the sequence, a set of characteristic features is detected by means of a corner detector. Then, their correspondences are found in the next image of the sequence. Solving the correspondence problem in an accurate and reliable way is a difficult task in computer vision. We consider different alternatives to solve this problem by introducing a detailed analysis of the textural characteristics of the image. This is done in two phases: first comparing different texture operators individually, and next selecting those that best characterize the point/matching pair and using them together to obtain a more robust characterization. Various alternatives are also studied to merge the information provided by the individual texture operators. Finally, the best approach in terms of robustness and efficiency is proposed. After the correspondences have been solved, for every pair of consecutive images we obtain a list of image features in the first image and their matchings in the next frame. Our aim is now to recover the apparent motion of the camera from these features. Although an accurate texture analysis is devoted to the matching pro-cedure, some false matches (known as outliers) could still appear among the right correspon-dences. For this reason, a robust estimation technique is used to estimate the planar transformation (homography) which explains the dominant motion of the image. Next, this homography is used to warp the processed image to the common mosaic frame, constructing a composite image formed by every frame of the sequence. With the aim of estimating the position of the vehicle as the mosaic is being constructed, the 3D motion of the vehicle can be computed from the measurements obtained by a sonar altimeter and the incremental motion computed from the homography. Unfortunately, as the mosaic increases in size, image local alignment errors increase the inaccuracies associated to the position of the vehicle. Occasionally, the trajectory described by the vehicle may cross over itself. In this situation new information is available, and the system can readjust the position estimates. Our proposal consists not only in localizing the vehicle, but also in readjusting the trajectory described by the vehicle when crossover information is obtained. This is achieved by implementing an Augmented State Kalman Filter (ASKF). Kalman filtering appears as an adequate framework to deal with position estimates and their associated covariances. Finally, some experimental results are shown. A laboratory setup has been used to analyze and evaluate the accuracy of the mosaicking system. This setup enables a quantitative measurement of the accumulated errors of the mosaics created in the lab. Then, the results obtained from real sea trials using the URIS underwater vehicle are shown.

Utilización de software libre para el análisis de la evolución de usos del suelo en la cuenca del Segura mediante teledetección

En este trabajo se describe la utilización de herramientas de software libre, básicamente GRASS y R, para obtener una serie de mapas de coberturas del suelo (1976-2006) a partir de imágenes de satélite Landsat MSS y Landsat TM. Se trata de un proyecto concedido a un año, por lo que se requería una metodología que permitiera realizar el análisis de forma rápida y sencilla, aún tratando de aplicar técnicas de clasificación avanzadas. Dada la complejidad del trabajo y la premura de tiempo, se ha tratado de automatizar gran parte del trabajo mediante diversos scripts con BASH y R. (...)

Object and Scene Classification: what does a Supervised Approach Provide us?

Given a set of images of scenes containing different object categories (e.g. grass, roads) our objective is to discover these objects in each image, and to use this object occurrences to perform a scene classification (e.g. beach scene, mountain scene). We achieve this by using a supervised learning algorithm able to learn with few images to facilitate the user task. We use a probabilistic model to recognise the objects and further we classify the scene based on their object occurrences. Experimental results are shown and evaluated to prove the validity of our proposal. Object recognition performance is compared to the approaches of He et al. (2004) and Marti et al. (2001) using their own datasets. Furthermore an unsupervised method is implemented in order to evaluate the advantages and disadvantages of our supervised classification approach versus an unsupervised one

Towards Detecting Changes in Underwater Image Sequences

Detecting changes between images of the same scene taken at different times is of great interest for monitoring and understanding the environment. It is widely used for on-land application but suffers from different constraints. Unfortunately, Change detection algorithms require highly accurate geometric and photometric registration. This requirement has precluded their use in underwater imagery in the past. In this paper, the change detection techniques available nowadays for on-land application were analyzed and a method to automatically detect the changes in sequences of underwater images is proposed. Target application scenarios are habitat restoration sites, or area monitoring after sudden impacts from hurricanes or ship groundings. The method is based on the creation of a 3D terrain model from one image sequence over an area of interest. This model allows for synthesizing textured views that correspond to the same viewpoints of a second image sequence. The generated views are photometrically matched and corrected against the corresponding frames from the second sequence. Standard change detection techniques are then applied to find areas of difference. Additionally, the paper shows that it is possible to detect false positives, resulting from non-rigid objects, by applying the same change detection method to the first sequence exclusively. The developed method was able to correctly find the changes between two challenging sequences of images from a coral reef taken one year apart and acquired with two different cameras

A new approach to segmentation based on fusing circumscribed contours, region growing and clustering

