Advanced statistical models for the segregation, identification and measurement of coexisting sound sources

Long-term monitoring of acoustical environments is gaining popularity thanks to the relevant amount of scientific and engineering insights that it provides. The increasing interest is due to the constant growth of storage capacity and computational power to process large amounts of data. In this perspective, machine learning (ML) provides a broad family of data-driven statistical techniques to deal with large databases. Nowadays, the conventional praxis of sound level meter measurements limits the global description of a sound scene to an energetic point of view. The equivalent continuous level Leq represents the main metric to define an acoustic environment, indeed. Finer analyses involve the use of statistical levels. However, acoustic percentiles are based on temporal assumptions, which are not always reliable. A statistical approach, based on the study of the occurrences of sound pressure levels, would bring a different perspective to the analysis of long-term monitoring. Depicting a sound scene through the most probable sound pressure level, rather than portions of energy, brought more specific information about the activity carried out during the measurements. The statistical mode of the occurrences can capture typical behaviors of specific kinds of sound sources. The present work aims to propose an ML-based method to identify, separate and measure coexisting sound sources in real-world scenarios. It is based on long-term monitoring and is addressed to acousticians focused on the analysis of environmental noise in manifold contexts. The presented method is based on clustering analysis. Two algorithms, Gaussian Mixture Model and K-means clustering, represent the main core of a process to investigate different active spaces monitored through sound level meters. The procedure has been applied in two different contexts: university lecture halls and offices. The proposed method shows robust and reliable results in describing the acoustic scenario and it could represent an important analytical tool for acousticians.

Inside standard and hyperspectral low-dose CT variational imaging: parameter identification and material decomposition

The main contribution of this thesis is the proposal of novel strategies for the selection of parameters arising in variational models employed for the solution of inverse problems with data corrupted by Poisson noise. In light of the importance of using a significantly small dose of X-rays in Computed Tomography (CT), and its need of using advanced techniques to reconstruct the objects due to the high level of noise in the data, we will focus on parameter selection principles especially for low photon-counts, i.e. low dose Computed Tomography. For completeness, since such strategies can be adopted for various scenarios where the noise in the data typically follows a Poisson distribution, we will show their performance for other applications such as photography, astronomical and microscopy imaging. More specifically, in the first part of the thesis we will focus on low dose CT data corrupted only by Poisson noise by extending automatic selection strategies designed for Gaussian noise and improving the few existing ones for Poisson. The new approaches will show to outperform the state-of-the-art competitors especially in the low-counting regime. Moreover, we will propose to extend the best performing strategy to the hard task of multi-parameter selection showing promising results. Finally, in the last part of the thesis, we will introduce the problem of material decomposition for hyperspectral CT, which data encodes information of how different materials in the target attenuate X-rays in different ways according to the specific energy. We will conduct a preliminary comparative study to obtain accurate material decomposition starting from few noisy projection data.

Detecção e seguimento de objectos em imagens termográficas: análise experimental de modelos de descrição

