Parallel GPU architecture for hyperspectral unmixing based on augmented Lagrangian method

Hyperspectral imaging has become one of the main topics in remote sensing applications, which comprise hundreds of spectral bands at different (almost contiguous) wavelength channels over the same area generating large data volumes comprising several GBs per flight. This high spectral resolution can be used for object detection and for discriminate between different objects based on their spectral characteristics. One of the main problems involved in hyperspectral analysis is the presence of mixed pixels, which arise when the spacial resolution of the sensor is not able to separate spectrally distinct materials. Spectral unmixing is one of the most important task for hyperspectral data exploitation. However, the unmixing algorithms can be computationally very expensive, and even high power consuming, which compromises the use in applications under on-board constraints. In recent years, graphics processing units (GPUs) have evolved into highly parallel and programmable systems. Specifically, several hyperspectral imaging algorithms have shown to be able to benefit from this hardware taking advantage of the extremely high floating-point processing performance, compact size, huge memory bandwidth, and relatively low cost of these units, which make them appealing for onboard data processing. In this paper, we propose a parallel implementation of an augmented Lagragian based method for unsupervised hyperspectral linear unmixing on GPUs using CUDA. The method called simplex identification via split augmented Lagrangian (SISAL) aims to identify the endmembers of a scene, i.e., is able to unmix hyperspectral data sets in which the pure pixel assumption is violated. The efficient implementation of SISAL method presented in this work exploits the GPU architecture at low level, using shared memory and coalesced accesses to memory.

Vertex component analysis GPU-based implementation for hyperspectral unmixing

Endmember extraction (EE) is a fundamental and crucial task in hyperspectral unmixing. Among other methods vertex component analysis ( VCA) has become a very popular and useful tool to unmix hyperspectral data. VCA is a geometrical based method that extracts endmember signatures from large hyperspectral datasets without the use of any a priori knowledge about the constituent spectra. Many Hyperspectral imagery applications require a response in real time or near-real time. Thus, to met this requirement this paper proposes a parallel implementation of VCA developed for graphics processing units. The impact on the complexity and on the accuracy of the proposed parallel implementation of VCA is examined using both simulated and real hyperspectral datasets.

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

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.

The visual image in Epiphanic Short History

The visual image is a fundamental component of epiphany, stressing its immediacy and vividness, corresponding to the enargeia of the traditional ekphrasis and also playing with cultural and social meanings. Morris Beja in his seminal book Epiphany in the Modern Novel, draws our attention to the distinction made by Joyce between the epiphany originated in a common object, in a discourse or gesture and the one arising in “a memorable phase of the mind itself”. This type materializes in the “dream-epiphany” and in the epiphany based in memory. On the other hand, Robert Langbaum in his study of the epiphanic mode, suggests that the category of “visionary epiphany” could account for the modern effect of an internally glowing vision like Blake’s “The Tyger”, which projects the vitality of a real tyger. The short story, whose length renders it a fitting genre for the use of different types of epiphany, has dealt with the impact of the visual image in this technique, to convey different effects and different aesthetic aims. This paper will present some examples of this occurrence in short stories of authors in whose work epiphany is a fundamental concept and literary technique: Walter Pater, Joseph Conrad, K. Mansfield, Clarice Lispector. Pater’s “imaginary portraits” concentrate on “priviledged moments” of the lives of the characters depicting their impressions through pictorial language; Conrad tries to show “moments of awakening” that can be remembered by the eye; Mansfield suggests that epiphany, the “glimpse”, should replace plot as an internal ordering principle of her impressionist short-stories; in C. Lispector the visualization of some situations is so aggressive that it causes nausea and a radical revelation on the protagonist’s.

Protein–polyphenol interaction on silica beads for astringency tests based on eye, photography or reflectance detection modes

Astringency is an organoleptic property of beverages and food products resulting mainly from the interaction of salivary proteins with dietary polyphenols. It is of great importance to consumers, but the only effective way of measuring it involves trained sensorial panellists, providing subjective and expensive responses. Concurrent chemical evaluations try to screen food astringency, by means of polyphenol and protein precipitation procedures, but these are far from the real human astringency sensation where not all polyphenol–protein interactions lead to the occurrence of precipitate. Here, a novel chemical approach that tries to mimic protein–polyphenol interactions in the mouth is presented to evaluate astringency. A protein, acting as a salivary protein, is attached to a solid support to which the polyphenol binds (just as happens when drinking wine), with subsequent colour alteration that is fully independent from the occurrence of precipitate. Employing this simple concept, Bovine Serum Albumin (BSA) was selected as the model salivary protein and used to cover the surface of silica beads. Tannic Acid (TA), employed as the model polyphenol, was allowed to interact with the BSA on the silica support and its adsorption to the protein was detected by reaction with Fe(III) and subsequent colour development. Quantitative data of TA in the samples were extracted by colorimetric or reflectance studies over the solid materials. The analysis was done by taking a regular picture with a digital camera, opening the image file in common software and extracting the colour coordinates from HSL (Hue, Saturation, Lightness) and RGB (Red, Green, Blue) colour model systems; linear ranges were observed from 10.6 to 106.0 μmol L−1. The latter was based on the Kubelka–Munk response, showing a linear gain with concentrations from 0.3 to 10.5 μmol L−1. In either of these two approaches, semi-quantitative estimation of TA was enabled by direct eye comparison. The correlation between the levels of adsorbed TA and the astringency of beverages was tested by using the assay to check the astringency of wines and comparing these to the response of sensorial panellists. Results of the two methods correlated well. The proposed sensor has significant potential as a robust tool for the quantitative/semi-quantitative evaluation of astringency in wine.

