Matching Items (198)
Description
Reliable extraction of human pose features that are invariant to view angle and body shape changes is critical for advancing human movement analysis. In this dissertation, the multifactor analysis techniques, including the multilinear analysis and the multifactor Gaussian process methods, have been exploited to extract such invariant pose features from video data by decomposing various key contributing factors, such as pose, view angle, and body shape, in the generation of the image observations. Experimental results have shown that the resulting pose features extracted using the proposed methods exhibit excellent invariance properties to changes in view angles and body shapes. Furthermore, using the proposed invariant multifactor pose features, a suite of simple while effective algorithms have been developed to solve the movement recognition and pose estimation problems. Using these proposed algorithms, excellent human movement analysis results have been obtained, and most of them are superior to those obtained from state-of-the-art algorithms on the same testing datasets. Moreover, a number of key movement analysis challenges, including robust online gesture spotting and multi-camera gesture recognition, have also been addressed in this research. To this end, an online gesture spotting framework has been developed to automatically detect and learn non-gesture movement patterns to improve gesture localization and recognition from continuous data streams using a hidden Markov network. In addition, the optimal data fusion scheme has been investigated for multicamera gesture recognition, and the decision-level camera fusion scheme using the product rule has been found to be optimal for gesture recognition using multiple uncalibrated cameras. Furthermore, the challenge of optimal camera selection in multi-camera gesture recognition has also been tackled. A measure to quantify the complementary strength across cameras has been proposed. Experimental results obtained from a real-life gesture recognition dataset have shown that the optimal camera combinations identified according to the proposed complementary measure always lead to the best gesture recognition results.
ContributorsPeng, Bo (Author) / Qian, Gang (Thesis advisor) / Ye, Jieping (Committee member) / Li, Baoxin (Committee member) / Spanias, Andreas (Committee member) / Arizona State University (Publisher)
Created2011
Description
With the introduction of compressed sensing and sparse representation,many image processing and computer vision problems have been looked at in a new way. Recent trends indicate that many challenging computer vision and image processing problems are being solved using compressive sensing and sparse representation algorithms. This thesis assays some applications of compressive sensing and sparse representation with regards to image enhancement, restoration and classication. The first application deals with image Super-Resolution through compressive sensing based sparse representation. A novel framework is developed for understanding and analyzing some of the implications of compressive sensing in reconstruction and recovery of an image through raw-sampled and trained dictionaries. Properties of the projection operator and the dictionary are examined and the corresponding results presented. In the second application a novel technique for representing image classes uniquely in a high-dimensional space for image classification is presented. In this method, design and implementation strategy of the image classification system through unique affine sparse codes is presented, which leads to state of the art results. This further leads to analysis of some of the properties attributed to these unique sparse codes. In addition to obtaining these codes, a strong classier is designed and implemented to boost the results obtained. Evaluation with publicly available datasets shows that the proposed method outperforms other state of the art results in image classication. The final part of the thesis deals with image denoising with a novel approach towards obtaining high quality denoised image patches using only a single image. A new technique is proposed to obtain highly correlated image patches through sparse representation, which are then subjected to matrix completion to obtain high quality image patches. Experiments suggest that there may exist a structure within a noisy image which can be exploited for denoising through a low-rank constraint.