A instalação de sistemas de videovigilância, no interior ou exterior, em locais como aeroportos, centros comerciais, escritórios, edifícios estatais, bases militares ou casas privadas tem o intuito de auxiliar na tarefa de monitorização do local contra eventuais intrusos. Com estes sistemas é possível realizar a detecção e o seguimento das pessoas que se encontram no ambiente local, tornando a monitorização mais eficiente. Neste contexto, as imagens típicas (imagem natural e imagem infravermelha) são utilizadas para extrair informação dos objectos detectados e que irão ser seguidos. Contudo, as imagens convencionais são afectadas por condições ambientais adversas como o nível de luminosidade existente no local (luzes muito fortes ou escuridão total), a presença de chuva, de nevoeiro ou de fumo que dificultam a tarefa de monitorização das pessoas. Deste modo, tornou‐se necessário realizar estudos e apresentar soluções que aumentem a eficácia dos sistemas de videovigilância quando sujeitos a condições ambientais adversas, ou seja, em ambientes não controlados, sendo uma das soluções a utilização de imagens termográficas nos sistemas de videovigilância. Neste documento são apresentadas algumas das características das câmaras e imagens termográficas, assim como uma caracterização de cenários de vigilância. Em seguida, são apresentados resultados provenientes de um algoritmo que permite realizar a segmentação de pessoas utilizando imagens termográficas. O maior foco desta dissertação foi na análise dos modelos de descrição (Histograma de Cor, HOG, SIFT, SURF) para determinar o desempenho dos modelos em três casos: distinguir entre uma pessoa e um carro; distinguir entre duas pessoas distintas e determinar que é a mesma pessoa ao longo de uma sequência. De uma forma sucinta pretendeu‐se, com este estudo, contribuir para uma melhoria dos algoritmos de detecção e seguimento de objectos em sequências de vídeo de imagens termográficas. No final, através de uma análise dos resultados provenientes dos modelos de descrição, serão retiradas conclusões que servirão de indicação sobre qual o modelo que melhor permite discriminar entre objectos nas imagens termográficas.

Itä-Savon sairaanhoitopiiri Ky:n Savonlinnan keskussairaalan paikannustoiminnan kehittäminen

Terveydenhuollon ja siihen liittyvien palvelujen kustannusten jatkuva kohoaminen ja kuntien paheneva taloustilanne sekä terveydenhuollon pienenevät henkilöstöresurssit ovat lisänneet painetta toimintojen kustannustehokkaaseen toteuttamiseen. Edellä mainitusta johtuen, terveydenhuollon toimijoita kehotetaan etsimään uusia ratkaisuja, joilla voidaan taata jatkossa riittävä asiakaspalvelutaso, kustannustehokkuus ja – palvelujen turvallisuus. Tämän työn tavoitteena oli vastata kysymyksiin tunnistus- ja paikannustoiminnan hyödyntämisen mahdollisuuksista Itä-Savon sairaanhoitopiirin Savonlinnan keskussairaalassa. Tarkoituksena oli selvittää, millaisia paikannus ja tunnistusteknologiaan liittyviä tavoitteita ja vaatimuksia terveydenhuollon toimialalla ja erityisesti Itä-Savon sairaanhoitopiirissä on ja millä tavalla RFID ja WLAN – teknologioilla saadaan kehitettyä asetettuihin tavoitteisiin ja hyötyodotuksiin vastaavat ratkaisut. Työssä pyrittiin selvittämään myös millaisia rahallisia säästöjä tunnistus- ja paikannusteknologioilla voidaan saada aikaan. Työn yhteydessä kartoitettiin tarpeita ja vaatimuksia tunnistus- ja paikannusteknologian hyödyntämiseen. Tarpeet ja vaatimukset testattiin tunnistus- ja paikannuspilotissa. Lisäksi perehdyttiin kirjallisuuteen ja aiempiin tutkimuksiin tunnistus- ja paikannusteknologioista. Suunnitelman perusteella näyttää siltä, että hyödyntämällä tunnistus- ja paikannusteknologioita voitaisiin tehostaa Savonlinnan keskussairaalan toimintaa. Suunnitelman pilottivaiheen tuloksien perusteella toiminnan tehostaminen tarkoittaisi kustannussäästöjä, parantaisi potilasturvallisuutta sekä hoitotyön laatua. Tunnistus- ja paikannusteknologian käyttökohteita sairaalassa voisivat olla esimerkiksi reaaliaikaiseen prosessien ohjaaminen, kulunvalvonnan ja -ohjauksen automatisointi, potilaan automaattinen tunnistaminen, sekä sairaalan tutkimuslaitteiden seuranta.

