Matching Items (11)
Filtering by
- All Subjects: Computer vision
- All Subjects: Consensus
- Creators: Spanias, Andreas
Description
Distributed estimation uses many inexpensive sensors to compose an accurate estimate of a given parameter. It is frequently implemented using wireless sensor networks. There have been several studies on optimizing power allocation in wireless sensor networks used for distributed estimation, the vast majority of which assume linear radio-frequency amplifiers. Linear amplifiers are inherently inefficient, so in this dissertation nonlinear amplifiers are examined to gain efficiency while operating distributed sensor networks. This research presents a method to boost efficiency by operating the amplifiers in the nonlinear region of operation. Operating amplifiers nonlinearly presents new challenges. First, nonlinear amplifier characteristics change across manufacturing process variation, temperature, operating voltage, and aging. Secondly, the equations conventionally used for estimators and performance expectations in linear amplify-and-forward systems fail. To compensate for the first challenge, predistortion is utilized not to linearize amplifiers but rather to force them to fit a common nonlinear limiting amplifier model close to the inherent amplifier performance. This minimizes the power impact and the training requirements for predistortion. Second, new estimators are required that account for transmitter nonlinearity. This research derives analytically and confirms via simulation new estimators and performance expectation equations for use in nonlinear distributed estimation. An additional complication when operating nonlinear amplifiers in a wireless environment is the influence of varied and potentially unknown channel gains. The impact of these varied gains and both measurement and channel noise sources on estimation performance are analyzed in this paper. Techniques for minimizing the estimate variance are developed. It is shown that optimizing transmitter power allocation to minimize estimate variance for the most-compressed parameter measurement is equivalent to the problem for linear sensors. Finally, a method for operating distributed estimation in a multipath environment is presented that is capable of developing robust estimates for a wide range of Rician K-factors. This dissertation demonstrates that implementing distributed estimation using nonlinear sensors can boost system efficiency and is compatible with existing techniques from the literature for boosting efficiency at the system level via sensor power allocation. Nonlinear transmitters work best when channel gains are known and channel noise and receiver noise levels are low.
ContributorsSantucci, Robert (Author) / Spanias, Andreas (Thesis advisor) / Tepedelenlioðlu, Cihan (Committee member) / Bakkaloglu, Bertan (Committee member) / Tsakalis, Kostas (Committee member) / Arizona State University (Publisher)
Created2013
Description
Image understanding has been playing an increasingly crucial role in vision applications. Sparse models form an important component in image understanding, since the statistics of natural images reveal the presence of sparse structure. Sparse methods lead to parsimonious models, in addition to being efficient for large scale learning. In sparse modeling, data is represented as a sparse linear combination of atoms from a "dictionary" matrix. This dissertation focuses on understanding different aspects of sparse learning, thereby enhancing the use of sparse methods by incorporating tools from machine learning. With the growing need to adapt models for large scale data, it is important to design dictionaries that can model the entire data space and not just the samples considered. By exploiting the relation of dictionary learning to 1-D subspace clustering, a multilevel dictionary learning algorithm is developed, and it is shown to outperform conventional sparse models in compressed recovery, and image denoising. Theoretical aspects of learning such as algorithmic stability and generalization are considered, and ensemble learning is incorporated for effective large scale learning. In addition to building strategies for efficiently implementing 1-D subspace clustering, a discriminative clustering approach is designed to estimate the unknown mixing process in blind source separation. By exploiting the non-linear relation between the image descriptors, and allowing the use of multiple features, sparse methods can be made more effective in recognition problems. The idea of multiple kernel sparse representations is developed, and algorithms for learning dictionaries in the feature space are presented. Using object recognition experiments on standard datasets it is shown that the proposed approaches outperform other sparse coding-based recognition frameworks. Furthermore, a segmentation technique based on multiple kernel sparse representations is developed, and successfully applied for automated brain tumor identification. Using sparse codes to define the relation between data samples can lead to a more robust graph embedding for unsupervised clustering. By performing discriminative embedding using sparse coding-based graphs, an algorithm for measuring the glomerular number in kidney MRI images is developed. Finally, approaches to build dictionaries for local sparse coding of image descriptors are presented, and applied to object recognition and image retrieval.