ContributorsKulkarni, Naveen (Author) / Li, Baoxin (Thesis advisor) / Ye, Jieping (Committee member) / Sen, Arunabha (Committee member) / Arizona State University (Publisher)
Created2011
Description
The trend towards using recycled materials on new construction projects is growing as the cost for construction materials are ever increasing and the awareness of the responsibility we have to be good stewards of our environment is heightened. While recycled asphalt is sometimes used in pavements, its use as structural fill has been hindered by concern that it is susceptible to large long-term deformations (creep), preventing its use for a great many geotechnical applications. While asphalt/soil blends are often proposed as an alternative to 100% recycled asphalt fill, little data is available characterizing the geotechnical properties of recycled asphalt soil blends. In this dissertation, the geotechnical properties for five different recycled asphalt soil blends are characterized. Data includes the particle size distribution, plasticity index, creep, and shear strength for each blend. Blends with 0%, 25%, 50%, 75% and 100% recycled asphalt were tested. As the recycled asphalt material used for testing had particles sizes up to 1.5 inches, a large 18 inch diameter direct shear apparatus was used to determine the shear strength and creep characteristics of the material. The results of the testing program confirm that the creep potential of recycled asphalt is a geotechnical concern when the material is subjected to loads greater than 1500 pounds per square foot (psf). In addition, the test results demonstrate that the amount of soil blended with the recycled asphalt can greatly influence the creep and shear strength behavior of the composite material. Furthermore, there appears to be an optimal blend ratio where the composite material had better properties than either the recycled asphalt or virgin soil alone with respect to shear strength.
ContributorsSchaper, Jeffery M (Author) / Kavazanjian, Edward (Thesis advisor) / Houston, Sandra L. (Committee member) / Zapata, Claudia E (Committee member) / Arizona State University (Publisher)
Created2011
Description
In geotechnical engineering, measuring the unsaturated hydraulic conductivity of fine grained soils can be time consuming and tedious. The various applications that require knowledge of the unsaturated hydraulic conductivity function are great, and in geotechnical engineering, they range from modeling seepage through landfill covers to determining infiltration of water under a building slab. The unsaturated hydraulic conductivity function can be measured using various direct and indirect techniques. The instantaneous profile method has been found to be the most promising unsteady state method for measuring the unsaturated hydraulic conductivity function for fine grained soils over a wide range of suction values. The instantaneous profile method can be modified by using different techniques to measure suction and water content and also through the way water is introduced or removed from the soil profile. In this study, the instantaneous profile method was modified by creating duplicate soil samples compacted into cylindrical tubes at two different water contents. The techniques used in the duplicate method to measure the water content and matric suction included volumetric moisture probes, manual water content measurements, and filter paper tests. The experimental testing conducted in this study provided insight into determining the unsaturated hydraulic conductivity using the instantaneous profile method for a sandy clay soil and recommendations are provided for further evaluation. Overall, this study has demonstrated that the presence of cracks has no significant impact on the hydraulic behavior of soil in high suction ranges. The results of this study do not examine the behavior of cracked soil unsaturated hydraulic conductivity at low suction and at moisture contents near saturation.
ContributorsJacquemin, Sean Christopher (Author) / Zapata, Claudia (Thesis advisor) / Houston, Sandra (Committee member) / Kavazanjian, Edward (Committee member) / Arizona State University (Publisher)
Created2011
Description
Genes have widely different pertinences to the etiology and pathology of diseases. Thus, they can be ranked according to their disease-significance on a genomic scale, which is the subject of gene prioritization. Given a set of genes known to be related to a disease, it is reasonable to use them as a basis to determine the significance of other candidate genes, which will then be ranked based on the association they exhibit with respect to the given set of known genes. Experimental and computational data of various kinds have different reliability and relevance to a disease under study. This work presents a gene prioritization method based on integrated biological networks that incorporates and models the various levels of relevance and reliability of diverse sources. The method is shown to achieve significantly higher performance as compared to two well-known gene prioritization algorithms. Essentially, no bias in the performance was seen as it was applied to diseases of diverse ethnology, e.g., monogenic, polygenic and cancer. The method was highly stable and robust against significant levels of noise in the data. Biological networks are often sparse, which can impede the operation of associationbased gene prioritization algorithms such as the one presented here from a computational perspective. As a potential approach to overcome this limitation, we explore the value that transcription factor binding sites can have in elucidating suitable targets. Transcription factors are needed for the expression of most genes, especially in higher organisms and hence genes can be associated via their genetic regulatory properties. While each transcription factor recognizes specific DNA sequence patterns, such patterns are mostly