Expression profiles in the progression of ductal carcinoma in the breast

An understanding of the multi-step nature of cancer as it is in the breast, as a series of pivotal genetic/epigenetic modifications is irrefutably a milestone in diagnostics, prognostics and eventually providing a cure. Here we have utilised a variant of analysis of variance (ANOVA) as a model for the identification and tracking of specific mRNA species whose transcription has been significantly altered at each grade in the progression of ductal carcinoma, making it possible to correlate histological progression with the genetic events underlying breast cancer. We show that in the progression of ductal carcinomas, from grade 1 to 3, there is a reduction in the actual number of mRNA species, which are significantly over or under expressed. We also show that this technique can be employed to generate differential gene expression patterns, whereby the combined expression profile of the tailored spectra of genes in the comparison of each ductal grade is sufficient to render them on clearly separate arms of an array-wise hierarchical cluster dendrogram.

A Census of Eddy Activities in the South China Sea During 1993-2007

Numerous mesoscale eddies occur each year in the South China Sea (SCS), but their statistical characteristics are still not well documented. A Pacific basin-wide three dimensional physical-biogeochemical model has been developed and the result in the SCS subdomain is used to quantify the eddy activities during the period of 1993-2007. The modeled results are compared with a merged and gridded satellite product of sea level anomaly by using the same eddy identification and tracking method. On average, there are about 32.9 +/- 2.4 eddies predicted by the model and 32.8 +/- 3.4 eddies observed by satellite each year, and about 52% of them are cyclonic eddies. The radius of these eddies ranges from about 46.5 to 223.5 km, with a mean value of 87.4 km. More than 70% of the eddies have a radius smaller than 100 km. The mean area covered by these eddies each year is around 160,170 km(2), equivalent to 9.8% of the SCS area with water depths greater than 1000 m. Linear relationships are found between eddy lifetime and eddy magnitude and between eddy vertical extent and eddy magnitude, showing that strong eddies usually last longer and penetrate deeper than weak ones. Interannual variations in eddy numbers and the total eddy-occupied area indicate that eddy activities in the SCS do not directly correspond to the El Nino-Southern Oscillation events. The wind stress curls are thought to be an important but not the only mechanism of eddy genesis in the SCS.

Homography-based ground plane detection using a single on-board camera

This study presents a robust method for ground plane detection in vision-based systems with a non-stationary camera. The proposed method is based on the reliable estimation of the homography between ground planes in successive images. This homography is computed using a feature matching approach, which in contrast to classical approaches to on-board motion estimation does not require explicit ego-motion calculation. As opposed to it, a novel homography calculation method based on a linear estimation framework is presented. This framework provides predictions of the ground plane transformation matrix that are dynamically updated with new measurements. The method is specially suited for challenging environments, in particular traffic scenarios, in which the information is scarce and the homography computed from the images is usually inaccurate or erroneous. The proposed estimation framework is able to remove erroneous measurements and to correct those that are inaccurate, hence producing a reliable homography estimate at each instant. It is based on the evaluation of the difference between the predicted and the observed transformations, measured according to the spectral norm of the associated matrix of differences. Moreover, an example is provided on how to use the information extracted from ground plane estimation to achieve object detection and tracking. The method has been successfully demonstrated for the detection of moving vehicles in traffic environments.

Real-time intensity domain characterization of fibre lasers using spatio-temporal dynamics

Fibre lasers are light sources that are synonymous with stability. They can give rise to highly coherent continuous-wave radiation, or a stable train of mode locked pulses with well-defined characteristics. However, they can also exhibit an exceedingly diverse range of nonlinear operational regimes spanning a multi-dimensional parameter space. The complex nature of the dynamics poses significant challenges in the theoretical and experimental studies of such systems. Here, we demonstrate how the real-time experimental methodology of spatio-temporal dynamics can be used to unambiguously identify and discern between such highly complex lasing regimes. This two-dimensional representation of laser intensity allows the identification and tracking of individual features embedded in the radiation as they make round-trip circulations inside the cavity. The salient features of this methodology are highlighted by its application to the case of Raman fibre lasers and a partially mode locked ring fibre laser operating in the normal dispersion regime.

