Image segmentation integrating colour, texture and boundary information

La tesis se centra en la Visión por Computador y, más concretamente, en la segmentación de imágenes, la cual es una de las etapas básicas en el análisis de imágenes y consiste en la división de la imagen en un conjunto de regiones visualmente distintas y uniformes considerando su intensidad, color o textura. Se propone una estrategia basada en el uso complementario de la información de región y de frontera durante el proceso de segmentación, integración que permite paliar algunos de los problemas básicos de la segmentación tradicional. La información de frontera permite inicialmente identificar el número de regiones presentes en la imagen y colocar en el interior de cada una de ellas una semilla, con el objetivo de modelar estadísticamente las características de las regiones y definir de esta forma la información de región. Esta información, conjuntamente con la información de frontera, es utilizada en la definición de una función de energía que expresa las propiedades requeridas a la segmentación deseada: uniformidad en el interior de las regiones y contraste con las regiones vecinas en los límites. Un conjunto de regiones activas inician entonces su crecimiento, compitiendo por los píxeles de la imagen, con el objetivo de optimizar la función de energía o, en otras palabras, encontrar la segmentación que mejor se adecua a los requerimientos exprsados en dicha función. Finalmente, todo esta proceso ha sido considerado en una estructura piramidal, lo que nos permite refinar progresivamente el resultado de la segmentación y mejorar su coste computacional. La estrategia ha sido extendida al problema de segmentación de texturas, lo que implica algunas consideraciones básicas como el modelaje de las regiones a partir de un conjunto de características de textura y la extracción de la información de frontera cuando la textura es presente en la imagen. Finalmente, se ha llevado a cabo la extensión a la segmentación de imágenes teniendo en cuenta las propiedades de color y textura. En este sentido, el uso conjunto de técnicas no-paramétricas de estimación de la función de densidad para la descripción del color, y de características textuales basadas en la matriz de co-ocurrencia, ha sido propuesto para modelar adecuadamente y de forma completa las regiones de la imagen. La propuesta ha sido evaluada de forma objetiva y comparada con distintas técnicas de integración utilizando imágenes sintéticas. Además, se han incluido experimentos con imágenes reales con resultados muy positivos.

A geostatistical analysis of soil, vegetation, and image data characterizing land surface variation

The elucidation of spatial variation in the landscape can indicate potential wildlife habitats or breeding sites for vectors, such as ticks or mosquitoes, which cause a range of diseases. Information from remotely sensed data could aid the delineation of vegetation distribution on the ground in areas where local knowledge is limited. The data from digital images are often difficult to interpret because of pixel-to-pixel variation, that is, noise, and complex variation at more than one spatial scale. Landsat Thematic Mapper Plus (ETM+) and Satellite Pour l'Observation de La Terre (SPOT) image data were analyzed for an area close to Douna in Mali, West Africa. The variograms of the normalized difference vegetation index (NDVI) from both types of image data were nested. The parameters of the nested variogram function from the Landsat ETM+ data were used to design the sampling for a ground survey of soil and vegetation data. Variograms of the soil and vegetation data showed that their variation was anisotropic and their scales of variation were similar to those of NDVI from the SPOT data. The short- and long-range components of variation in the SPOT data were filtered out separately by factorial kriging. The map of the short-range component appears to represent the patterns of vegetation and associated shallow slopes and drainage channels of the tiger bush system. The map of the long-range component also appeared to relate to broader patterns in the tiger bush and to gentle undulations in the topography. The results suggest that the types of image data analyzed in this study could be used to identify areas with more moisture in semiarid regions that could support wildlife and also be potential vector breeding sites.

Classification-based probabilistic modeling of texture transition for fast line search tracking and delineation

We introduce a classification-based approach to finding occluding texture boundaries. The classifier is composed of a set of weak learners, which operate on image intensity discriminative features that are defined on small patches and are fast to compute. A database that is designed to simulate digitized occluding contours of textured objects in natural images is used to train the weak learners. The trained classifier score is then used to obtain a probabilistic model for the presence of texture transitions, which can readily be used for line search texture boundary detection in the direction normal to an initial boundary estimate. This method is fast and therefore suitable for real-time and interactive applications. It works as a robust estimator, which requires a ribbon-like search region and can handle complex texture structures without requiring a large number of observations. We demonstrate results both in the context of interactive 2D delineation and of fast 3D tracking and compare its performance with other existing methods for line search boundary detection.