ContributorsJayaraman Thiagarajan, Jayaraman (Author) / Spanias, Andreas (Thesis advisor) / Frakes, David (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2013
Description
As a promising solution to the problem of acquiring and storing large amounts of image and video data, spatial-multiplexing camera architectures have received lot of attention in the recent past. Such architectures have the attractive feature of combining a two-step process of acquisition and compression of pixel measurements in a conventional camera, into a single step. A popular variant is the single-pixel camera that obtains measurements of the scene using a pseudo-random measurement matrix. Advances in compressive sensing (CS) theory in the past decade have supplied the tools that, in theory, allow near-perfect reconstruction of an image from these measurements even for sub-Nyquist sampling rates. However, current state-of-the-art reconstruction algorithms suffer from two drawbacks -- They are (1) computationally very expensive and (2) incapable of yielding high fidelity reconstructions for high compression ratios. In computer vision, the final goal is usually to perform an inference task using the images acquired and not signal recovery. With this motivation, this thesis considers the possibility of inference directly from compressed measurements, thereby obviating the need to use expensive reconstruction algorithms. It is often the case that non-linear features are used for inference tasks in computer vision. However, currently, it is unclear how to extract such features from compressed measurements. Instead, using the theoretical basis provided by the Johnson-Lindenstrauss lemma, discriminative features using smashed correlation filters are derived and it is shown that it is indeed possible to perform reconstruction-free inference at high compression ratios with only a marginal loss in accuracy. As a specific inference problem in computer vision, face recognition is considered, mainly beyond the visible spectrum such as in the short wave infra-red region (SWIR), where sensors are expensive.
ContributorsLohit, Suhas Anand (Author) / Turaga, Pavan (Thesis advisor) / Spanias, Andreas (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2015
Description
Fully distributed wireless sensor networks (WSNs) without fusion center have advantages such as scalability in network size and energy efficiency in communications. Each sensor shares its data only with neighbors and then achieves global consensus quantities by in-network processing. This dissertation considers robust distributed parameter estimation methods, seeking global consensus on parameters of adaptive learning algorithms and statistical quantities.
Diffusion adaptation strategy with nonlinear transmission is proposed. The nonlinearity was motivated by the necessity for bounded transmit power, as sensors need to iteratively communicate each other energy-efficiently. Despite the nonlinearity, it is shown that the algorithm performs close to the linear case with the added advantage of power savings. This dissertation also discusses convergence properties of the algorithm in the mean and the mean-square sense.
Often, average is used to measure central tendency of sensed data over a network. When there are outliers in the data, however, average can be highly biased. Alternative choices of robust metrics against outliers are median, mode, and trimmed mean. Quantiles generalize the median, and they also can be used for trimmed mean. Consensus-based distributed quantile estimation algorithm is proposed and applied for finding trimmed-mean, median, maximum or minimum values, and identification of outliers through simulation. It is shown that the estimated quantities are asymptotically unbiased and converges toward the sample quantile in the mean-square sense. Step-size sequences with proper decay rates are also discussed for convergence analysis.
Another measure of central tendency is a mode which represents the most probable value and also be robust to outliers and other contaminations in data. The proposed distributed mode estimation algorithm achieves a global mode by recursively shifting conditional mean of the measurement data until it converges to stationary points of estimated density function. It is also possible to estimate the mode by utilizing grid vector as well as kernel density estimator. The densities are estimated at each grid point, while the points are updated until they converge to a global mode.
Diffusion adaptation strategy with nonlinear transmission is proposed. The nonlinearity was motivated by the necessity for bounded transmit power, as sensors need to iteratively communicate each other energy-efficiently. Despite the nonlinearity, it is shown that the algorithm performs close to the linear case with the added advantage of power savings. This dissertation also discusses convergence properties of the algorithm in the mean and the mean-square sense.
Often, average is used to measure central tendency of sensed data over a network. When there are outliers in the data, however, average can be highly biased. Alternative choices of robust metrics against outliers are median, mode, and trimmed mean. Quantiles generalize the median, and they also can be used for trimmed mean. Consensus-based distributed quantile estimation algorithm is proposed and applied for finding trimmed-mean, median, maximum or minimum values, and identification of outliers through simulation. It is shown that the estimated quantities are asymptotically unbiased and converges toward the sample quantile in the mean-square sense. Step-size sequences with proper decay rates are also discussed for convergence analysis.
Another measure of central tendency is a mode which represents the most probable value and also be robust to outliers and other contaminations in data. The proposed distributed mode estimation algorithm achieves a global mode by recursively shifting conditional mean of the measurement data until it converges to stationary points of estimated density function. It is also possible to estimate the mode by utilizing grid vector as well as kernel density estimator. The densities are estimated at each grid point, while the points are updated until they converge to a global mode.
