Theses and Dissertations from UMD
Permanent URI for this communityhttp://hdl.handle.net/1903/2
New submissions to the thesis/dissertation collections are added automatically as they are received from the Graduate School. Currently, the Graduate School deposits all theses and dissertations from a given semester after the official graduation date. This means that there may be up to a 4 month delay in the appearance of a give thesis/dissertation in DRUM
More information is available at Theses and Dissertations at University of Maryland Libraries.
Browse
8 results
Search Results
Item DEVELOPMENT OF A COUPLED FDS MODELING AND VIDEO ANALYSIS APPROACH TO ESTIMATE THE BURNING CHARACTERISTICS OF A THIN-WALLED HUMANITARIAN SHELTER(2022) Tan, Genevieve Claire; Milke, James A.; Trouve, Arnaud; Fire Protection Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Large fires in humanitarian settlements lead to enormous losses in material, time, and resources that organizations allocate toward supporting refugee camps and displaced persons. In the absence of full-scale shelter fire experiments in humanitarian settlements, a combination of video analysis and fire modeling can be used to estimate burning characteristics of the shelter fire. A MATLAB-based image binarization method is developed to measure the flame height and structure loss over the course of fire development in footage from a shelter burn test conducted in Cox’s Bazar, Bangladesh. The conditions of the shelter fire are recreated in Fire Dynamics Simulator (FDS). Diagnostics in the FDS models provide estimates for the flame height, heat release rate, heat flux, and radiant integrated intensity in and around the shelter. The FDS models exhibit a 10-25 second delay in matching key events in the fire development timeline of the original shelter fire. Otherwise, measurements from the FDS simulations show good agreement to measurements from image processing. Based on results from image processing and FDS models, the steady burning HRR is approximately 900 kW for a shelter fire with a flame height range of approximately 4.1-4.5 m.Item Metareasoning Approaches to Thermal Management During Image Processing(2022) Dawson, Michael Kenneth; Herrmann, Jeffrey W; Mechanical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Resource-constrained electronic systems are present in many semi- and fully-autonomous systems and are tasked with computationally heavy tasks such as image processing. Without sufficient cooling, these tasks often increase device temperature up to a predetermined maximum, beyond which the task is slowed by the device firmware to maintain the maximum. This is done to avoid decreased processor lifespan due to thermal fatigue or catastrophic processor failure due to thermal overstress. This thesis describes a study that evaluated how well metareasoning can manage the central processing unit (CPU) temperature during image processing (object detection and classification) on two devices: a Raspberry Pi 4B and an NVIDIA Jetson Nano Developer Kit. Three policies that employ metareasoning were developed; one which maintains a constant image throughput, one which maintains a constant expected detection precision, and a third that trades between throughput and precision losses based on a user-defined parameter. All policies used the EfficientDet series of object detectors. Depending on the policy, these networks were either switched between, delayed, or both. This thesis also considered cases that used the system's built-in throttling policy to control the temperature. A policy was also created via reinforcement learning. The policy was able to adjust the detection precision and program throughput based on a set of states corresponding to the possible temperatures, neural networks, and processing delays. All three designed metareasoning policies were able to stabilize the device temperature without relying on thermal throttling. Additionally, the policy created through reinforcement learning was able to successfully stabilize the device temperature, though less consistently. These results suggest that a metareasoning-based approach to thermal management in image processing is able to provide a platform-agnostic and programmatic way to comply with constant or variable temperature constraints.Item Anomaly Detection in Noisy Images(2015) Gibert Serra, Xavier; Chellappa, Rama; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Finding rare events in multidimensional data is an important detection problem that has applications in many fields, such as risk estimation in insurance industry, finance, flood prediction, medical diagnosis, quality assurance, security, or safety in transportation. The occurrence of such anomalies is so infrequent that there is usually not enough training data to learn an accurate statistical model of the anomaly class. In some cases, such events may have never been observed, so the only information that is available is a set of normal samples and an assumed pairwise similarity function. Such metric may only be known up to a certain number of unspecified parameters, which would either need to be learned from training data, or fixed by a domain expert. Sometimes, the anomalous condition may be formulated algebraically, such as a measure exceeding a predefined threshold, but nuisance variables may complicate the estimation of such a measure. Change detection methods used in time series analysis are not easily extendable to the multidimensional case, where discontinuities are not localized to a single point. On the other hand, in higher dimensions, data exhibits more complex interdependencies, and there is redundancy that could be exploited to adaptively model the normal data. In the first part of this dissertation, we review the theoretical framework for anomaly detection in images and previous anomaly detection