Image restoration for a rectangular poor-pixels detector

This paper presents a unique two-stage image restoration framework especially for further application of a novel rectangular poor-pixels detector, which, with properties of miniature size, light weight and low power consumption, has great value in the micro vision system. To meet the demand of fast processing, only a few measured images shifted up to subpixel level are needed to join the fusion operation, fewer than those required in traditional approaches. By maximum likelihood estimation with a least squares method, a preliminary restored image is linearly interpolated. After noise removal via Canny operator based level set evolution, the final high-quality restored image is achieved. Experimental results demonstrate effectiveness of the proposed framework. It is a sensible step towards subsequent image understanding and object identification.

Image fusion based on median filters and SOFM neural networks: a three-step scheme

This paper presents a new image data fusion scheme by combining median filtering with self-organizing feature map (SOFM) neural networks. The scheme consists of three steps: (1) pre-processing of the images, where weighted median filtering removes part of the noise components corrupting the image, (2) pixel clustering for each image using self-organizing feature map neural networks, and (3) fusion of the images obtained in Step (2), which suppresses the residual noise components and thus further improves the image quality. It proves that such a three-step combination offers an impressive effectiveness and performance improvement, which is confirmed by simulations involving three image sensors (each of which has a different noise structure).

Modeling camera orientation and 3D structure from a sequence of images taken by a perambulating commercial video camera

In this paper we report the degree of reliability of image sequences taken by off-the-shelf TV cameras for modeling camera rotation and reconstructing 3D structure using computer vision techniques. This is done in spite of the fact that computer vision systems usually use imaging devices that are specifically designed for the human vision. Our scenario consists of a static scene and a mobile camera moving through the scene. The scene is any long axial building dominated by features along the three principal orientations and with at least one wall containing prominent repetitive planar features such as doors, windows bricks etc. The camera is an ordinary commercial camcorder moving along the axial axis of the scene and is allowed to rotate freely within the range +/- 10 degrees in all directions. This makes it possible that the camera be held by a walking unprofessional cameraman with normal gait, or to be mounted on a mobile robot. The system has been tested successfully on sequence of images of a variety of structured, but fairly cluttered scenes taken by different walking cameramen. The potential application areas of the system include medicine, robotics and photogrammetry.

Numerical modeling of inhaled charged aerosol deposition in human airways

A new numerical modeling of inhaled charge aerosol has been developed based on a modified Weibel's model. Both the velocity profiles (slug and parabolic flows) and the particle distributions (uniform and parabolic distributions) have been considered. Inhaled particles are modeled as a dilute dispersed phase flow in which the particle motion is controlled by fluid force and external forces acting on particles. This numerical study extends the previous numerical studies by considering both space- and image-charge forces. Because of the complex computation of interacting forces due to space-charge effect, the particle-mesh (PM) method is selected to calculate these forces. In the PM technique, the charges of all particles are assigned to the space-charge field mesh, for calculating charge density. The Poisson's equation of the electrostatic potential is then solved, and the electrostatic force acting on individual particle is interpolated. It is assumed that there is no effect of humidity on charged particles. The results show that many significant factors also affect the deposition, such as the volume of particle cloud, the velocity profile and the particle distribution. This study allows a better understanding of electrostatic mechanism of aerosol transport and deposition in human airways.

Periodic time series modeling of environmental proxy records with guaranteed positive growth rate estimation

Identifying a periodic time-series model from environmental records, without imposing the positivity of the growth rate, does not necessarily respect the time order of the data observations. Consequently, subsequent observations, sampled in the environmental archive, can be inversed on the time axis, resulting in a non-physical signal model. In this paper an optimization technique with linear constraints on the signal model parameters is proposed that prevents time inversions. The activation conditions for this constrained optimization are based upon the physical constraint of the growth rate, namely, that it cannot take values smaller than zero. The actual constraints are defined for polynomials and first-order splines as basis functions for the nonlinear contribution in the distance-time relationship. The method is compared with an existing method that eliminates the time inversions, and its noise sensitivity is tested by means of Monte Carlo simulations. Finally, the usefulness of the method is demonstrated on the measurements of the vessel density, in a mangrove tree, Rhizophora mucronata, and the measurement of Mg/Ca ratios, in a bivalve, Mytilus trossulus.