Semantic feature-based visual attention model for pedestrian detection

Objective
Pedestrian detection under video surveillance systems has always been a hot topic in computer vision research. These systems are widely used in train stations, airports, large commercial plazas, and other public places. However, pedestrian detection remains difficult because of complex backgrounds. Given its development in recent years, the visual attention mechanism has attracted increasing attention in object detection and tracking research, and previous studies have achieved substantial progress and breakthroughs. We propose a novel pedestrian detection method based on the semantic features under the visual attention mechanism.
Method
The proposed semantic feature-based visual attention model is a spatial-temporal model that consists of two parts: the static visual attention model and the motion visual attention model. The static visual attention model in the spatial domain is constructed by combining bottom-up with top-down attention guidance. Based on the characteristics of pedestrians, the bottom-up visual attention model of Itti is improved by intensifying the orientation vectors of elementary visual features to make the visual saliency map suitable for pedestrian detection. In terms of pedestrian attributes, skin color is selected as a semantic feature for pedestrian detection. The regional and Gaussian models are adopted to construct the skin color model. Skin feature-based visual attention guidance is then proposed to complete the top-down process. The bottom-up and top-down visual attentions are linearly combined using the proper weights obtained from experiments to construct the static visual attention model in the spatial domain. The spatial-temporal visual attention model is then constructed via the motion features in the temporal domain. Based on the static visual attention model in the spatial domain, the frame difference method is combined with optical flowing to detect motion vectors. Filtering is applied to process the field of motion vectors. The saliency of motion vectors can be evaluated via motion entropy to make the selected motion feature more suitable for the spatial-temporal visual attention model.
Result
Standard datasets and practical videos are selected for the experiments. The experiments are performed on a MATLAB R2012a platform. The experimental results show that our spatial-temporal visual attention model demonstrates favorable robustness under various scenes, including indoor train station surveillance videos and outdoor scenes with swaying leaves. Our proposed model outperforms the visual attention model of Itti, the graph-based visual saliency model, the phase spectrum of quaternion Fourier transform model, and the motion channel model of Liu in terms of pedestrian detection. The proposed model achieves a 93% accuracy rate on the test video.
Conclusion
This paper proposes a novel pedestrian method based on the visual attention mechanism. A spatial-temporal visual attention model that uses low-level and semantic features is proposed to calculate the saliency map. Based on this model, the pedestrian targets can be detected through focus of attention shifts. The experimental results verify the effectiveness of the proposed attention model for detecting pedestrians.

People and object tracking for video annotation

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Mycobacteria mobility shift assay: a method for the rapid identification of Mycobacterium tuberculosis and nontuberculous mycobacteria

The identification of mycobacteria is essential because tuberculosis (TB) and mycobacteriosis are clinically indistinguishable and require different therapeutic regimens. The traditional phenotypic method is time consuming and may last up to 60 days. Indeed, rapid, affordable, specific and easy-to-perform identification methods are needed. We have previously described a polymerase chain reaction-based method called a mycobacteria mobility shift assay (MMSA) that was designed for Mycobacterium tuberculosis complex (MTC) and nontuberculous mycobacteria (NTM) species identification. The aim of this study was to assess the MMSA for the identification of MTC and NTM clinical isolates and to compare its performance with that of the PRA-hsp65 method. A total of 204 clinical isolates (102 NTM and 102 MTC) were identified by the MMSA and PRA-hsp65. For isolates for which these methods gave discordant results, definitive species identification was obtained by sequencing fragments of the 16S rRNA and hsp65 genes. Both methods correctly identified all MTC isolates. Among the NTM isolates, the MMSA alone assigned 94 (92.2%) to a complex or species, whereas the PRA-hsp65 method assigned 100% to a species. A 91.5% agreement was observed for the 94 NTM isolates identified by both methods. The MMSA provided correct identification for 96.8% of the NTM isolates compared with 94.7% for PRA-hsp65. The MMSA is a suitable auxiliary method for routine use for the rapid identification of mycobacteria.

