Advanced image processing techniques for detection and quantification of drusen

Dissertation presented to obtain the degree of Doctor of Philosophy in Electrical Engineering, speciality on Perceptional Systems, by the Universidade Nova de Lisboa, Faculty of Sciences and Technology

Unmixing hyperspectral data: independent and dependent component analysis

The development of high spatial resolution airborne and spaceborne sensors has improved the capability of ground-based data collection in the fields of agriculture, geography, geology, mineral identification, detection [2, 3], and classification [4–8]. The signal read by the sensor from a given spatial element of resolution and at a given spectral band is a mixing of components originated by the constituent substances, termed endmembers, located at that element of resolution. This chapter addresses hyperspectral unmixing, which is the decomposition of the pixel spectra into a collection of constituent spectra, or spectral signatures, and their corresponding fractional abundances indicating the proportion of each endmember present in the pixel [9, 10]. Depending on the mixing scales at each pixel, the observed mixture is either linear or nonlinear [11, 12]. The linear mixing model holds when the mixing scale is macroscopic [13]. The nonlinear model holds when the mixing scale is microscopic (i.e., intimate mixtures) [14, 15]. The linear model assumes negligible interaction among distinct endmembers [16, 17]. The nonlinear model assumes that incident solar radiation is scattered by the scene through multiple bounces involving several endmembers [18]. Under the linear mixing model and assuming that the number of endmembers and their spectral signatures are known, hyperspectral unmixing is a linear problem, which can be addressed, for example, under the maximum likelihood setup [19], the constrained least-squares approach [20], the spectral signature matching [21], the spectral angle mapper [22], and the subspace projection methods [20, 23, 24]. Orthogonal subspace projection [23] reduces the data dimensionality, suppresses undesired spectral signatures, and detects the presence of a spectral signature of interest. The basic concept is to project each pixel onto a subspace that is orthogonal to the undesired signatures. As shown in Settle [19], the orthogonal subspace projection technique is equivalent to the maximum likelihood estimator. This projection technique was extended by three unconstrained least-squares approaches [24] (signature space orthogonal projection, oblique subspace projection, target signature space orthogonal projection). Other works using maximum a posteriori probability (MAP) framework [25] and projection pursuit [26, 27] have also been applied to hyperspectral data. In most cases the number of endmembers and their signatures are not known. Independent component analysis (ICA) is an unsupervised source separation process that has been applied with success to blind source separation, to feature extraction, and to unsupervised recognition [28, 29]. ICA consists in finding a linear decomposition of observed data yielding statistically independent components. Given that hyperspectral data are, in given circumstances, linear mixtures, ICA comes to mind as a possible tool to unmix this class of data. In fact, the application of ICA to hyperspectral data has been proposed in reference 30, where endmember signatures are treated as sources and the mixing matrix is composed by the abundance fractions, and in references 9, 25, and 31–38, where sources are the abundance fractions of each endmember. In the first approach, we face two problems: (1) The number of samples are limited to the number of channels and (2) the process of pixel selection, playing the role of mixed sources, is not straightforward. In the second approach, ICA is based on the assumption of mutually independent sources, which is not the case of hyperspectral data, since the sum of the abundance fractions is constant, implying dependence among abundances. This dependence compromises ICA applicability to hyperspectral images. In addition, hyperspectral data are immersed in noise, which degrades the ICA performance. IFA [39] was introduced as a method for recovering independent hidden sources from their observed noisy mixtures. IFA implements two steps. First, source densities and noise covariance are estimated from the observed data by maximum likelihood. Second, sources are reconstructed by an