Decentralized Target Tracking based on Multi-Robot Cooperative Triangulation

Target tracking with bearing-only sensors is a challenging problem when the target moves dynamically in complex scenarios. Besides the partial observability of such sensors, they have limited field of views, occlusions can occur, etc. In those cases, cooperative approaches with multiple tracking robots are interesting, but the different sources of uncertain information need to be considered appropriately in order to achieve better estimates. Even though there exist probabilistic filters that can estimate the position of a target dealing with incertainties, bearing-only measurements bring usually additional problems with initialization and data association. In this paper, we propose a multi-robot triangulation method with a dynamic baseline that can triangulate bearing-only measurements in a probabilistic manner to produce 3D observations. This method is combined with a decentralized stochastic filter and used to tackle those initialization and data association issues. The approach is validated with simulations and field experiments where a team of aerial and ground robots with cameras track a dynamic target.

Vision-Based Assisted Teleoperation for Inspection Tasks with a Small ROV

It is well-known that ROVs require human intervention to guarantee the success of their assignment, as well as the equipment safety. However, as its teleoperation is quite complex to perform, there is a need for assisted teleoperation. This study aims to take on this challenge by developing vision-based assisted teleoperation maneuvers, since a standard camera is present in any ROV. The proposed approach is a visual servoing solution, that allows the user to select between several standard image processing methods and is applied to a 3-DOF ROV. The most interesting characteristic of the presented system is the exclusive use of the camera data to improve the teleoperation of an underactuated ROV. It is demonstrated through the comparison and evaluation of standard implementations of different vision methods and the execution of simple maneuvers to acquire experimental results, that the teleoperation of a small ROV can be drastically improved without the need to install additional sensors.

A learning approach to swarm-based path detection and tracking

Dissertação para obtenção do Grau de Mestre em Engenharia Electrotécnica e de Computadores

Gesture based persuasive interfaces for public ambient displays

Dissertação de Mestrado em Engenharia Informática 2º Semestre, 2011/2012

Development of a satellite based PM10 concentration product for urban areas

Dissertação para obtenção do Grau de Doutor em Engenharia do Ambiente

Hand gesture recognition for human computer interaction : a comparative study of different image features

Hand gesture recognition for human computer interaction, being a natural way of human computer interaction, is an area of active research in computer vision and machine learning. This is an area with many different possible applications, giving users a simpler and more natural way to communicate with robots/systems interfaces, without the need for extra devices. So, the primary goal of gesture recognition research is to create systems, which can identify specific human gestures and use them to convey information or for device control. For that, vision-based hand gesture interfaces require fast and extremely robust hand detection, and gesture recognition in real time. In this study we try to identify hand features that, isolated, respond better in various situations in human-computer interaction. The extracted features are used to train a set of classifiers with the help of RapidMiner in order to find the best learner. A dataset with our own gesture vocabulary consisted of 10 gestures, recorded from 20 users was created for later processing. Experimental results show that the radial signature and the centroid distance are the features that when used separately obtain better results, with an accuracy of 91% and 90,1% respectively obtained with a Neural Network classifier. These to methods have also the advantage of being simple in terms of computational complexity, which make them good candidates for real-time hand gesture recognition.

Exploring TM image texture and its relationships with biomass estimation in Rondônia, Brazilian Amazon

Many texture measures have been developed and used for improving land-cover classification accuracy, but rarely has research examined the role of textures in improving the performance of aboveground biomass estimations. The relationship between texture and biomass is poorly understood. This paper used Landsat Thematic Mapper (TM) data to explore relationships between TM image textures and aboveground biomass in Rondônia, Brazilian Amazon. Eight grey level co-occurrence matrix (GLCM) based texture measures (i.e., mean, variance, homogeneity, contrast, dissimilarity, entropy, second moment, and correlation), associated with seven different window sizes (5x5, 7x7, 9x9, 11x11, 15x15, 19x19, and 25x25), and five TM bands (TM 2, 3, 4, 5, and 7) were analyzed. Pearson's correlation coefficient was used to analyze texture and biomass relationships. This research indicates that most textures are weakly correlated with successional vegetation biomass, but some textures are significantly correlated with mature forest biomass. In contrast, TM spectral signatures are significantly correlated with successional vegetation biomass, but weakly correlated with mature forest biomass. Our findings imply that textures may be critical in improving mature forest biomass estimation, but relatively less important for successional vegetation biomass estimation.

Land cover classification of Lago Grande de Curuai floodplain (Amazon, Brazil) using multi-sensor and image fusion techniques

Given the limitations of different types of remote sensing images, automated land-cover classifications of the Amazon várzea may yield poor accuracy indexes. One way to improve accuracy is through the combination of images from different sensors, by either image fusion or multi-sensor classifications. Therefore, the objective of this study was to determine which classification method is more efficient in improving land cover classification accuracies for the Amazon várzea and similar wetland environments - (a) synthetically fused optical and SAR images or (b) multi-sensor classification of paired SAR and optical images. Land cover classifications based on images from a single sensor (Landsat TM or Radarsat-2) are compared with multi-sensor and image fusion classifications. Object-based image analyses (OBIA) and the J.48 data-mining algorithm were used for automated classification, and classification accuracies were assessed using the kappa index of agreement and the recently proposed allocation and quantity disagreement measures. Overall, optical-based classifications had better accuracy than SAR-based classifications. Once both datasets were combined using the multi-sensor approach, there was a 2% decrease in allocation disagreement, as the method was able to overcome part of the limitations present in both images. Accuracy decreased when image fusion methods were used, however. We therefore concluded that the multi-sensor classification method is more appropriate for classifying land cover in the Amazon várzea.

Fluorescence-based approaches towards the assessment of structural and functional alterations in lysosomes and vacuoles induced by lactoferrin and acetic acid

Dissertação de mestrado em Biofísica e Bionanossistemas