Temporally stable feature clusters for maritime object tracking in visible and thermal imagery

This paper describes a new approach to detect and track maritime objects in real time. The approach particularly addresses the highly dynamic maritime environment, panning cameras, target scale changes, and operates on both visible and thermal imagery. Object detection is based on agglomerative clustering of temporally stable features. Object extents are first determined based on persistence of detected features and their relative separation and motion attributes. An explicit cluster merging and splitting process handles object creation and separation. Stable object clus- ters are tracked frame-to-frame. The effectiveness of the approach is demonstrated on four challenging real-world public datasets.

Simultaneous 3D object tracking and camera parameter estimation by Bayesian methods and transdimensional MCMC sampling

Multi-camera 3D tracking systems with overlapping cameras represent a powerful mean for scene analysis, as they potentially allow greater robustness than monocular systems and provide useful 3D information about object location and movement. However, their performance relies on accurately calibrated camera networks, which is not a realistic assumption in real surveillance environments. Here, we introduce a multi-camera system for tracking the 3D position of a varying number of objects and simultaneously refin-ing the calibration of the network of overlapping cameras. Therefore, we introduce a Bayesian framework that combines Particle Filtering for tracking with recursive Bayesian estimation methods by means of adapted transdimensional MCMC sampling. Addi-tionally, the system has been designed to work on simple motion detection masks, making it suitable for camera networks with low transmission capabilities. Tests show that our approach allows a successful performance even when starting from clearly inaccurate camera calibrations, which would ruin conventional approaches.

Vision-Based Tracking, Odometry and Control for UAV Autonomy

El principal objetivo de este trabajo es proporcionar una solución en tiempo real basada en visión estéreo o monocular precisa y robusta para que un vehículo aéreo no tripulado (UAV) sea autónomo en varios tipos de aplicaciones UAV, especialmente en entornos abarrotados sin señal GPS. Este trabajo principalmente consiste en tres temas de investigación de UAV basados en técnicas de visión por computador: (I) visual tracking, proporciona soluciones efectivas para localizar visualmente objetos de interés estáticos o en movimiento durante el tiempo que dura el vuelo del UAV mediante una aproximación adaptativa online y una estrategia de múltiple resolución, de este modo superamos los problemas generados por las diferentes situaciones desafiantes, tales como cambios significativos de aspecto, iluminación del entorno variante, fondo del tracking embarullado, oclusión parcial o total de objetos, variaciones rápidas de posición y vibraciones mecánicas a bordo. La solución ha sido utilizada en aterrizajes autónomos, inspección de plataformas mar adentro o tracking de aviones en pleno vuelo para su detección y evasión; (II) odometría visual: proporciona una solución eficiente al UAV para estimar la posición con 6 grados de libertad (6D) usando únicamente la entrada de una cámara estéreo a bordo del UAV. Un método Semi-Global Blocking Matching (SGBM) eficiente basado en una estrategia grueso-a-fino ha sido implementada para una rápida y profunda estimación del plano. Además, la solución toma provecho eficazmente de la información 2D y 3D para estimar la posición 6D, resolviendo de esta manera la limitación de un punto de referencia fijo en la cámara estéreo. Una robusta aproximación volumétrica de mapping basada en el framework Octomap ha sido utilizada para reconstruir entornos cerrados y al aire libre bastante abarrotados en 3D con memoria y errores correlacionados espacialmente o temporalmente; (III) visual control, ofrece soluciones de control prácticas para la navegación de un UAV usando Fuzzy Logic Controller (FLC) con la estimación visual. Y el framework de Cross-Entropy Optimization (CEO) ha sido usado para optimizar el factor de escala y la función de pertenencia en FLC. Todas las soluciones basadas en visión en este trabajo han sido probadas en test reales. Y los conjuntos de datos de imágenes reales grabados en estos test o disponibles para la comunidad pública han sido utilizados para evaluar el rendimiento de estas soluciones basadas en visión con ground truth. Además, las soluciones de visión presentadas han sido comparadas con algoritmos de visión del estado del arte. Los test reales y los resultados de evaluación muestran que las soluciones basadas en visión proporcionadas han obtenido rendimientos en tiempo real precisos y robustos, o han alcanzado un mejor rendimiento que aquellos algoritmos del estado del arte. La estimación basada en visión ha ganado un rol muy importante en controlar un UAV típico para alcanzar autonomía en aplicaciones UAV. ABSTRACT The main objective of this dissertation is providing real-time accurate robust monocular or stereo vision-based solution for Unmanned Aerial Vehicle (UAV) to achieve the autonomy in various types of UAV applications, especially in GPS-denied dynamic cluttered environments. This dissertation mainly consists of three UAV research topics based on computer vision technique: (I) visual tracking, it supplys effective solutions to visually locate interesting static or moving object over time during UAV flight with on-line adaptivity approach and multiple-resolution strategy, thereby overcoming the problems generated by the different challenging situations, such as significant appearance change, variant surrounding illumination, cluttered tracking background, partial or full object occlusion, rapid pose variation and onboard mechanical vibration. The solutions have been utilized in autonomous landing, offshore floating platform inspection and midair aircraft tracking for sense-and-avoid; (II) visual odometry: it provides the efficient solution for UAV to estimate the 6 Degree-of-freedom (6D) pose using only the input of stereo camera onboard UAV. An efficient Semi-Global Blocking Matching (SGBM) method based on a coarse-to-fine strategy has been implemented for fast depth map estimation. In addition, the solution effectively takes advantage of both 2D and 3D information to estimate the 6D pose, thereby solving the limitation of a fixed small baseline in the stereo camera. A robust volumetric occupancy mapping approach based on the Octomap framework has been utilized to reconstruct indoor and outdoor large-scale cluttered environments in 3D with less temporally or spatially correlated measurement errors and memory; (III) visual control, it offers practical control solutions to navigate UAV using Fuzzy Logic Controller (FLC) with the visual estimation. And the Cross-Entropy Optimization (CEO) framework has been used to optimize the scaling factor and the membership function in FLC. All the vision-based solutions in this dissertation have been tested in real tests. And the real image datasets recorded from these tests or available from public community have been utilized to evaluate the performance of these vision-based solutions with ground truth. Additionally, the presented vision solutions have compared with the state-of-art visual algorithms. Real tests and evaluation results show that the provided vision-based solutions have obtained real-time accurate robust performances, or gained better performance than those state-of-art visual algorithms. The vision-based estimation has played a critically important role for controlling a typical UAV to achieve autonomy in the UAV application.