unknown for many transcription factors. Even those that are known are inconsistently reported in the literature, implying a potentially high level of inaccuracy. We developed computational methods for prediction and improvement of transcription factor binding patterns. Tests performed on the improvement method by employing synthetic patterns under various conditions showed that the method is very robust and the patterns produced invariably converge to nearly identical series of patterns. Preliminary tests were conducted to incorporate knowledge from transcription factor binding sites into our networkbased model for prioritization, with encouraging results. Genes have widely different pertinences to the etiology and pathology of diseases. Thus, they can be ranked according to their disease-significance on a genomic scale, which is the subject of gene prioritization. Given a set of genes known to be related to a disease, it is reasonable to use them as a basis to determine the significance of other candidate genes, which will then be ranked based on the association they exhibit with respect to the given set of known genes. Experimental and computational data of various kinds have different reliability and relevance to a disease under study. This work presents a gene prioritization method based on integrated biological networks that incorporates and models the various levels of relevance and reliability of diverse sources. The method is shown to achieve significantly higher performance as compared to two well-known gene prioritization algorithms. Essentially, no bias in the performance was seen as it was applied to diseases of diverse ethnology, e.g., monogenic, polygenic and cancer. The method was highly stable and robust against significant levels of noise in the data. Biological networks are often sparse, which can impede the operation of associationbased gene prioritization algorithms such as the one presented here from a computational perspective. As a potential approach to overcome this limitation, we explore the value that transcription factor binding sites can have in elucidating suitable targets. Transcription factors are needed for the expression of most genes, especially in higher organisms and hence genes can be associated via their genetic regulatory properties. While each transcription factor recognizes specific DNA sequence patterns, such patterns are mostly unknown for many transcription factors. Even those that are known are inconsistently reported in the literature, implying a potentially high level of inaccuracy. We developed computational methods for prediction and improvement of transcription factor binding patterns. Tests performed on the improvement method by employing synthetic patterns under various conditions showed that the method is very robust and the patterns produced invariably converge to nearly identical series of patterns. Preliminary tests were conducted to incorporate knowledge from transcription factor binding sites into our networkbased model for prioritization, with encouraging results. To validate these approaches in a disease-specific context, we built a schizophreniaspecific network based on the inferred associations and performed a comprehensive prioritization of human genes with respect to the disease. These results are expected to be validated empirically, but computational validation using known targets are very positive.
ContributorsLee, Jang (Author) / Gonzalez, Graciela (Thesis advisor) / Ye, Jieping (Committee member) / Davulcu, Hasan (Committee member) / Gallitano-Mendel, Amelia (Committee member) / Arizona State University (Publisher)
Created2011
Description
Bridging semantic gap is one of the fundamental problems in multimedia computing and pattern recognition. The challenge of associating low-level signal with their high-level semantic interpretation is mainly due to the fact that semantics are often conveyed implicitly in a context, relying on interactions among multiple levels of concepts or low-level data entities. Also, additional domain knowledge may often be indispensable for uncovering the underlying semantics, but in most cases such domain knowledge is not readily available from the acquired media streams. Thus, making use of various types of contextual information and leveraging corresponding domain knowledge are vital for effectively associating high-level semantics with low-level signals with higher accuracies in multimedia computing problems. In this work, novel computational methods are explored and developed for incorporating contextual information/domain knowledge in different forms for multimedia computing and pattern recognition problems. Specifically, a novel Bayesian approach with statistical-sampling-based inference is proposed for incorporating a special type of domain knowledge, spatial prior for the underlying shapes; cross-modality correlations via Kernel Canonical Correlation Analysis is explored and the learnt space is then used for associating multimedia contents in different forms; model contextual information as a graph is leveraged for regulating interactions among high-level semantic concepts (e.g., category labels), low-level input signal (e.g., spatial/temporal structure). Four real-world applications, including visual-to-tactile face conversion, photo tag recommendation, wild web video classification and unconstrained consumer video summarization, are selected to demonstrate the effectiveness of the approaches. These applications range from classic research challenges to emerging tasks in multimedia computing. Results from experiments on large-scale real-world data with comparisons to other state-of-the-art methods and subjective evaluations with end users confirmed that the developed approaches exhibit salient advantages, suggesting that they are promising for leveraging contextual information/domain knowledge for a wide range of multimedia computing and pattern recognition problems.
