UMD Theses and Dissertations
Permanent URI for this collectionhttp://hdl.handle.net/1903/3
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 given thesis/dissertation in DRUM.
More information is available at Theses and Dissertations at University of Maryland Libraries.
Browse
3 results
Search Results
Item LEARNING OF DENSE OPTICAL FLOW, MOTION AND DEPTH, FROM SPARSE EVENT CAMERAS(2019) Ye, Chengxi; Aloimonos, Yiannis; Fermüller, Cornelia; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)With recent advances in the field of autonomous driving, autonomous agents need to safely navigate around humans or other moving objects in unconstrained, highly dynamic environments. In this thesis, we demonstrate the feasibility of reconstructing dense depth, optical flow and motion information from a neuromorphic imaging device, called Dynamic Vision Sensor (DVS). The DVS only records sparse and asynchronous events when the changes of lighting occur at camera pixels. Our work is the first monocular pipeline that generates dense depth and optical flow from sparse event data only. To tackle this problem of reconstructing dense information from sparse information, we introduce the Evenly-Cascaded convolutional Network (ECN), a bio-inspired multi-level, multi-resolution neural network architecture. The network features an evenly-shaped design, and utilization of both high and low level features. With just 150k parameters, our self-supervised pipeline is able to surpass pipelines that are 100x larger. We evaluate our pipeline on the MVSEC self driving dataset and present results for depth, optical flow and and egomotion estimation in wild outdoor scenes. Due to the lightweight design, the inference part of the network runs at 250 FPS on a single GPU, making the pipeline ready for realtime robotics applications. Our experiments demonstrate significant improvements upon previous works that used deep learning on event data, as well as the ability of our pipeline to perform well during both day and night. We also extend our pipeline to dynamic indoor scenes with independent moving objects. In addition to camera egomotion and a dense depth map, the network utilizes a mixture model to segment and compute per-object 3D translational velocities for moving objects. For this indoor task we are able to train a shallow network with just 40k parameters, which computes qualitative depth and egomotion. Our analysis of the training shows modern neural networks are trained on tangled signals. This tangling effect can be imagined as a blurring introduced both by nature and by the training process. We propose to untangle the data with network deconvolution. We notice significantly better convergence without using any standard normalization techniques, which suggests us deconvolution is what we need.Item Controlling light Propagation in complex media for Imaging, focusing and Brillouin measurements(2018) Edrei, Eitan Y; Scarcelli, Giuliano; Bioengineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Imaging and focusing light through turbid media are two fundamental challenges of optical sciences that have attracted significant attention in recent years. Traditional optical systems such as confocal microscopy, optical coherence tomography and multi-photon microscopy utilize ballistic photons traveling in straight trajectories to generate an image; however, with increasing depth, the signal to noise ratio (SNR) decreases as the number of ballistic photons decays exponentially. In the first part of this thesis I present two novel techniques for imaging through scattering medium by decoding seemingly random scattered light patterns and demonstrate the highest resolution and acquisition speed to date. For point scanning applications I also study methods to focus light through scattering materials and report on a fundamental trade-off between the focal point intensity and the focal plane in which it is generated. In the second part of the thesis I investigate how the ability to control light propagation within turbid media can be used to enhance point scanning measurements such as Brillouin scattering spectroscopy, a technology recently developed in our lab to characterize material stiffness without contact. To do this, I first present a novel optical system (“spectral coronagraph”) which yields an improved extinction ratio when inserted into Brillouin spectrometers to enable the spectral separation in the presence of scattering or close to interfaces. Additionally, to enhance the Brillouin signal, I apply adaptive optics techniques, first developed for astronomy applications, where the incident wave front is shaped to circumvent for optical phase aberrations. Using adaptive optics, I show signal enhancement in artificial and biological samples, an important feature in the context of Brillouin microscopy to promote high SNR imaging in practical scenarios.Item Sparse and Redundant Representations for Inverse Problems and Recognition(2010) Patel, Vishal M.; Chellappa, Rama; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Sparse and redundant representation of data enables the description of signals as linear combinations of a few atoms from a dictionary. In this dissertation, we study applications of sparse and redundant representations in inverse problems and object recognition. Furthermore, we propose two novel imaging modalities based on the recently introduced theory of Compressed Sensing (CS). This dissertation consists of four major parts. In the first part of the dissertation, we study a new type of deconvolution algorithm that is based on estimating the image from a shearlet decomposition. Shearlets provide a multi-directional and multi-scale decomposition that has been mathematically shown to represent distributed discontinuities such as edges better than traditional wavelets. We develop a deconvolution algorithm that allows for the approximation inversion operator to be controlled on a multi-scale and multi-directional basis. Furthermore, we develop a method for the automatic determination of the threshold values for the noise shrinkage for each scale and direction without explicit knowledge of the noise variance using a generalized cross validation method. In the second part of the dissertation, we study a reconstruction method that recovers highly undersampled images assumed to have a sparse representation in a gradient domain by using partial measurement samples that are collected in the Fourier domain. Our method makes use of a robust generalized Poisson solver that greatly aids in achieving a significantly improved performance over similar proposed methods. We will demonstrate by experiments that this new technique is more flexible to work with either random or restricted sampling scenarios better than its competitors. In the third part of the dissertation, we introduce a novel Synthetic Aperture Radar (SAR) imaging modality which can provide a high resolution map of the spatial distribution of targets and terrain using a significantly reduced number of needed transmitted and/or received electromagnetic waveforms. We demonstrate that this new imaging scheme, requires no new hardware components and allows the aperture to be compressed. Also, it presents many new applications and advantages which include strong resistance to countermesasures and interception, imaging much wider swaths and reduced on-board storage requirements. The last part of the dissertation deals with object recognition based on learning dictionaries for simultaneous sparse signal approximations and feature extraction. A dictionary is learned for each object class based on given training examples which minimize the representation error with a sparseness constraint. A novel test image is then projected onto the span of the atoms in each learned dictionary. The residual vectors along with the coefficients are then used for recognition. Applications to illumination robust face recognition and automatic target recognition are presented.