optimal nonlinear estimator. Although IFA is a well-suited technique to unmix independent sources under noisy observations, the dependence among abundance fractions in hyperspectral imagery compromises, as in the ICA case, the IFA performance. Considering the linear mixing model, hyperspectral observations are in a simplex whose vertices correspond to the endmembers. Several approaches [40–43] have exploited this geometric feature of hyperspectral mixtures [42]. Minimum volume transform (MVT) algorithm [43] determines the simplex of minimum volume containing the data. The MVT-type approaches are complex from the computational point of view. Usually, these algorithms first find the convex hull defined by the observed data and then fit a minimum volume simplex to it. Aiming at a lower computational complexity, some algorithms such as the vertex component analysis (VCA) [44], the pixel purity index (PPI) [42], and the N-FINDR [45] still find the minimum volume simplex containing the data cloud, but they assume the presence in the data of at least one pure pixel of each endmember. This is a strong requisite that may not hold in some data sets. In any case, these algorithms find the set of most pure pixels in the data. Hyperspectral sensors collects spatial images over many narrow contiguous bands, yielding large amounts of data. For this reason, very often, the processing of hyperspectral data, included unmixing, is preceded by a dimensionality reduction step to reduce computational complexity and to improve the signal-to-noise ratio (SNR). Principal component analysis (PCA) [46], maximum noise fraction (MNF) [47], and singular value decomposition (SVD) [48] are three well-known projection techniques widely used in remote sensing in general and in unmixing in particular. The newly introduced method [49] exploits the structure of hyperspectral mixtures, namely the fact that spectral vectors are nonnegative. The computational complexity associated with these techniques is an obstacle to real-time implementations. To overcome this problem, band selection [50] and non-statistical [51] algorithms have been introduced. This chapter addresses hyperspectral data source dependence and its impact on ICA and IFA performances. The study consider simulated and real data and is based on mutual information minimization. Hyperspectral observations are described by a generative model. This model takes into account the degradation mechanisms normally found in hyperspectral applications—namely, signature variability [52–54], abundance constraints, topography modulation, and system noise. The computation of mutual information is based on fitting mixtures of Gaussians (MOG) to data. The MOG parameters (number of components, means, covariances, and weights) are inferred using the minimum description length (MDL) based algorithm [55]. We study the behavior of the mutual information as a function of the unmixing matrix. The conclusion is that the unmixing matrix minimizing the mutual information might be very far from the true one. Nevertheless, some abundance fractions might be well separated, mainly in the presence of strong signature variability, a large number of endmembers, and high SNR. We end this chapter by sketching a new methodology to blindly unmix hyperspectral data, where abundance fractions are modeled as a mixture of Dirichlet sources. This model enforces positivity and constant sum sources (full additivity) constraints. The mixing matrix is inferred by an expectation-maximization (EM)-type algorithm. This approach is in the vein of references 39 and 56, replacing independent sources represented by MOG with mixture of Dirichlet sources. Compared with the geometric-based approaches, the advantage of this model is that there is no need to have pure pixels in the observations. The chapter is organized as follows. Section 6.2 presents a spectral radiance model and formulates the spectral unmixing as a linear problem accounting for abundance constraints, signature variability, topography modulation, and system noise. Section 6.3 presents a brief resume of ICA and IFA algorithms. Section 6.4 illustrates the performance of IFA and of some well-known ICA algorithms with experimental data. Section 6.5 studies the ICA and IFA limitations in unmixing hyperspectral data. Section 6.6 presents results of ICA based on real data. Section 6.7 describes the new blind unmixing scheme and some illustrative examples. Section 6.8 concludes with some remarks.