ContributorsWang, Zhesheng (Author) / Li, Baoxin (Thesis advisor) / Sundaram, Hari (Committee member) / Qian, Gang (Committee member) / Ye, Jieping (Committee member) / Arizona State University (Publisher)
Created2011
Description
The theme for this work is the development of fast numerical algorithms for sparse optimization as well as their applications in medical imaging and source localization using sensor array processing. Due to the recently proposed theory of Compressive Sensing (CS), the $\ell_1$ minimization problem attracts more attention for its ability to exploit sparsity. Traditional interior point methods encounter difficulties in computation for solving the CS applications. In the first part of this work, a fast algorithm based on the augmented Lagrangian method for solving the large-scale TV-$\ell_1$ regularized inverse problem is proposed. Specifically, by taking advantage of the separable structure, the original problem can be approximated via the sum of a series of simple functions with closed form solutions. A preconditioner for solving the block Toeplitz with Toeplitz block (BTTB) linear system is proposed to accelerate the computation. An in-depth discussion on the rate of convergence and the optimal parameter selection criteria is given. Numerical experiments are used to test the performance and the robustness of the proposed algorithm to a wide range of parameter values. Applications of the algorithm in magnetic resonance (MR) imaging and a comparison with other existing methods are included. The second part of this work is the application of the TV-$\ell_1$ model in source localization using sensor arrays. The array output is reformulated into a sparse waveform via an over-complete basis and study the $\ell_p$-norm properties in detecting the sparsity. An algorithm is proposed for minimizing a non-convex problem. According to the results of numerical experiments, the proposed algorithm with the aid of the $\ell_p$-norm can resolve closely distributed sources with higher accuracy than other existing methods.
ContributorsShen, Wei (Author) / Mittlemann, Hans D (Thesis advisor) / Renaut, Rosemary A. (Committee member) / Jackiewicz, Zdzislaw (Committee member) / Gelb, Anne (Committee member) / Ringhofer, Christian (Committee member) / Arizona State University (Publisher)
Created2011
Description
It is estimated that wind induced soil transports more than 500 x 106 metric tons of fugitive dust annually. Soil erosion has negative effects on human health, the productivity of farms, and the quality of surface waters. A variety of different polymer stabilizers are available on the market for fugitive dust control. Most of these polymer stabilizers are expensive synthetic polymer products. Their adverse effects and expense usually limits their use. Biopolymers provide a potential alternative to synthetic polymers. They can provide dust abatement by encapsulating soil particles and creating a binding network throughout the treated area. This research into the effectiveness of biopolymers for fugitive dust control involved three phases. Phase I included proof of concept tests. Phase II included carrying out the tests in a wind tunnel. Phase III consisted of conducting the experiments in the field. Proof of concept tests showed that biopolymers have the potential to reduce soil erosion and fugitive dust transport. Wind tunnel tests on two candidate biopolymers, xanthan and chitosan, showed that there is a proportional relationship between biopolymer application rates and threshold wind velocities. The wind tunnel tests also showed that xanthan gum is more successful in the field than chitosan. The field tests showed that xanthan gum was effective at controlling soil erosion. However, the chitosan field data was inconsistent with the xanthan data and field data on bare soil.