One of the major problems in machine vision is the segmentation of images of natural scenes. This paper presents a new proposal for the image segmentation problem which has been based on the integration of edge and region information. The main contours of the scene are detected and used to guide the posterior region growing process. The algorithm places a number of seeds at both sides of a contour allowing stating a set of concurrent growing processes. A previous analysis of the seeds permits to adjust the homogeneity criterion to the regions's characteristics. A new homogeneity criterion based on clustering analysis and convex hull construction is proposed

L'imaginari monumental i artístic del turisme cultural. El cas de la revista Barcelona Atracción

Aportació al Turisme Cultural a partir de l'estudi i anàlisi d'una revista de difusió turística en el mercat internacional, la Barcelona Atracción. (1910-1936 i 1945-1954), amb un anàlisi més extens de l'etapa republicana. La revista s' edita a Barcelona i es difon als cinc continents des de 1910. S'analitza la construcció de la imatge i la propaganda turístiques a partir de la posada en valor del patrimoni cultural, sobretot del monumental i artístic. S'annexen resums de tots els articles de la revista mensual Barcelona Atracción que d'una manera directa o indirecta tenen per subjecte un element cultural tangible o intangible, i un recull de centenars d'imatges de personalitats, monuments, cartells, que il·lustren la revista en l'etapa republicana.

Les pintures rupestres prehistòriques del Zemmur (Sahara Occidental)

El treball de tesi ha tingut per objectiu estudiar les pintures rupestres del Zemmur, al Sahara Occidental. El Zemmur és una regió muntanyosa molt rica en abrics, que s'obren a les cingleres dels seus turons de gres baixos, aplanats i allargassats. Aquestes pintures foren descobertes al 1995, quan el personal del ministeri de Cultura de la República Àrab Sahrauí i Democràtica les va mostrar a un equip d'arqueòlegs i antropòlegs de la Universitat de Girona. Les campanyes d'estudi continuades que s'han realitzat en aquests jaciments de pintura rupestre prehistòrica des d'aleshores han proporcionat les dades per aquesta investigació. En total es tracta d'un conjunt de 2734 figures repartides en 130 abrics de 5 jaciments diferents: Uad Ymal, Uadi Kenta, Rekeiz Ajahfun, Rekeiz Lemgasem i Asako. Les hipòtesis a contrastar eren dues. La primera que al Zemmur hi havia diversos estils de pintura rupestre. La segona que la majoria d'aquests estils dataven de la prehistòria. Ambdues han pogut ser verificades i s'han aportat arguments que demostren que eren certes. El treball de tesi ha consistit en fotografiar les pintures, digitalitzar-les, reproduir-les i estudiar-les. Concretament l'estudi ha consistit en descriure-les, classificar-les estilísticament i datar-les. La classificació s'ha realitzat a partir d'una sèrie de criteris morfològics i tècnics. Posteriorment les imatges han estat atribuïdes a diversos estils, que també havien estat definits amb criteris morfotècnics a partir de l'observació de les imatges. La seva existència, i per tant la verificació de la primera hipòtesi, es dedueix de la presència de recurrències morfotècniques en les representacions. Més tard aquests estils han estat ordenats de manera relativa tot estudiant les seves superposicions. La seqüència dels cinc estils identificats, de més antic a més recent és: Balladors, Modelats, Tracejats, Figures Fosques i Linial. Posteriorment s'ha intentat datar cadascun dels estils a partir de les representacions ja que les anàlisis efectuades indicaren que no era possible datar les imatges per tècniques radiomètriques a causa de la manca de matèria orgànica en les pintures. En qualsevol cas, gràcies a les representacions d'armes, d'animals i els textos escrits hem pogut verificar que la majoria d'elles són prehistòriques, tal com apuntàvem en la nostra segona hipòtesi. Finalment s'ha arribat a la conclusió que l'estil dels Balladors data, de manera molt aproximada, d'ara fa entre 3800 i 3200 anys tal com indiquen les representacions d'alabardes. L'estil Linial, el més recent, data d'entre ara fa 2400 i 2000 anys perquè és acompanyat de textos líbico-berbers però no de representacions de camells. Els estils Modelat, Tracejat i Figures Fosques es daten entremig. A part de les conclusions obtingudes, un dels resultats més importants d'aquest treball ha estat la realització del corpus de pintura prehistòrica del Zemmur que consta, com ja hem dit, de milers d'imatges. Per tant aquesta recerca, a més de tractar sobre un material inèdit i d'un gran interès històric, hauria d'ésser útil per a la gestió de tot aquest patrimoni.