work done in the context of crack detection and detection of anomalous components in railway tracks. In the second part, we propose new anomaly detection algorithms. The fact that curvilinear discontinuities in images are sparse with respect to the frame of shearlets, allows us to pose this anomaly detection problem as basis pursuit optimization. Therefore, we pose the problem of detecting curvilinear anomalies in noisy textured images as a blind source separation problem under sparsity constraints, and propose an iterative shrinkage algorithm to solve it. Taking advantage of the parallel nature of this algorithm, we describe how this method can be accelerated using graphical processing units (GPU). Then, we propose a new method for finding defective components on railway tracks using cameras mounted on a train. We describe how to extract features and use a combination of classifiers to solve this problem. Then, we scale anomaly detection to bigger datasets with complex interdependencies. We show that the anomaly detection problem naturally fits in the multitask learning framework. The first task consists of learning a compact representation of the good samples, while the second task consists of learning the anomaly detector. Using deep convolutional neural networks, we show that it is possible to train a deep model with a limited number of anomalous examples. In sequential detection problems, the presence of time-variant nuisance parameters affect the detection performance. In the last part of this dissertation, we present a method for adaptively estimating the threshold of sequential detectors using Extreme Value Theory on a Bayesian framework. Finally, conclusions on the results obtained are provided, followed by a discussion of possible future work.Item Using Domain-Specific Information in Image Processing(2014) Cash, Brianna Rose; O'Leary, Dianne P; Applied Mathematics and Scientific Computation; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)With the increasing availability of high resolution imaging tools, even in our pockets (i.e. smartphones), everyday users can do far more than simply digitally capturing a family moment. The ease of new applications available in these portable forms, linked with users who have expert knowledge about the images and tasks, opens the door to new possibilities. With this in mind we propose two new approaches that utilize the user's knowledge for improved results. We apply these approaches to real life problems in medical and scientific image applications. In the first approach, we introduce a class of linear and nonlinear methods which we call Domain-Specific Grayscale (DSGS) methods. A DSGS method transforms a color image into an image analogous to a grayscale image, where user-specified information is used to optimize a specified image processing task and reduce the computational complexity. We introduce new methods based on projection into the space of single-coordinate images, and we adapt support vector machines by using their scores to create a DSGS image. We apply these methods to applications in dermatology, analyzing images of skin tests and skin lesions, and demonstrate their usefulness. In the second approach, we introduce a tool for improved image deblurring that safeguards against bias that can easily be introduced by a user favoring a particular result. This is particularly important in scientific and medical applications used for discovery or diagnosis. We provide real-time results of choices of regularization methods and parameter selection, and we check the statistical plausibility of the results, using three statistical diagnostics, allowing a user to see the results of the choices. Our work demonstrates the utility of domain-specific information, supplied by the user, in improving the results of image processing algorithms.Item Edge-Based Automated Facial Blemish Removal(2013) NessAiver, Avisha; Chellappa, Rama; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)This thesis presents an end-to-end approach for taking a an image of a face and seamlessly isolating and filling in any blemishes contained therein. This consists of detecting the face within a larger image, building an accurate mask of the facial features so as not to mistake them as blemishes, detecting the blemishes themselves and painting over them with accurate skin tones. We devote the first part of the thesis to detailing our algorithm for extracting facial features. This is done by first improving the image through histogram equal- ization and illumination compensation followed by finding the features themselves from a computed edge map. Geometric knowledge of general feature positioning and blemish shapes is used to determine which edge clusters belong to correspond- ing facial features. Color and reflectance thresholding is then used to build a skin map. In the second part of the thesis we identify the blemishes themselves. A Lapla- cian of Gaussian blob detector is used to identify potential candidates. Thresholding and dilating operations are then performed to trim this candidate list down followed by the use of various morphological properties to reject regions likely to not be blem- ishes. Finally, in the third part, we examine four possible techniques for inpainting blemish regions once found. We settle on using a technique that fills in pixels based on finding a patch in the nearby image region with the most similar surrounding texture to the target pixel. Priority in the pixel fill-order is given to strong edges and contours.Item Cellular Pattern Quantication and Automatic Bench-marking Data-set Generation on confocal microscopy images(2010) Cui, Chi; JaJa, Joseph; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)The distribution, directionality and motility of the actin fibers control cell shape, affect cell function and are different