ContributorsAlsanad, Abdullah (Author) / Kavazanjian, Edward (Thesis advisor) / Edwards, David (Committee member) / Zapata, Claudia (Committee member) / Arizona State University (Publisher)
Created2011
Description
A method for evaluating the integrity of geosynthetic elements of a waste containment system subject to seismic loading is developed using a large strain finite difference numerical computer program. The method accounts for the effect of interaction between the geosynthetic elements and the overlying waste on seismic response and allows for explicit calculation of forces and strains in the geosynthetic elements. Based upon comparison of numerical results to experimental data, an elastic-perfectly plastic interface model is demonstrated to adequately reproduce the cyclic behavior of typical geomembrane-geotextile and geomembrane-geomembrane interfaces provided the appropriate interface properties are used. New constitutive models are developed for the in-plane cyclic shear behavior of textured geomembrane/geosynthetic clay liner (GMX/GCL) interfaces and GCLs. The GMX/GCL model is an empirical model and the GCL model is a kinematic hardening, isotropic softening multi yield surface plasticity model. Both new models allows for degradation in the cyclic shear resistance from a peak to a large displacement shear strength. The ability of the finite difference model to predict forces and strains in a geosynthetic element modeled as a beam element with zero moment of inertia sandwiched between two interface elements is demonstrated using hypothetical models of a heap leach pad and two typical landfill configurations. The numerical model is then used to conduct back analyses of the performance of two lined municipal solid waste (MSW) landfills subjected to strong ground motions in the Northridge earthquake. The modulus reduction "backbone curve" employed with the Masing criterion and 2% Rayleigh damping to model the cyclic behavior of MSW was established by back-analysis of the response of the Operating Industries Inc. landfill to five different earthquakes, three small magnitude nearby events and two larger magnitude distant events. The numerical back analysis was able to predict the tears observed in the Chiquita Canyon Landfill liner system after the earthquake if strain concentrations due to seams and scratches in the geomembrane are taken into account. The apparent good performance of the Lopez Canyon landfill geomembrane and the observed tension in the overlying geotextile after the Northridge event was also successfully predicted using the numerical model.
ContributorsArab, Mohamed G (Author) / Kavazanjian, Edward (Thesis advisor) / Zapata, Claudia (Committee member) / Houston, Sandra (Committee member) / Arizona State University (Publisher)
Created2011
Description
Multi-label learning, which deals with data associated with multiple labels simultaneously, is ubiquitous in real-world applications. To overcome the curse of dimensionality in multi-label learning, in this thesis I study multi-label dimensionality reduction, which extracts a small number of features by removing the irrelevant, redundant, and noisy information while considering the correlation among different labels in multi-label learning. Specifically, I propose Hypergraph Spectral Learning (HSL) to perform dimensionality reduction for multi-label data by exploiting correlations among different labels using a hypergraph. The regularization effect on the classical dimensionality reduction algorithm known as Canonical Correlation Analysis (CCA) is elucidated in this thesis. The relationship between CCA and Orthonormalized Partial Least Squares (OPLS) is also investigated. To perform dimensionality reduction efficiently for large-scale problems, two efficient implementations are proposed for a class of dimensionality reduction algorithms, including canonical correlation analysis, orthonormalized partial least squares, linear discriminant analysis, and hypergraph spectral learning. The first approach is a direct least squares approach which allows the use of different regularization penalties, but is applicable under a certain assumption; the second one is a two-stage approach which can be applied in the regularization setting without any assumption. Furthermore, an online implementation for the same class of dimensionality reduction algorithms is proposed when the data comes sequentially. A Matlab toolbox for multi-label dimensionality reduction has been developed and released. The proposed algorithms have been applied successfully in the Drosophila gene expression pattern image annotation. The experimental results on some benchmark data sets in multi-label learning also demonstrate the effectiveness and efficiency of the proposed algorithms.
ContributorsSun, Liang (Author) / Ye, Jieping (Thesis advisor) / Li, Baoxin (Committee member) / Liu, Huan (Committee member) / Mittelmann, Hans D. (Committee member) / Arizona State University (Publisher)
Created2011