Highly pathogenic adapted HIV-1 strains limit host immunity and dictate rapid disease progression.

OBJECTIVE:: The study of HIV-1 rapid progressors has been limited to specific case reports. Nevertheless, identification and characterization of the viral and host factors involved in rapid progression are crucial when attempting to uncover the correlates of rapid disease outcome. DESIGN:: We carried out comparative functional analyses in rapid progressors (n = 46) and standard progressors (n = 46) early after HIV-1 seroconversion (≤1 year). The viral traits tested were viral replicative capacity, co-receptor usage, and genomic variation. Host CD8 T-cell responses, humoral activity, and HLA immunogenetic markers were also determined. RESULTS:: Our data demonstrate an unusual convergence of highly pathogenic HIV-1 strains in rapid progressors. Compared with standard progressors, rapid progressor viral strains show higher in-vitro replicative capacity (81.5 vs. 67.9%; P = 0.025) and greater X4/DM co-receptor usage (26.3 vs. 2.8%; P = 0.006) in early infection. Limited or absent functional HIV-1 CD8 T-cell responses and neutralizing activity were measured in rapid progressors. Moreover, the increase in common HLA allele-restricted CD8 T-cell escape mutations in rapid progressors acts as a signature of uncontrolled HIV-1 replication and early impairment of adaptive cellular responses. CONCLUSION:: Our data support a dominant role for viral factors in rapid progressors. Robust HIV-1 replication and intrinsic viral properties limit host adaptive immune responses, thus driving rapid disease progression.