in cancer versus normal cells. Quantification of actin structural changes is important for further understanding differences between cell types and for elucidation the effects and dynamics of drug interactions. We propose an image analysis framework to quantify the F-actin organization patterns in response to different pharmaceutical treatments.The main problems addressed include which features to quantify and what quantification measurements to compute when dealing with unlabeled confocal microscopy images. The resultant numerical features are very effective to profile the functional mechanism and facilitate the comparison of different drugs. The analysis software is originally implemented in Matlab and more recently the most time consuming part in the feature extraction stage is implemented onto the NVIDIA GPU using CUDA where we obtain 15 to 20 speedups for different sizes of image. We also propose a computational framework for generating synthetic images for validation purposes. The validation for the feature extraction is done by visual inspection and the validation for quantification is done by comparing them with well-known biological facts. Future studies will further validate the algorithms, and elucidate the molecular pathways and kinetics underlying the F-actin changes. This is the first study quantifying different structural formations of the same protein in intact cells. Since many anti-cancer drugs target the cytoskeleton, we believe that the quantitative image analysis method reported here will have broad applications to understanding the mechanisms of candidate pharmaceutical.Item SIMULTANEOUS MULTI-VIEW FACE TRACKING AND RECOGNITION IN VIDEO USING PARTICLE FILTERING(2009) Seo, Naotoshi; Chellappa, Rama; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Recently, face recognition based on video has gained wide interest especially due to its role in surveillance systems. Video-based recognition has superior advantages over image-based recognition because a video contains image sequences as well as temporal information. However, surveillance videos are generally of low-resolution and contain faces mostly in non-frontal poses. We propose a multi-view, video-based face recognition algorithm using the Bayesian inference framework. This method represents an appearance of each subject by a complex nonlinear appearance manifold expressed as a collection of simpler pose manifolds and the connections, represented by transition probabilities, among them. A Bayesian inference formulation is introduced to utilize the temporal information in the video via the transition probabilities among pose manifolds. The Bayesian inference formulation realizes video-based face recognition by progressively accumulating the recognition confidences in frames. The accumulation step possibly enables to solve face recognition problems in low-resolution videos, and the progressive characteristic is especially useful for a real-time processing. Furthermore, this face recognition framework has another characteristic that does not require processing all frames in a video if enough recognition confidence is accumulated in an intermediate frame. This characteristic gives an advantage over batch methods in terms of a computational efficiency. Furthermore, we propose a simultaneous multi-view face tracking and recognition algorithm. Conventionally, face recognition in a video is performed in tracking-then-recognition scenario that extracts the best facial image patch in the tracking and then recognizes the identity of the facial image. Simultaneous face tracking and recognition works in a different fashion, by handling both tracking and recognition simultaneously. Particle filter is a technique for implementing a Bayesian inference filter by Monte Carlo simulation, which has gained prevalence in the visual tracking literature since the Condensation algorithm was introduced. Since we have proposed a video-based face recognition algorithm based on the Bayesian inference framework, it is easy to integrate the particle filter tracker and our proposed recognition method into one, using the particle filter for both tracking and recognition simultaneously. This simultaneous framework utilizes the temporal information in a video for not only tracking but also recognition by modeling the dynamics of facial poses. Although the time series formulation remains more general, only the facial pose dynamics is utilized for recognition in this thesis.Item Calibration and Metrology Using Still and Video Images(2007-08-03) Guo, Feng; Chellappa, Rama; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Metrology, the measurement of real world metrics, has been investigated extensively in computer vision for many applications. The prevalence of video cameras and sequences has led to the demand for fully automated systems. Most of the existing video metrology methods are simple extensions of still-image algorithms, which have certain limitations, requiring constraints such as parallelism of lines. New techniques are needed in order to achieve accurate results for broader applications. An important preprocessing step and a closely related topic to metrology is calibration using planar patterns. Existing approaches lack exibility and robustness when extended to video sequences. This dissertation advances the state of the art in calibration and video metrology in three directions: (1) the concept of partial rectification is proposed along with new calibration techniques using a circle with diverse types of constraints; (2) new calibration methods for video sequences using planar patterns undergoing planar motion are proposed; and (3) new algorithms to extend video metrology to a wide range of applications are presented. A fully automated system using the new technique has been built for measuring the wheelbases of vehicles.