Vertex component analysis: a geometric-based approach to unmix hyperspectral data

Hyperspectral remote sensing exploits the electromagnetic scattering patterns of the different materials at specific wavelengths [2, 3]. Hyperspectral sensors have been developed to sample the scattered portion of the electromagnetic spectrum extending from the visible region through the near-infrared and mid-infrared, in hundreds of narrow contiguous bands [4, 5]. The number and variety of potential civilian and military applications of hyperspectral remote sensing is enormous [6, 7]. Very often, the resolution cell corresponding to a single pixel in an image contains several substances (endmembers) [4]. In this situation, the scattered energy is a mixing of the endmember spectra. A challenging task underlying many hyperspectral imagery applications is then decomposing a mixed pixel into a collection of reflectance spectra, called endmember signatures, and the corresponding abundance fractions [8–10]. Depending on the mixing scales at each pixel, the observed mixture is either linear or nonlinear [11, 12]. Linear mixing model holds approximately when the mixing scale is macroscopic [13] and there is negligible interaction among distinct endmembers [3, 14]. If, however, the mixing scale is microscopic (or intimate mixtures) [15, 16] and the incident solar radiation is scattered by the scene through multiple bounces involving several endmembers [17], the linear model is no longer accurate. Linear spectral unmixing has been intensively researched in the last years [9, 10, 12, 18–21]. It considers that a mixed pixel is a linear combination of endmember signatures weighted by the correspondent abundance fractions. Under this model, and assuming that the number of substances and their reflectance spectra are known, hyperspectral unmixing is a linear problem for which many solutions have been proposed (e.g., maximum likelihood estimation [8], spectral signature matching [22], spectral angle mapper [23], subspace projection methods [24,25], and constrained least squares [26]). In most cases, the number of substances and their reflectances are not known and, then, hyperspectral unmixing falls into the class of blind source separation problems [27]. Independent component analysis (ICA) has recently been proposed as a tool to blindly unmix hyperspectral data [28–31]. ICA is based on the assumption of mutually independent sources (abundance fractions), which is not the case of hyperspectral data, since the sum of abundance fractions is constant, implying statistical dependence among them. This dependence compromises ICA applicability to hyperspectral images as shown in Refs. [21, 32]. In fact, ICA finds the endmember signatures by multiplying the spectral vectors with an unmixing matrix, which minimizes the mutual information among sources. If sources are independent, ICA provides the correct unmixing, since the minimum of the mutual information is obtained only when sources are independent. This is no longer true for dependent abundance fractions. Nevertheless, some endmembers may be approximately unmixed. These aspects are addressed in Ref. [33]. Under the linear mixing model, the observations from a scene are in a simplex whose vertices correspond to the endmembers. Several approaches [34–36] have exploited this geometric feature of hyperspectral mixtures [35]. Minimum volume transform (MVT) algorithm [36] determines the simplex of minimum volume containing the data. The method presented in Ref. [37] is also of MVT type but, by introducing the notion of bundles, it takes into account the endmember variability usually present in hyperspectral mixtures. The MVT type approaches are complex from the computational point of view. Usually, these algorithms find in the first place the convex hull defined by the observed data and then fit a minimum volume simplex to it. For example, the gift wrapping algorithm [38] computes the convex hull of n data points in a d-dimensional space with a computational complexity of O(nbd=2cþ1), where bxc is the highest integer lower or equal than x and n is the number of samples. The complexity of the method presented in Ref. [37] is even higher, since the temperature of the simulated annealing algorithm used shall follow a log( ) law [39] to assure convergence (in probability) to the desired solution. Aiming at a lower computational complexity, some algorithms such as the pixel purity index (PPI) [35] and the N-FINDR [40] still find the minimum volume simplex containing the data cloud, but they assume the presence of at least one pure pixel of each endmember in the data. This is a strong requisite that may not hold in some data sets. In any case, these algorithms find the set of most pure pixels in the data. PPI algorithm uses the minimum noise fraction (MNF) [41] as a preprocessing step to reduce dimensionality and to improve the signal-to-noise ratio (SNR). The algorithm then projects every spectral vector onto skewers (large number of random vectors) [35, 42,43]. The points corresponding to extremes, for each skewer direction, are stored. A cumulative account records the number of times each pixel (i.e., a given spectral vector) is found to be an extreme. The pixels with the highest scores are the purest ones. N-FINDR algorithm [40] is based on the fact that in p spectral dimensions, the p-volume defined by a simplex formed by the purest pixels is larger than any other volume defined by any other combination of pixels. This algorithm finds the set of pixels defining the largest volume by inflating a simplex inside the data. ORA SIS [44, 45] is a hyperspectral framework developed by the U.S. Naval Research Laboratory consisting of several algorithms organized in six modules: exemplar selector, adaptative learner, demixer, knowledge base or spectral library, and spatial postrocessor. The first step consists in flat-fielding the spectra. Next, the exemplar selection module is used to select spectral vectors that best represent the smaller convex cone containing the data. The other pixels are rejected when the spectral angle distance (SAD) is less than a given thresh old. The procedure finds the basis for a subspace of a lower dimension using a modified Gram–Schmidt orthogonalizati on. The selected vectors are then projected onto this subspace and a simplex is found by an MV T pro cess. ORA SIS is oriented to real-time target detection from uncrewed air vehicles using hyperspectral data [46]. In this chapter we develop a new algorithm to unmix linear mixtures of endmember spectra. First, the algorithm determines the number of endmembers and the signal subspace using a newly developed concept [47, 48]. Second, the algorithm extracts the most pure pixels present in the data. Unlike other methods, this algorithm is completely automatic and unsupervised. To estimate the number of endmembers and the signal subspace in hyperspectral linear mixtures, the proposed scheme begins by estimating sign al and noise correlation matrices. The latter is based on multiple regression theory. The signal subspace is then identified by selectin g the set of signal eigenvalue s that best represents the data, in the least-square sense [48,49 ], we note, however, that VCA works with projected and with unprojected data. The extraction of the end members exploits two facts: (1) the endmembers are the vertices of a simplex and (2) the affine transformation of a simplex is also a simplex. As PPI and N-FIND R algorithms, VCA also assumes the presence of pure pixels in the data. The algorithm iteratively projects data on to a direction orthogonal to the subspace spanned by the endmembers already determined. The new end member signature corresponds to the extreme of the projection. The algorithm iterates until all end members are exhausted. VCA performs much better than PPI and better than or comparable to N-FI NDR; yet it has a computational complexity between on e and two orders of magnitude lower than N-FINDR. The chapter is structure d as follows. Section 19.2 describes the fundamentals of the proposed method. Section 19.3 and Section 19.4 evaluate the proposed algorithm using simulated and real data, respectively. Section 19.5 presents some concluding remarks.