ContributorsLee, Jongmin (Electrical engineer) (Author) / Tepedelenlioğlu, Cihan (Thesis advisor) / Spanias, Andreas (Thesis advisor) / Tsakalis, Konstantinos (Committee member) / Reisslein, Martin (Committee member) / Arizona State University (Publisher)
Created2017
Description
Sense of Community is related to numerous positive outcomes for university students. The purpose of this study was to explore sense of community amongst low income students who received a last dollar scholarship. This study also sought to understand how students define community and how they interact with communities from their past (before university), present (since they started college), and how they envision their future community involvement after graduation. Through purposive sampling, six low income Arizona State University students were selected based on similar characteristics. The scholarship that they belong to selects them based on financial need, integrity, and prolonged commitment to community service. Using a qualitative narrative inquiry, I interviewed participants about their understanding and experiences with communities. Interviews were audio recorded and transcribed verbatim for analysis. Based on the analysis, I identified three major themes: community as construction, community as nonlinear, and community as intersectional. Drawing from participants' definitions and experiences of community, I argue that community is a construction. In other words, individuals create their own constructions of community, and their actions vary based on that construction. Participants also experience their communities intersectionally, that is individual's experience their communities as coexisting and through multiple community perspectives, rather than as a single stand-alone entity. Finally, community does not exist as part of a linear time paradigm. Instead community is experienced in terms of relevance to the individual in creating meaning from that community. In addition to the above themes, I also examined participant perspectives of ASU as a community. Based on this research, I recommend that a platform be provided for students to engage in a dialogue about their understanding of community and interactions with communities. Moreover, I suggest researchers utilize intersectionality, constructionism, and non-linear time to frame future research on sense of community. This research is significant because it helps us understand student engagement, and offers a framework through which universities can provide students an opportunity to better understand their own sense of community.
ContributorsWhite, Misha Alexsandra (Author) / Foroughi-Mobarakeh, Behrang (Thesis director) / Legg, Walter Eric (Committee member) / School of Community Resources and Development (Contributor) / School of Social Transformation (Contributor) / Barrett, The Honors College (Contributor)
Created2017-05
Description
Distributed wireless sensor networks (WSNs) have attracted researchers recently due to their advantages such as low power consumption, scalability and robustness to link failures. In sensor networks with no fusion center, consensus is a process where
all the sensors in the network achieve global agreement using only local transmissions. In this dissertation, several consensus and consensus-based algorithms in WSNs are studied.
Firstly, a distributed consensus algorithm for estimating the maximum and minimum value of the initial measurements in a sensor network in the presence of communication noise is proposed. In the proposed algorithm, a soft-max approximation together with a non-linear average consensus algorithm is used. A design parameter controls the trade-off between the soft-max error and convergence speed. An analysis of this trade-off gives guidelines towards how to choose the design parameter for the max estimate. It is also shown that if some prior knowledge of the initial measurements is available, the consensus process can be accelerated.
Secondly, a distributed system size estimation algorithm is proposed. The proposed algorithm is based on distributed average consensus and L2 norm estimation. Different sources of error are explicitly discussed, and the distribution of the final estimate is derived. The CRBs for system size estimator with average and max consensus strategies are also considered, and different consensus based system size estimation approaches are compared.
Then, a consensus-based network center and radius estimation algorithm is described. The center localization problem is formulated as a convex optimization problem with a summation form by using soft-max approximation with exponential functions. Distributed optimization methods such as stochastic gradient descent and diffusion adaptation are used to estimate the center. Then, max consensus is used to compute the radius of the network area.
Finally, two average consensus based distributed estimation algorithms are introduced: distributed degree distribution estimation algorithm and algorithm for tracking the dynamics of the desired parameter. Simulation results for all proposed algorithms are provided.
all the sensors in the network achieve global agreement using only local transmissions. In this dissertation, several consensus and consensus-based algorithms in WSNs are studied.
Firstly, a distributed consensus algorithm for estimating the maximum and minimum value of the initial measurements in a sensor network in the presence of communication noise is proposed. In the proposed algorithm, a soft-max approximation together with a non-linear average consensus algorithm is used. A design parameter controls the trade-off between the soft-max error and convergence speed. An analysis of this trade-off gives guidelines towards how to choose the design parameter for the max estimate. It is also shown that if some prior knowledge of the initial measurements is available, the consensus process can be accelerated.
Secondly, a distributed system size estimation algorithm is proposed. The proposed algorithm is based on distributed average consensus and L2 norm estimation. Different sources of error are explicitly discussed, and the distribution of the final estimate is derived. The CRBs for system size estimator with average and max consensus strategies are also considered, and different consensus based system size estimation approaches are compared.
