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

A review of sensor fusion techniques for underwater vehicle navigation

This work provides a general description of the multi sensor data fusion concept, along with a new classification of currently used sensor fusion techniques for unmanned underwater vehicles (UUV). Unlike previous proposals that focus the classification on the sensors involved in the fusion, we propose a synthetic approach that is focused on the techniques involved in the fusion and their applications in UUV navigation. We believe that our approach is better oriented towards the development of sensor fusion systems, since a sensor fusion architecture should be first of all focused on its goals and then on the fused sensors

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 Camera-Projector System for Robot Positioning by Visual Servoing

Positioning a robot with respect to objects by using data provided by a camera is a well known technique called visual servoing. In order to perform a task, the object must exhibit visual features which can be extracted from different points of view. Then, visual servoing is object-dependent as it depends on the object appearance. Therefore, performing the positioning task is not possible in presence of nontextured objets or objets for which extracting visual features is too complex or too costly. This paper proposes a solution to tackle this limitation inherent to the current visual servoing techniques. Our proposal is based on the coded structured light approach as a reliable and fast way to solve the correspondence problem. In this case, a coded light pattern is projected providing robust visual features independently of the object appearance

A new optimised De Bruijn coding strategy for structured light patterns

Coded structured light is an optical technique based on active stereovision that obtains the shape of objects. One shot techniques are based on projecting a unique light pattern with an LCD projector so that grabbing an image with a camera, a large number of correspondences can be obtained. Then, a 3D reconstruction of the illuminated object can be recovered by means of triangulation. The most used strategy to encode one-shot patterns is based on De Bruijn sequences. In This work a new way to design patterns using this type of sequences is presented. The new coding strategy minimises the number of required colours and maximises both the resolution and the accuracy

Implementation of a robust coded structured light technique for dynamic 3D measurements

This paper presents the implementation details of a coded structured light system for rapid shape acquisition of unknown surfaces. Such techniques are based on the projection of patterns onto a measuring surface and grabbing images of every projection with a camera. Analyzing the pattern deformations that appear in the images, 3D information of the surface can be calculated. The implemented technique projects a unique pattern so that it can be used to measure moving surfaces. The structure of the pattern is a grid where the color of the slits are selected using a De Bruijn sequence. Moreover, since both axis of the pattern are coded, the cross points of the grid have two codewords (which permits to reconstruct them very precisely), while pixels belonging to horizontal and vertical slits have also a codeword. Different sets of colors are used for horizontal and vertical slits, so the resulting pattern is invariant to rotation. Therefore, the alignment constraint between camera and projector considered by a lot of authors is not necessary

Imaging techniques and histology in the evaluation of liver fibrosis in hepatosplenic schistosomiasis mansoni in Brazil: a comparative study

Few publications have compared ultrasound (US) to histology in diagnosing schistosomiasis-induced liver fibrosis (LF); none has used magnetic resonance (MR). The aim of this study was to evaluate schistosomal LF using these three methods. Fourteen patients with hepatosplenic schistosomiasis admitted to hospital for surgical treatment of variceal bleeding were investigated. They were submitted to upper digestive endoscopy, US, MR and wedge liver biopsy. The World Health Organization protocol for US in schistosomiasis was used. Hepatic fibrosis was classified as absent, slight, moderate or intense. Histology and MR confirmed Symmers' fibrosis in all cases. US failed to detect it in one patient. Moderate agreement was found comparing US to MR; poor agreement was found when US or MR were compared to histology. Re-classifying LF as only slight or intense created moderate agreement between imaging techniques and histology. Histomorphometry did not separate slight from intense LF. Two patients with advanced hepatosplenic schistosomiasis presented slight LF. Our data suggest that the presence of the characteristic periportal fibrosis, diagnosed by US, MR or histology, associated with a sign of portal hypertension, defines the severity of the disease. We conclude that imaging techniques are reliable to define the presence of LF but fail in grading its intensity.

Assessment of Severe Apnoea through Voice Analysis, Automatic Speech, and Speaker Recognition Techniques

This study is part of an ongoing collaborative effort between the medical and the signal processing communities to promote research on applying standard Automatic Speech Recognition (ASR) techniques for the automatic diagnosis of patients with severe obstructive sleep apnoea (OSA). Early detection of severe apnoea cases is important so that patients can receive early treatment. Effective ASR-based detection could dramatically cut medical testing time. Working with a carefully designed speech database of healthy and apnoea subjects, we describe an acoustic search for distinctive apnoea voice characteristics. We also study abnormal nasalization in OSA patients by modelling vowels in nasal and nonnasal phonetic contexts using Gaussian Mixture Model (GMM) pattern recognition on speech spectra. Finally, we present experimental findings regarding the discriminative power of GMMs applied to severe apnoea detection. We have achieved an 81% correct classification rate, which is very promising and underpins the interest in this line of inquiry.