Sistema localizador interior de baixo custo

Projeto para obtenção do grau de Mestre em Engenharia Informática e de Computadores

Burrows-wheeler transform in secondary memory

Master’s Thesis in Computer Engineering

A DCAP for the social and solidarity economy

This article presents a work-in-progress version of a Dublin Core Application Profile (DCAP) developed to serve the Social and Solidarity Economy (SSE). Studies revealed that this community is interested in implementing both internal interoperability between their Web platforms to build a global SSE e-marketplace, and external interoperability among their Web platforms and external ones. The Dublin Core Application Profile for Social and Solidarity Economy (DCAP-SSE) serves this purpose. SSE organisations are submerged in the market economy but they have specificities not taken into account in this economy. The DCAP-SSE integrates terms from well-known metadata schemas, Resource Description Framework (RDF) vocabularies or ontologies, in order to enhance interoperability and take advantage of the benefits of the Linked Open Data ecosystem. It also integrates terms from the new essglobal RDF vocabulary which was created with the goal to respond to the SSE-specific needs. The DCAP-SSE also integrates five new Vocabulary Encoding Schemes to be used with DCAP-SSE properties. The DCAP development was based on a method for the development of application profiles (Me4MAP). We believe that this article has an educational value since it presents the idea that it is important to base DCAP developments on a method. This article shows the main results of applying such a method.

Towards a Mobile Three-dimensional Modelling System for Underground Structures

Robotica 2012: 12th International Conference on Autonomous Robot Systems and Competitions April 11, 2012, Guimarães, Portugal

