Interactive Effects of Plant Species and Organic Carbon on Nitrate Removal in Chesapeake Bay Treatment Wetlands

Nitrate from agricultural runoff are a significant cause of algal blooms in estuarine ecosystems such as the Chesapeake Bay. These blooms block sunlight vital to submerged aquatic vegetation, leading to hypoxic areas. Natural and constructed wetlands have been shown to reduce the amount of nitrate flowing into adjacent bodies of water. We tested three wetland plant species native to Maryland, Typha latifolia (cattail), Panicum virgatum (switchgrass), and Schoenoplectus validus (soft-stem bulrush), in wetland microcosms to determine the effect of species combination and organic amendment on nitrate removal. In the first phase of our study, we found that microcosms containing sawdust exhibited significantly greater nitrate removal than microcosms amended with glucose or hay at a low nitrate loading rate. In the second phase of our study, we confirmed that combining these plants removed nitrate, although no one combination was significantly better. Furthermore, the above-ground biomass of microcosms containing switchgrass had a significantly greater percentage of carbon than microcosms without switchgrass, which can be studied for potential biofuel use. Based on our data, future environmental groups can make a more informed decision when choosing biofuel-capable plant species for artificial wetlands native to the Chesapeake Bay Watershed.

Anomaly Detection in Noisy Images

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.

High Quality Acoustic Time History Measurements of Rotor Harmonic Noise in Confined Spaces

A methodology has been developed and presented to enable the use of small to medium scale acoustic hover facilities for the quantitative measurement of rotor impulsive noise. The methodology was applied to the University of Maryland Acoustic Chamber resulting in accurate measurements of High Speed Impulsive (HSI) noise for rotors running at tip Mach numbers between 0.65 and 0.85 – with accuracy increasing as the tip Mach number was increased. Several factors contributed to the success of this methodology including: • High Speed Impulsive (HSI) noise is characterized by very distinct pulses radiated from the rotor. The pulses radiate high frequency energy – but the energy is contained in short duration time pulses. • The first reflections from these pulses can be tracked (using ray theory) and, through adjustment of the microphone position and suitably applied acoustic treatment at the reflected surface, reduced to small levels. A computer code was developed that automates this process. The code also tracks first bounce reflection timing, making it possible to position the first bounce reflections outside of a measurement window. • Using a rotor with a small number of blades (preferably one) reduces the number of interfering first bounce reflections and generally improves the measured signal fidelity. The methodology will help the gathering of quantitative hovering rotor noise data in less than optimal acoustic facilities and thus enable basic rotorcraft research and rotor blade acoustic design.

Texture-Detail Preservation Measurement in Camera Phones: An Updated Approach

Recent advances in mobile phone cameras have poised them to take over compact hand-held cameras as the consumer’s preferred camera option. Along with advances in the number of pixels, motion blur removal, face-tracking, and noise reduction algorithms have significant roles in the internal processing of the devices. An undesired effect of severe noise reduction is the loss of texture (i.e. low-contrast fine details) of the original scene. Current established methods for resolution measurement fail to accurately portray the texture loss incurred in a camera system. The development of an accurate objective method to identify the texture preservation or texture reproduction capability of a camera device is important in this regard. The ‘Dead Leaves’ target has been used extensively as a method to measure the modulation transfer function (MTF) of cameras that employ highly non-linear noise-reduction methods. This stochastic model consists of a series of overlapping circles with radii r distributed as r−3, and having uniformly distributed gray level, which gives an accurate model of occlusion in a natural setting and hence mimics a natural scene. This target can be used to model the texture transfer through a camera system when a natural scene is captured. In the first part of our study we identify various factors that affect the MTF measured using the ‘Dead Leaves’ chart. These include variations in illumination, distance, exposure time and ISO sensitivity among others. We discuss the main differences of this method with the existing resolution measurement techniques and identify the advantages. In the second part of this study, we propose an improvement to the current texture MTF measurement algorithm. High frequency residual noise in the processed image contains the same frequency content as fine texture detail, and is sometimes reported as such, thereby leading to inaccurate results. A wavelet thresholding based denoising technique is utilized for modeling the noise present in the final captured image. This updated noise model is then used for calculating an accurate texture MTF. We present comparative results for both algorithms under various image capture conditions.