Green noise or green value? Measuring the price effects of environmental certification in commercial buildings

This paper investigates the price effects of environmental certification on commercial real estate assets. It is argued that there are likely to be three main drivers of price differences between certified and non-certified buildings. First, certified buildings offer a bundle of benefits to occupiers relating to business productivity, image and occupancy costs. Second, due to these occupier benefits, certified buildings can result in higher rents and lower holding costs for investors. Third, certified buildings may require a lower risk premium. Drawing upon the CoStar database of US commercial real estate assets, hedonic regression analysis is used to measure the effect of certification on both rent and price. We first estimate the rental regression for a sample of 110 LEED and 433 Energy Star as well as several thousand benchmark buildings to compare the sample to. The results suggest that, compared to buildings in the same metropolitan region, certified buildings have a rental premium and that the more highly rated that buildings are in terms of their environmental impact, the greater the rental premium. Furthermore, based on a sample of transaction prices for 292 Energy Star and 30 LEED-certified buildings, we find price premia of 10% and 31% respectively compared to non-certified buildings in the same metropolitan area

Integrated visual vocabulary in latent Dirichlet allocation-based scene classification for IKONOS image

Scene classification based on latent Dirichlet allocation (LDA) is a more general modeling method known as a bag of visual words, in which the construction of a visual vocabulary is a crucial quantization process to ensure success of the classification. A framework is developed using the following new aspects: Gaussian mixture clustering for the quantization process, the use of an integrated visual vocabulary (IVV), which is built as the union of all centroids obtained from the separate quantization process of each class, and the usage of some features, including edge orientation histogram, CIELab color moments, and gray-level co-occurrence matrix (GLCM). The experiments are conducted on IKONOS images with six semantic classes (tree, grassland, residential, commercial/industrial, road, and water). The results show that the use of an IVV increases the overall accuracy (OA) by 11 to 12% and 6% when it is implemented on the selected and all features, respectively. The selected features of CIELab color moments and GLCM provide a better OA than the implementation over CIELab color moment or GLCM as individuals. The latter increases the OA by only ∼2 to 3%. Moreover, the results show that the OA of LDA outperforms the OA of C4.5 and naive Bayes tree by ∼20%. © 2014 Society of Photo-Optical Instrumentation Engineers (SPIE) [DOI: 10.1117/1.JRS.8.083690]

Ensemble downscaling in coupled solar wind-magnetosphere modeling for space weather forecasting

Advanced forecasting of space weather requires simulation of the whole Sun-to-Earth system, which necessitates driving magnetospheric models with the outputs from solar wind models. This presents a fundamental difficulty, as the magnetosphere is sensitive to both large-scale solar wind structures, which can be captured by solar wind models, and small-scale solar wind “noise,” which is far below typical solar wind model resolution and results primarily from stochastic processes. Following similar approaches in terrestrial climate modeling, we propose statistical “downscaling” of solar wind model results prior to their use as input to a magnetospheric model. As magnetospheric response can be highly nonlinear, this is preferable to downscaling the results of magnetospheric modeling. To demonstrate the benefit of this approach, we first approximate solar wind model output by smoothing solar wind observations with an 8 h filter, then add small-scale structure back in through the addition of random noise with the observed spectral characteristics. Here we use a very simple parameterization of noise based upon the observed probability distribution functions of solar wind parameters, but more sophisticated methods will be developed in the future. An ensemble of results from the simple downscaling scheme are tested using a model-independent method and shown to add value to the magnetospheric forecast, both improving the best estimate and quantifying the uncertainty. We suggest a number of features desirable in an operational solar wind downscaling scheme.

Modeling the observed proton aurora and ionospheric convection responses to changes in the IMF clock angle: 2. Persistence of ionospheric convection