Application of Visual-Inertial SLAM for 3D Mapping of Underground Environments

The underground scenarios are one of the most challenging environments for accurate and precise 3d mapping where hostile conditions like absence of Global Positioning Systems, extreme lighting variations and geometrically smooth surfaces may be expected. So far, the state-of-the-art methods in underground modelling remain restricted to environments in which pronounced geometric features are abundant. This limitation is a consequence of the scan matching algorithms used to solve the localization and registration problems. This paper contributes to the expansion of the modelling capabilities to structures characterized by uniform geometry and smooth surfaces, as is the case of road and train tunnels. To achieve that, we combine some state of the art techniques from mobile robotics, and propose a method for 6DOF platform positioning in such scenarios, that is latter used for the environment modelling. A visual monocular Simultaneous Localization and Mapping (MonoSLAM) approach based on the Extended Kalman Filter (EKF), complemented by the introduction of inertial measurements in the prediction step, allows our system to localize himself over long distances, using exclusively sensors carried on board a mobile platform. By feeding the Extended Kalman Filter with inertial data we were able to overcome the major problem related with MonoSLAM implementations, known as scale factor ambiguity. Despite extreme lighting variations, reliable visual features were extracted through the SIFT algorithm, and inserted directly in the EKF mechanism according to the Inverse Depth Parametrization. Through the 1-Point RANSAC (Random Sample Consensus) wrong frame-to-frame feature matches were rejected. The developed method was tested based on a dataset acquired inside a road tunnel and the navigation results compared with a ground truth obtained by post-processing a high grade Inertial Navigation System and L1/L2 RTK-GPS measurements acquired outside the tunnel. Results from the localization strategy are presented and analyzed.

Groundtruth system for underwater benchmarking

Oceans - San Diego, 2013

Multi-robot cooperative stereo for outdoor scenarios

13th International Conference on Autonomous Robot Systems (Robotica), 2013

Método de correspondência para sistemas de visão multi-câmara

Os sistemas de perceção visual são das principais fontes de informação sensorial utilizadas pelos robôs autónomos, para localização e navegação em diferentes meios de operação. O objetivo passa por obter uma grande quantidade de informação sobre o ambiente que a câmara está a visualizar, processar e extrair informação que permita realizar as tarefas de uma forma e ciente. Uma informação em particular que os sistemas de visão podem fornecer, e a informação tridimensional acerca do meio envolvente. Esta informação pode ser adquirida recorrendo a sistemas de visão monoculares ou com múltiplas câmaras. Nestes sistemas a informação tridimensional pode ser obtida recorrendo a técnica de triangulação, tirando partido do conhecimento da posição relativa entre as câmaras. No entanto, para calcular as coordenadas de um ponto tridimensional no referencial da câmara e necessário existir correspondência entre pontos comuns às imagens adquiridas pelo sistema. No caso de más correspondências a informação 3D e obtida de forma incorreta. O problema associado à correspondência de pontos pode ser agravado no caso das câmaras do sistema terem características intrínsecas diferentes nomeadamente: resolução, abertura da lente, distorção. Outros fatores como as orientações e posições das câmaras também podem condicionar a correspondência de pontos. Este trabalho incide sobre problemática de correspondência de pontos existente no processo de cálculo da informação tridimensional. A presente dissertação visa o desenvolvimento de uma abordagem de correspondência de pontos para sistemas de visão no qual é conhecida a posição relativa entre câmaras.

Energy Harvesting for Autonomous Underwater Vehicles

In this study, energy production for autonomous underwater vehicles is investigated. This project is part of a bigger project called TURTLE. The autonomous vehicles perform oceanic researches at seabed for which they are intended to be kept operational underwater for several months. In order to ful l a long-term underwater condition, powerful batteries are combined with \micro- scale" energy production on the spot. This work tends to develop a system that generates power up to a maximum of 30 W. Latter energy harvesting structure consists basically of a turbine combined with a generator and low-power electronics to adjust the achieved voltage to a required battery charger voltage. Every component is examined separately hence an optimum can be de ned for all, and subsequently also an overall optimum. Di erent design parameters as e.g. number of blades, solidity ratio and cross-section area are compared for di erent turbines, in order to see what is the most feasible type. Further, a generator is chosen by studying how ux distributions might be adjusted to low velocities, and how cogging torque can be excluded by adapted designs. Low-power electronics are con gured in order to convert and stabilize heavily varying three-phase voltages to a constant, recti ed voltage which is usable for battery storage. Clearly, di erent component parameters as maximum power and torque are matched here to increase the overall power generation. Furthermore an overall maximum power is set up for achieving a maximum power ow at load side. Due to among others typical low velocities of about 0.1 to 0.5 m/s, and constructing limits of the prototype, the vast range of components is restricted to only a few that could be used. Hence, a helical turbine is combined in a direct drive mode to a coreless-stator axial- ux permanent-magnet generator, from which the output voltage is adjusted subsequently by a recti er, impedance matching unit, upconverter circuit and an overall control unit to regulate di erent component parameters. All these electronics are combined in a closed-loop design to involve positive feedback signals. Furthermore a theoretical con guration for the TURTLE vehicle is described in this work and a solution is proposed that might be implemented, for which several design tests are performable in a future study.