Interacting software-agents to support a kind of expert supervision systems

Expert supervision systems are software applications specially designed to automate process monitoring. The goal is to reduce the dependency on human operators to assure the correct operation of a process including faulty situations. Construction of this kind of application involves an important task of design and development in order to represent and to manipulate process data and behaviour at different degrees of abstraction for interfacing with data acquisition systems connected to the process. This is an open problem that becomes more complex with the number of variables, parameters and relations to account for the complexity of the process. Multiple specialised modules tuned to solve simpler tasks that operate under a co-ordination provide a solution. A modular architecture based on concepts of software agents, taking advantage of the integration of diverse knowledge-based techniques, is proposed for this purpose. The components (software agents, communication mechanisms and perception/action mechanisms) are based on ICa (Intelligent Control architecture), software middleware supporting the build-up of applications with software agent features

Expert supervision based on cases

The paper focuses on taking advantage of large amounts of data that are systematically stored in plants (by means of SCADA systems), but not exploited enough in order to achieve supervisory goals (fault detection, diagnosis and reconfiguration). The methodology of case base reasoning (CBR) is proposed to perform supervisory tasks in industrial processes by re-using the stored data. The goal is to take advantage of experiences, registered in a suitable structure as cam, avoiding the tedious task of knowledge acquisition and representation needed by other reasoning techniques as expert systems. An outlook of CBR terminology and basic concepts are presented. The adaptation of CBR in performing expert supervisory tasks, taking into account the particularities and difficulties derived from dynamic systems, is discussed. A special interest is focused in proposing a general case definition suitable for supervisory tasks. Finally, this structure and the whole methodology is tested in a application example for monitoring a real drier chamber

NUTRISOL: un programa informático para la evaluación nutricional comunitaria y hospitalaria de acceso libre.

We have developed the computer programme NUTRISOL, a nutritional programme destined to analysis of dietary intake by means of the food transformation to nutrient. It has been performed under Windows operative system, using Visual Basic 6.0. It is presented in a CD-Rom. We have used the Spanish CSIC Food Composition Table and domestic food measures commonly used in Spain which could be modified and updated. Diverse kind of diets and reference anthropometric data are also presented. The results may be treated using various statistical programmes. The programme contains three modules: 1) Nutritional epidemiology, which allows to create or open a data base, sample management, analyse food intake, consultation of nutrient content and exportation of data to statistical programmes. 2) Analyses of diets and recipes, creation or modification of new ones. 3) To ask different diets for prevalent pathologies. Independent tools for modifying the original tables, calculate energetic needs, recommend nutrient intake and anthropometric indexes are also offered. In conclusion, NUTRISOL Programme is an application which runs in PC computers with minimal equipment in a friendly interface, of easy use, freeware, which may be adapted to each country, and has demonstrated its usefulness and reliability in different epidemiologic studies. Furthermore, it may become an efficient instrument for clinical nutrition and health promotion.

Evaluation of rapid techniques for the detection of mycobacteria in sputum with scanty bacilli or clinically evident, smear negative cases of pulmonary and extra-pulmonary tuberculosis

The objective of the current study was to compare two rapid methods, the BBL Mycobacteria Growth Indicator Tube (MGIT TM) and Biotec FASTPlaque TB TM (FPTB) assays, with the conventional Löwenstein-Jensen (LJ) media assay to diagnose mycobacterial infections from paucibacillary clinical specimens. For evaluation of the clinical utility of the BBL MGIT TM and FPTB assays, respiratory tract specimens (n = 208), with scanty bacilli or clinically evident, smear negative cases and non-respiratory tract specimens (n = 119) were analyzed and the performance of each assay was compared with LJ media. MGIT and FPTB demonstrated a greater sensitivity (95.92% and 87.68%), specificity (94.59% and 98.78%), positive predictive value (94.91% and 99.16%) and negative predictive value (96.56% and 90.92%), respectively, compared to LJ culture for both respiratory tract and non-respiratory tract specimens. However, the FPTB assay was unable to detect nontuberculous mycobacteria and few Mycobacterium tuberculosis complex cases from paucibacillary clinical specimens. It is likely that the analytical sensitivity of FPTB is moderately low and may not be useful for the direct detection of tuberculosis in paucibacillary specimens. The current study concluded that MGIT was a dependable, highly efficient system for recovery of M. tuberculosis complexes and nontuberculous mycobacteria from both respiratory and non-respiratory tract specimens in combination with LJ media.

Evaluation of two coproscopic techniques for the diagnosis of schistosomiasis in a low-transmission area in the state of Minas Gerais, Brazil

This population study, which evaluated two parasitological methods for the diagnosis of schistosomiasis mansoni, was performed in a low-transmission area in Pedra Preta, Montes Claros, Minas Gerais, Brazil. A total of 201 inhabitants of the rural area participated in this research. Four stool samples were obtained from all participants and analysed using the Kato-Katz method (18 slides) and a commercial test, the TF-Test®, which was performed quantitatively. The data were analysed to determine prevalence, the sensitivity of the diagnostic methods, the worm burden and the definition of the "gold standard", which was obtained by totalling the results of all samples examined using the Kato-Katz technique and the TF-Test®. The results showed that the prevalence obtained from the examination of one Kato-Katz slide (the methodology adopted by the Brazilian control programme) was 8% compared to 35.8% from the "gold standard", which was a 4.5-fold difference. This result indicates that the prevalence of schistosomiasis in so-called low-transmission areas is significantly underestimated.