Then, a consensus-based network center and radius estimation algorithm is described. The center localization problem is formulated as a convex optimization problem with a summation form by using soft-max approximation with exponential functions. Distributed optimization methods such as stochastic gradient descent and diffusion adaptation are used to estimate the center. Then, max consensus is used to compute the radius of the network area.
Finally, two average consensus based distributed estimation algorithms are introduced: distributed degree distribution estimation algorithm and algorithm for tracking the dynamics of the desired parameter. Simulation results for all proposed algorithms are provided.
ContributorsZhang, Sai (Electrical engineer) (Author) / Tepedelenlioğlu, Cihan (Thesis advisor) / Spanias, Andreas (Thesis advisor) / Tsakalis, Kostas (Committee member) / Bliss, Daniel (Committee member) / Arizona State University (Publisher)
Created2017
Description
Using stereo vision for 3D reconstruction and depth estimation has become a popular and promising research area as it has a simple setup with passive cameras and relatively efficient processing procedure. The work in this dissertation focuses on locally adaptive stereo vision methods and applications to different imaging setups and image scenes.
Solder ball height and substrate coplanarity inspection is essential to the detection of potential connectivity issues in semi-conductor units. Current ball height and substrate coplanarity inspection tools are expensive and slow, which makes them difficult to use in a real-time manufacturing setting. In this dissertation, an automatic, stereo vision based, in-line ball height and coplanarity inspection method is presented. The proposed method includes an imaging setup together with a computer vision algorithm for reliable, in-line ball height measurement. The imaging setup and calibration, ball height estimation and substrate coplanarity calculation are presented with novel stereo vision methods. The results of the proposed method are evaluated in a measurement capability analysis (MCA) procedure and compared with the ground-truth obtained by an existing laser scanning tool and an existing confocal inspection tool. The proposed system outperforms existing inspection tools in terms of accuracy and stability.
In a rectified stereo vision system, stereo matching methods can be categorized into global methods and local methods. Local stereo methods are more suitable for real-time processing purposes with competitive accuracy as compared with global methods. This work proposes a stereo matching method based on sparse locally adaptive cost aggregation. In order to reduce outlier disparity values that correspond to mis-matches, a novel sparse disparity subset selection method is proposed by assigning a significance status to candidate disparity values, and selecting the significant disparity values adaptively. An adaptive guided filtering method using the disparity subset for refined cost aggregation and disparity calculation is demonstrated. The proposed stereo matching algorithm is tested on the Middlebury and the KITTI stereo evaluation benchmark images. A performance analysis of the proposed method in terms of the I0 norm of the disparity subset is presented to demonstrate the achieved efficiency and accuracy.
Solder ball height and substrate coplanarity inspection is essential to the detection of potential connectivity issues in semi-conductor units. Current ball height and substrate coplanarity inspection tools are expensive and slow, which makes them difficult to use in a real-time manufacturing setting. In this dissertation, an automatic, stereo vision based, in-line ball height and coplanarity inspection method is presented. The proposed method includes an imaging setup together with a computer vision algorithm for reliable, in-line ball height measurement. The imaging setup and calibration, ball height estimation and substrate coplanarity calculation are presented with novel stereo vision methods. The results of the proposed method are evaluated in a measurement capability analysis (MCA) procedure and compared with the ground-truth obtained by an existing laser scanning tool and an existing confocal inspection tool. The proposed system outperforms existing inspection tools in terms of accuracy and stability.
In a rectified stereo vision system, stereo matching methods can be categorized into global methods and local methods. Local stereo methods are more suitable for real-time processing purposes with competitive accuracy as compared with global methods. This work proposes a stereo matching method based on sparse locally adaptive cost aggregation. In order to reduce outlier disparity values that correspond to mis-matches, a novel sparse disparity subset selection method is proposed by assigning a significance status to candidate disparity values, and selecting the significant disparity values adaptively. An adaptive guided filtering method using the disparity subset for refined cost aggregation and disparity calculation is demonstrated. The proposed stereo matching algorithm is tested on the Middlebury and the KITTI stereo evaluation benchmark images. A performance analysis of the proposed method in terms of the I0 norm of the disparity subset is presented to demonstrate the achieved efficiency and accuracy.