Diffusion characteristics of ethylene glycol in skeletal muscle

Part of the optical clearing study in biological tissues concerns the determination of the diffusion characteristics of water and optical clearing agents in the subject tissue. Such information is sufficient to characterize the time dependence of the optical clearing mechanisms—tissue dehydration and refractive index (RI) matching. We have used a simple method based on collimated optical transmittance measurements made from muscle samples under treatment with aqueous solutions containing different concentrations of ethylene glycol (EG), to determine the diffusion time values of water and EG in skeletal muscle. By representing the estimated mean diffusion time values from each treatment as a function of agent concentration in solution, we could identify the real diffusion times for water and agent. These values allowed for the calculation of the correspondent diffusion coefficients for those fluids. With these results, we have demonstrated that the dehydration mechanism is the one that dominates optical clearing in the first minute of treatment, while the RI matching takes over the optical clearing operations after that and remains for a longer time of treatment up to about 10 min, as we could see for EG and thin tissue samples of 0.5 mm.

The characteristic time of glucose diffusion measured for muscle tissue at optical clearing

The study of agent diffusion in biological tissues is very important to understand and characterize the optical clearing effects and mechanisms involved: tissue dehydration and refractive index matching. From measurements made to study the optical clearing, it is obvious that light scattering is reduced and that the optical properties of the tissue are controlled in the process. On the other hand, optical measurements do not allow direct determination of the diffusion properties of the agent in the tissue and some calculations are necessary to estimate those properties. This fact is imposed by the occurrence of two fluxes at optical clearing: water typically directed out of and agent directed into the tissue. When the water content in the immersion solution is approximately the same as the free water content of the tissue, a balance is established for water and the agent flux dominates. To prove this concept experimentally, we have measured the collimated transmittance of skeletal muscle samples under treatment with aqueous solutions containing different concentrations of glucose. After estimating the mean diffusion time values for each of the treatments we have represented those values as a function of glucose concentration in solution. Such a representation presents a maximum diffusion time for a water content in solution equal to the tissue free water content. Such a maximum represents the real diffusion time of glucose in the muscle and with this value we could calculate the corresponding diffusion coefficient.

Rat muscle opacity decrease due to the osmosis of a simple mixture

It is known that the fibrous structure of muscle causes light scattering. This phenomenon occurs due to the refractive index discontinuities located between muscle fibers and interstitial fluid. To study the possibility of reducing light scattering inside muscle, we consider its spectral transmittance evolution during an immersion treatment with an optical clearing solution containing ethanol, glycerol, and distilled water. Our methodology consists of registering spectral transmittance of muscle samples while immersed in that solution. With the spectral data collected, we represent the transmittance evolution for some wavelengths during the treatment applied. Additionally, we study the variations that the treatment has caused on the samples regarding tissue refractive index and mass. By analyzing microscopic photographs of tissue cross section, we can also verify changes in the internal arrangement of muscle fibers caused by the immersion treatment. Due to a mathematical model that we develop, we can explain the variations observed in the studied parameters and estimate the amount of optical clearing agent that has diffused into the tissue samples during the immersion treatment. At the end of the study, we observe and explain the improvement in tissue spectral transmittance, which is approximately 65% after 20 min.