VLSI architecture for an Underwater Robot Vision System

It is well known that image processing requires a huge amount of computation, mainly at low level processing where the algorithms are dealing with a great number of data-pixel. One of the solutions to estimate motions involves detection of the correspondences between two images. For normalised correlation criteria, previous experiments shown that the result is not altered in presence of nonuniform illumination. Usually, hardware for motion estimation has been limited to simple correlation criteria. The main goal of this paper is to propose a VLSI architecture for motion estimation using a matching criteria more complex than Sum of Absolute Differences (SAD) criteria. Today hardware devices provide many facilities for the integration of more and more complex designs as well as the possibility to easily communicate with general purpose processors

Dam wall detection and tracking using a Mechanically Scanned Imaging Sonar

In dam inspection tasks, an underwater robot has to grab images while surveying the wall meanwhile maintaining a certain distance and relative orientation. This paper proposes the use of an MSIS (mechanically scanned imaging sonar) for relative positioning of a robot with respect to the wall. An imaging sonar gathers polar image scans from which depth images (range & bearing) are generated. Depth scans are first processed to extract a line corresponding to the wall (with the Hough transform), which is then tracked by means of an EKF (Extended Kalman Filter) using a static motion model and an implicit measurement equation associating the sensed points to the candidate line. The line estimate is referenced to the robot fixed frame and represented in polar coordinates (rho&thetas) which directly corresponds to the actual distance and relative orientation of the robot with respect to the wall. The proposed system has been tested in simulation as well as in water tank conditions

Recovering Euclidean deformable models from stereo-motion

In this paper we present a novel structure from motion (SfM) approach able to infer 3D deformable models from uncalibrated stereo images. Using a stereo setup dramatically improves the 3D model estimation when the observed 3D shape is mostly deforming without undergoing strong rigid motion. Our approach first calibrates the stereo system automatically and then computes a single metric rigid structure for each frame. Afterwards, these 3D shapes are aligned to a reference view using a RANSAC method in order to compute the mean shape of the object and to select the subset of points on the object which have remained rigid throughout the sequence without deforming. The selected rigid points are then used to compute frame-wise shape registration and to extract the motion parameters robustly from frame to frame. Finally, all this information is used in a global optimization stage with bundle adjustment which allows to refine the frame-wise initial solution and also to recover the non-rigid 3D model. We show results on synthetic and real data that prove the performance of the proposed method even when there is no rigid motion in the original sequence

Online Robust 3D Mapping Using Structure from Motion Cues

This paper presents a complete solution for creating accurate 3D textured models from monocular video sequences. The methods are developed within the framework of sequential structure from motion, where a 3D model of the environment is maintained and updated as new visual information becomes available. The camera position is recovered by directly associating the 3D scene model with local image observations. Compared to standard structure from motion techniques, this approach decreases the error accumulation while increasing the robustness to scene occlusions and feature association failures. The obtained 3D information is used to generate high quality, composite visual maps of the scene (mosaics). The visual maps are used to create texture-mapped, realistic views of the scene

Monocular-based 3-D seafloor reconstruction and ortho-mosaicing by piecewise planar representation

Photo-mosaicing techniques have become popular for seafloor mapping in various marine science applications. However, the common methods cannot accurately map regions with high relief and topographical variations. Ortho-mosaicing borrowed from photogrammetry is an alternative technique that enables taking into account the 3-D shape of the terrain. A serious bottleneck is the volume of elevation information that needs to be estimated from the video data, fused, and processed for the generation of a composite ortho-photo that covers a relatively large seafloor area. We present a framework that combines the advantages of dense depth-map and 3-D feature estimation techniques based on visual motion cues. The main goal is to identify and reconstruct certain key terrain feature points that adequately represent the surface with minimal complexity in the form of piecewise planar patches. The proposed implementation utilizes local depth maps for feature selection, while tracking over several views enables 3-D reconstruction by bundle adjustment. Experimental results with synthetic and real data validate the effectiveness of the proposed approach