We apply a numerical model of time-dependent ionospheric convection to two directly driven reconnection pulses during a 15-min interval of southward IMF on 26 November 2000. The model requires an input magnetopause reconnection rate variation, which is here derived from the observed variation in the upstream IMF clock angle, q. The reconnection rate is mapped to an ionospheric merging gap, the MLT extent of which is inferred from the Doppler-shifted Lyman-a emission on newly opened field lines, as observed by the FUV instrument on the IMAGE spacecraft. The model is used to reproduce a variety of features observed during this event: SuperDARN observations of the ionospheric convection pattern and transpolar voltage; FUV observations of the growth of patches of newly opened flux; FUVand in situ observations of the location of the Open-Closed field line Boundary (OCB) and a cusp ion step. We adopt a clock angle dependence of the magnetopause reconnection electric field, mapped to the ionosphere, of the form Enosin4(q/2) and estimate the peak value, Eno, by matching observed and modeled variations of both the latitude, LOCB, of the dayside OCB (as inferred from the equatorward edge of cusp proton emissions seen by FUV) and the transpolar voltage FPC (as derived using the mapped potential technique from SuperDARN HF radar data). This analysis also yields the time constant tOCB with which the open-closed boundary relaxes back toward its equilibrium configuration. For the case studied here, we find tOCB = 9.7 ± 1.3 min, consistent with previous inferences from the observed response of ionospheric flow to southward turnings of the IMF. The analysis confirms quantitatively the concepts of ionospheric flow excitation on which the model is based and explains some otherwise anomalous features of the cusp precipitation morphology.

Modeling the observed proton aurora and ionospheric convection responses to changes in the IMF clock angle: 1. Persistence of cusp proton aurora

We employ a numerical model of cusp ion precipitation and proton aurora emission to fit variations of the peak Doppler-shifted Lyman-a intensity observed on 26 November 2000 by the SI-12 channel of the FUV instrument on the IMAGE satellite. The major features of this event appeared in response to two brief swings of the interplanetary magnetic field (IMF) toward a southward orientation. We reproduce the observed spatial distributions of this emission on newly opened field lines by combining the proton emission model with a model of the response of ionospheric convection. The simulations are based on the observed variations of the solar wind proton temperature and concentration and the interplanetary magnetic field clock angle. They also allow for the efficiency, sampling rate, integration time and spatial resolution of the FUV instrument. The good match (correlation coefficient 0.91, significant at the 98% level) between observed and modeled variations confirms the time constant (about 4 min) for the rise and decay of the proton emissions predicted by the model for southward IMF conditions. The implications for the detection of pulsed magnetopause reconnection using proton aurora are discussed for a range of interplanetary conditions.

Wave spectra assimilation in typhoon wave modeling for the East China Sea

The East China Sea is a hot area for typhoon waves to occur. A wave spectra assimilation model has been developed to predict the typhoon wave more accurately and operationally. This is the first time where wave data from Taiwan have been used to predict typhoon wave along the mainland China coast. The two-dimensional spectra observed in Taiwan northeast coast modify the wave field output by SWAN model through the technology of optimal interpolation (OI) scheme. The wind field correction is not involved as it contributes less than a quarter of the correction achieved by assimilation of waves. The initialization issue for assimilation is discussed. A linear evolution law for noise in the wave field is derived from the SWAN governing equations. A two-dimensional digital low-pass filter is used to obtain the initialized wave fields. The data assimilation model is optimized during the typhoon Sinlaku. During typhoons Krosa and Morakot, data assimilation significantly improves the low frequency wave energy and wave propagation direction in Taiwan coast. For the far-field region, the assimilation model shows an expected ability of improving typhoon wave forecast as well, as data assimilation enhances the low frequency wave energy. The proportion of positive assimilation indexes is over 81% for all the periods of comparison. The paper also finds that the impact of data assimilation on the far-field region depends on the state of the typhoon developing and the swell propagation direction.

Cross-situational learning of object-word mapping using Neural Modeling Fields

The issue of how children learn the meaning of words is fundamental to developmental psychology. The recent attempts to develop or evolve efficient communication protocols among interacting robots or Virtual agents have brought that issue to a central place in more applied research fields, such as computational linguistics and neural networks, as well. An attractive approach to learning an object-word mapping is the so-called cross-situational learning. This learning scenario is based on the intuitive notion that a learner can determine the meaning of a word by finding something in common across all observed uses of that word. Here we show how the deterministic Neural Modeling Fields (NMF) categorization mechanism can be used by the learner as an efficient algorithm to infer the correct object-word mapping. To achieve that we first reduce the original on-line learning problem to a batch learning problem where the inputs to the NMF mechanism are all possible object-word associations that Could be inferred from the cross-situational learning scenario. Since many of those associations are incorrect, they are considered as clutter or noise and discarded automatically by a clutter detector model included in our NMF implementation. With these two key ingredients - batch learning and clutter detection - the NMF mechanism was capable to infer perfectly the correct object-word mapping. (C) 2009 Elsevier Ltd. All rights reserved.