Understanding Urban Stormwater Denitrification in Bioretention Internal Water Storage Zones

Free-draining bioretention systems commonly demonstrate poor nitrate removal. In this study, column tests verified the necessity of a permanently saturated zone to target nitrate removal via denitrification. Experiments determined a first-order denitrification rate constant of 0.0011 min-1 specific to Willow Oak woodchip media. A 2.6-day retention time reduced 3.0 mgN/L to below 0.05 mg-N/L. During simulated storm events, hydraulic retention time may be used as a predictive measurement of nitrate fate and removal. A minimum 4.0 hour retention time was necessary for in-storm denitrification defined by a minimum 20% nitrate removal. Additional environmental parameters, e.g., pH, temperature, oxidation-reduction potential, and dissolved oxygen, affect denitrification rate and response, but macroscale measurements may not be an accurate depiction of denitrifying biofilm conditions. A simple model was developed to predict annual bioretention nitrate performance. Novel bioretention design should incorporate bowl storage and large subsurface denitrifying zones to maximize treatment volume and contact time.

Leveraging Multiple Features for Image Retrieval and Matching

The goal of image retrieval and matching is to find and locate object instances in images from a large-scale image database. While visual features are abundant, how to combine them to improve performance by individual features remains a challenging task. In this work, we focus on leveraging multiple features for accurate and efficient image retrieval and matching. We first propose two graph-based approaches to rerank initially retrieved images for generic image retrieval. In the graph, vertices are images while edges are similarities between image pairs. Our first approach employs a mixture Markov model based on a random walk model on multiple graphs to fuse graphs. We introduce a probabilistic model to compute the importance of each feature for graph fusion under a naive Bayesian formulation, which requires statistics of similarities from a manually labeled dataset containing irrelevant images. To reduce human labeling, we further propose a fully unsupervised reranking algorithm based on a submodular objective function that can be efficiently optimized by greedy algorithm. By maximizing an information gain term over the graph, our submodular function favors a subset of database images that are similar to query images and resemble each other. The function also exploits the rank relationships of images from multiple ranked lists obtained by different features. We then study a more well-defined application, person re-identification, where the database contains labeled images of human bodies captured by multiple cameras. Re-identifications from multiple cameras are regarded as related tasks to exploit shared information. We apply a novel multi-task learning algorithm using both low level features and attributes. A low rank attribute embedding is joint learned within the multi-task learning formulation to embed original binary attributes to a continuous attribute space, where incorrect and incomplete attributes are rectified and recovered. To locate objects in images, we design an object detector based on object proposals and deep convolutional neural networks (CNN) in view of the emergence of deep networks. We improve a Fast RCNN framework and investigate two new strategies to detect objects accurately and efficiently: scale-dependent pooling (SDP) and cascaded rejection classifiers (CRC). The SDP improves detection accuracy by exploiting appropriate convolutional features depending on the scale of input object proposals. The CRC effectively utilizes convolutional features and greatly eliminates negative proposals in a cascaded manner, while maintaining a high recall for true objects. The two strategies together improve the detection accuracy and reduce the computational cost.

Generating Discriminative Objective Proposals via Submodular Ranking

Object recognition has long been a core problem in computer vision. To improve object spatial support and speed up object localization for object recognition, generating high-quality category-independent object proposals as the input for object recognition system has drawn attention recently. Given an image, we generate a limited number of high-quality and category-independent object proposals in advance and used as inputs for many computer vision tasks. We present an efficient dictionary-based model for image classification task. We further extend the work to a discriminative dictionary learning method for tensor sparse coding. In the first part, a multi-scale greedy-based object proposal generation approach is presented. Based on the multi-scale nature of objects in images, our approach is built on top of a hierarchical segmentation. We first identify the representative and diverse exemplar clusters within each scale. Object proposals are obtained by selecting a subset from the multi-scale segment pool via maximizing a submodular objective function, which consists of a weighted coverage term, a single-scale diversity term and a multi-scale reward term. The weighted coverage term forces the selected set of object proposals to be representative and compact; the single-scale diversity term encourages choosing segments from different exemplar clusters so that they will cover as many object patterns as possible; the multi-scale reward term encourages the selected proposals to be discriminative and selected from multiple layers generated by the hierarchical image segmentation. The experimental results on the Berkeley Segmentation Dataset and PASCAL VOC2012 segmentation dataset demonstrate the accuracy and efficiency of our object proposal model. Additionally, we validate our object proposals in simultaneous segmentation and detection and outperform the state-of-art performance. To classify the object in the image, we design a discriminative, structural low-rank framework for image classification. We use a supervised learning method to construct a discriminative and reconstructive dictionary. By introducing an ideal regularization term, we perform low-rank matrix recovery for contaminated training data from all categories simultaneously without losing structural information. A discriminative low-rank representation for images with respect to the constructed dictionary is obtained. With semantic structure information and strong identification capability, this representation is good for classification tasks even using a simple linear multi-classifier.