Automatic classification of breast density

A recent trend in digital mammography is computer-aided diagnosis systems, which are computerised tools designed to assist radiologists. Most of these systems are used for the automatic detection of abnormalities. However, recent studies have shown that their sensitivity is significantly decreased as the density of the breast increases. This dependence is method specific. In this paper we propose a new approach to the classification of mammographic images according to their breast parenchymal density. Our classification uses information extracted from segmentation results and is based on the underlying breast tissue texture. Classification performance was based on a large set of digitised mammograms. Evaluation involves different classifiers and uses a leave-one-out methodology. Results demonstrate the feasibility of estimating breast density using image processing and analysis techniques

A system to reduce the effect of CCDs saturation

Colour image segmentation based on the hue component presents some problems due to the physical process of image formation. One of that problems is colour clipping, which appear when at least one of the sensor components is saturated. We have designed a system, that works for a trained set of colours, to recover the chromatic information of those pixels on which colour has been clipped. The chromatic correction method is based on the fact that hue and saturation are invariant to the uniform scaling of the three RGB components. The proposed method has been validated by means of a specific colour image processing board that has allowed its execution in real time. We show experimental results of the application of our method

Behaviours implemented using a vision system based on coded light projection

In a search for new sensor systems and new methods for underwater vehicle positioning based on visual observation, this paper presents a computer vision system based on coded light projection. 3D information is taken from an underwater scene. This information is used to test obstacle avoidance behaviour. In addition, the main ideas for achieving stabilisation of the vehicle in front of an object are presented

An overview of the advantages and constraints of coded pattern projection techniques for autonomous navigation

The absolute necessity of obtaining 3D information of structured and unknown environments in autonomous navigation reduce considerably the set of sensors that can be used. The necessity to know, at each time, the position of the mobile robot with respect to the scene is indispensable. Furthermore, this information must be obtained in the least computing time. Stereo vision is an attractive and widely used method, but, it is rather limited to make fast 3D surface maps, due to the correspondence problem. The spatial and temporal correspondence among images can be alleviated using a method based on structured light. This relationship can be directly found codifying the projected light; then each imaged region of the projected pattern carries the needed information to solve the correspondence problem. We present the most significant techniques, used in recent years, concerning the coded structured light method

Compression-based Image Registration

Image registration is an important component of image analysis used to align two or more images. In this paper, we present a new framework for image registration based on compression. The basic idea underlying our approach is the conjecture that two images are correctly registered when we can maximally compress one image given the information in the other. The contribution of this paper is twofold. First, we show that the image registration process can be dealt with from the perspective of a compression problem. Second, we demonstrate that the similarity metric, introduced by Li et al., performs well in image registration. Two different versions of the similarity metric have been used: the Kolmogorov version, computed using standard real-world compressors, and the Shannon version, calculated from an estimation of the entropy rate of the images

Medical image registration based on random line sampling

One of the key aspects in 3D-image registration is the computation of the joint intensity histogram. We propose a new approach to compute this histogram using uniformly distributed random lines to sample stochastically the overlapping volume between two 3D-images. The intensity values are captured from the lines at evenly spaced positions, taking an initial random offset different for each line. This method provides us with an accurate, robust and fast mutual information-based registration. The interpolation effects are drastically reduced, due to the stochastic nature of the line generation, and the alignment process is also accelerated. The results obtained show a better performance of the introduced method than the classic computation of the joint histogram

An information theoretic framework for image segmentation

In this paper, an information theoretic framework for image segmentation is presented. This approach is based on the information channel that goes from the image intensity histogram to the regions of the partitioned image. It allows us to define a new family of segmentation methods which maximize the mutual information of the channel. Firstly, a greedy top-down algorithm which partitions an image into homogeneous regions is introduced. Secondly, a histogram quantization algorithm which clusters color bins in a greedy bottom-up way is defined. Finally, the resulting regions in the partitioning algorithm can optionally be merged using the quantized histogram