ContributorsLi, Jinjin (Author) / Karam, Lina (Thesis advisor) / Chakrabarti, Chaitali (Committee member) / Patel, Nital (Committee member) / Spanias, Andreas (Committee member) / Arizona State University (Publisher)
Created2017
Description
Computer vision is becoming an essential component of embedded system applications such as smartphones, wearables, autonomous systems and internet-of-things (IoT). These applications are generally deployed into environments with limited energy, memory bandwidth and computational resources. This trend is driving the development of energy-effi cient image processing solutions from sensing to computation. In this thesis, diff erent alternatives are explored to implement energy-efficient computer vision systems. First, I present a fi eld programmable gate array (FPGA) implementation of an adaptive subsampling algorithm for region-of-interest (ROI) -based object tracking. By implementing the computationally intensive sections of this algorithm on an FPGA, I aim to offl oad computing resources from energy-ineffi cient graphics processing units (GPUs) and/or general-purpose central processing units (CPUs). I also present a working system executing this algorithm in near real-time latency implemented on a standalone embedded device. Secondly, I present a neural network-based pipeline to improve the performance of event-based cameras in non-ideal optical conditions. Event-based cameras or dynamic vision sensors (DVS) are bio-inspired sensors that measure logarithmic per-pixel brightness changes in a scene. Their advantages include high dynamic range, low latency and ultra-low power when compared to standard frame-based cameras. Several tasks have been proposed to take advantage of these novel sensors but they rely on perfectly calibrated optical lenses that are in-focus. In this work I propose a methodto reconstruct events captured with an out-of-focus event-camera so they can be fed into an intensity reconstruction task. The network is trained with a dataset generated by simulating defocus blur in sequences from object tracking datasets such as LaSOT and OTB100. I also test the generalization performance of this network in scenes captured with a DAVIS event-based sensor equipped with an out-of-focus lens.
ContributorsTorres Muro, Victor Isaac (Author) / Jayasuriya, Suren (Thesis advisor) / Spanias, Andreas (Committee member) / Seo, Jae-Sun (Committee member) / Arizona State University (Publisher)
Created2022
Description
Over the last decade, deep neural networks also known as deep learning, combined with large databases and specialized hardware for computation, have made major strides in important areas such as computer vision, computational imaging and natural language processing. However, such frameworks currently suffer from some drawbacks. For example, it is generally not clear how the architectures are to be designed for different applications, or how the neural networks behave under different input perturbations and it is not easy to make the internal representations and parameters more interpretable. In this dissertation, I propose building constraints into feature maps, parameters and and design of algorithms involving neural networks for applications in low-level vision problems such as compressive imaging and multi-spectral image fusion, and high-level inference problems including activity and face recognition. Depending on the application, such constraints can be used to design architectures which are invariant/robust to certain nuisance factors, more efficient and, in some cases, more interpretable. Through extensive experiments on real-world datasets, I demonstrate these advantages of the proposed methods over conventional frameworks.
ContributorsLohit, Suhas Anand (Author) / Turaga, Pavan (Thesis advisor) / Spanias, Andreas (Committee member) / Li, Baoxin (Committee member) / Jayasuriya, Suren (Committee member) / Arizona State University (Publisher)
Created2019
Description
Over the past decade, machine learning research has made great strides and significant impact in several fields. Its success is greatly attributed to the development of effective machine learning algorithms like deep neural networks (a.k.a. deep learning), availability of large-scale databases and access to specialized hardware like Graphic Processing Units. When designing and training machine learning systems, researchers often assume access to large quantities of data that capture different possible variations. Variations in the data is needed to incorporate desired invariance and robustness properties in the machine learning system, especially in the case of deep learning algorithms. However, it is very difficult to gather such data in a real-world setting. For example, in certain medical/healthcare applications, it is very challenging to have access to data from all possible scenarios or with the necessary amount of variations as required to train the system. Additionally, the over-parameterized and unconstrained nature of deep neural networks can cause them to be poorly trained and in many cases over-confident which, in turn, can hamper their reliability and generalizability. This dissertation is a compendium of my research efforts to address the above challenges. I propose building invariant feature representations by wedding concepts from topological data analysis and Riemannian geometry, that automatically incorporate the desired invariance properties for different computer vision applications. I discuss how deep learning can be used to address some of the common challenges faced when working with topological data analysis methods. I describe alternative learning strategies based on unsupervised learning and transfer learning to address issues like dataset shifts and limited training data. Finally, I discuss my preliminary work on applying simple orthogonal constraints on deep learning feature representations to help develop more reliable and better calibrated models.
ContributorsSom, Anirudh (Author) / Turaga, Pavan (Thesis advisor) / Krishnamurthi, Narayanan (Committee member) / Spanias, Andreas (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2020