Implementació logística pel projecte Peccata Mundi

Peccata Mundi arrenca de la iniciativa del director de R+D+I de l'empresa Mas Parés, Jaume Juher, i l’artista plàstic Jaume Xifra, que l’any 2004 van decidir sumar a l’amistat que els uneix un objectiu: convergir en un sol projecte els reptes professionals que es plantejaven individualment des de cadascuna de les seves disciplines: l’art i la investigació gastronòmica. Posteriorment, a l'any 2005, s'incorporen al projecte els experts que constitueixen actualment el nucli central de treball: Josep Bel, expert en anàlisi sensorial i aplicació d'aromes; David Juher, matemàtic i professor de la UdG; Xavier de Palau, músic electrònic; Clara Perxachs, investigadora de la cultura del menjar; i Toni Botella, cuiner. A l'experiència gastronòmico-artística Peccata Mundi el participant tasta un seguit de plats i vins i valora les seves percepcions contestant un qüestionari. Les dades d'aquest qüestionari s'utilitzen, a través d'unes transformacions regides per criteris neurològics, matemàtics, antropològics, etc., per produir unes dades numèriques que seran l'entrada a una aplicació que les farà servir per generar un vídeo amb música d'una durada aproximadament de 2 minuts. Aquest vídeo, que consta d'imatges fractals en moviment i d'una música de fons, generada també utilitzant funcions de comportament caòtic, és el retrat audiovisual de l'experiència sensorial del participant. El projecte consisteix a implementar tota la logística informàtica de l’experiència sensorial Peccata Mundi: dissenyar les aplicacions d'entrada de dades, tractament de la base de dades, processament de les dades del qüestionari, generació del vídeo i la música i producció de l'arxiu audiovisual que finalment el participant s'emporta gravat en suport DVD

Modelatge procedural d’edificis

L’objectiu d’aquest PFC és el desenvolupament d’una eina pel modelatge procedural d’edificis i altres estructures arquitectòniques. El modelatge d’edificis és, per si sol, un bon tema on aplicar‐hi la programació procedural. Un edifici normal compte sempre amb elements que es repeteixen en altura i amplada. El fet de “repetir” una tasca suggereix sempre l’aplicació d’algun tipus de procediment per tal de simplificar i reduir la feina de l’usuari a l’hora de desenvolupar aquesta feina

Mòdul de visualització 3D d’ ajuda al diagnòstic de les neoplàsies rectals

El diagnòstic mitjançant la imatge mèdica s’ha convertit en una eina fonamental en la pràctica clínica, permet entre altres coses, reconstruir a partir d’un conjunt d’imatges 2D, obtingudes a partir d’aparells de captació, qualsevol part de l’organisme d’un pacient i representar-lo en un model 3D. Sobre aquest model 3D poden realitzar-se diferents operacions que faciliten el diagnòstic i la presa de decisions als especialistes. El projecte que es presenta forma part del desenvolupament de la plataforma informàtica de visualització i tractament de dades mèdiques, anomenada Starviewer, que desenvolupen conjuntament el laboratori de Gràfics i Imatge (GiLab) de la Universitat de Girona i l’ Institut de Diagnòstic per la Imatge (IDI) de l’Hospital Josep Trueta de Girona. En particular, en aquest projecte es centra en el diagnòstic del càncer colorectal i el desenvolupament de mètodes i tècniques de suport al seu diagnòstic. Els dos punts claus en el tractament d’aqueta patologia són: la detecció de les lesions I l’estudi de l’evolució d’aquestes lesions, una vegada s’ha iniciat el tractament tumoral. L’objectiu principal d’aquest projecte és implementar i integrar en la plataforma Starviewer les tècniques de visualització i processament de dades necessàries per donar suport als especialistes en el diagnòstic de les lesions del colon. Donada la dificultat en el processament de les dades reals del budell ens proposem: dissenyar i implementar un sistema per crear models sintètics del budell; estudiar, implementar i avaluar les tècniques de processament d’imatge que calen per segmentar lesions de budell; dissenyar i implementar un sistema d’exploració del budell iintegrar de tots els mòduls implementats en la plataforma starviewer