With augmenting security concerns and decreasing costs of surveillance and computing equipment, research on automated systems for object detection has been increasing, but the majority of the studies focus their attention on sequences where high resolution objects are present. The main objective of this work is the detection and extraction of information of low resolution objects (e.g. objects that are so far away from the camera that they occupy only tens of pixels) in order to provide a base for higher level information operations such as classification and behavioral analysis. The system proposed is composed of four stages (preprocessing, background modeling, information extraction, and post processing) and uses context based region of importance selection, histogram equalization, background subtraction and morphological filtering techniques. The result is a system capable of detecting and tracking low resolution objects in a controlled background scene which can be a base for systems with higher complexity. / by Diego F. Pava. / Thesis (M.S.C.S.)--Florida Atlantic University, 2009. / Includes bibliography. / Electronic reproduction. Boca Raton, Fla., 2009. Mode of access: World Wide Web.

Professional imaging systems, particularly motion picture cameras, usually employ larger photosites and lower pixel counts than many amateur cameras. This results in the desirable characteristics of improved dynamic range, signal to noise and sensitivity. However, high performance optics often have frequency response characteristics that exceed the Nyquist limit of the sensor, which, if not properly addressed, results in aliasing artifacts in the captured image. Most contemporary still and video cameras employ various optically birefringent materials as optical low-pass filters (OLPF) in order to minimize aliasing artifacts in the image. Most OLPFs are designed as optical elements with a frequency response that does not change even if the frequency responses of the other elements of the capturing systems are altered. An extended evaluation of currently used birefringent-based OLPFs is provided. In this work, the author proposed and demonstrated the use of a parallel optical window p ositioned between a lens and a sensor as an OLPF. Controlled X- and Y-axes rotations of the optical window during the image exposure results in a manipulation of the system's point-spread function (PSF). Consequently, changing the PSF affects some portions of the frequency components contained in the image formed on the sensor. The system frequency response is evaluated when various window functions are used to shape the lens' PSF, such as rectangle, triangle, Tukey, Gaussian, Blackman-Harris etc. In addition to the ability to change the PSF, this work demonstrated that the PSF can be manipulated dynamically, which allowed us to modify the PSF to counteract any alteration of other optical elements of the capturing system. There are several instances presented in the dissertation in which it is desirable to change the characteristics of an OLPF in a controlled way. / In these instances, an OLPF whose characteristics can be altered dynamically results in an improvement of the image quality. / by Branko Petljanski. / Thesis (Ph.D.)--Florida Atlantic University, 2010. / Includes bibliography. / Electronic reproduction. Boca Raton, Fla., 2010. Mode of access: World Wide Web.

For an 8-bit grayscale image patch of size n x n, the number of distinguishable signals is 256(n2). Natural images (e.g.,photographs of a natural scene) comprise a very small subset of these possible signals. Traditional image and video processing relies on band-limited or low-pass signal models. In contrast, we will explore the observation that most signals of interest are sparse, i.e. in a particular basis most of the expansion coefficients will be zero. Recent developments in sparse modeling and L1 optimization have allowed for extraordinary applications such as the single pixel camera, as well as computer vision systems that can exceed human performance. Here we present a novel neural network architecture combining a sparse filter model and locally competitive algorithms (LCAs), and demonstrate the networks ability to classify human actions from video. Sparse filtering is an unsupervised feature learning algorithm designed to optimize the sparsity of the feature distribution directly without having the need to model the data distribution. LCAs are defined by a system of di↵erential equations where the initial conditions define an optimization problem and the dynamics converge to a sparse decomposition of the input vector. We applied this architecture to train a classifier on categories of motion in human action videos. Inputs to the network were small 3D patches taken from frame di↵erences in the videos. Dictionaries were derived for each action class and then activation levels for each dictionary were assessed during reconstruction of a novel test patch. We discuss how this sparse modeling approach provides a natural framework for multi-sensory and multimodal data processing including RGB video, RGBD video, hyper-spectral video, and stereo audio/video streams. / Includes bibliography. / Dissertation (Ph.D.)--Florida Atlantic University, 2016. / FAU Electronic Theses and Dissertations Collection

Video signature techniques based on tomography images address the problem of video identification. This method relies on temporal segmentation and sampling strategies to build and determine the unique elements that will form the signature. In this thesis an extension for these methods is presented; first a new feature extraction method, derived from the previously proposed sampling pattern, is implemented and tested, resulting in a highly distinctive set of signature elements, second a robust temporal video segmentation system is used to replace the original method applied to determine shot changes more accurately. Under a very exhaustive set of tests the system was able to achieve 99.58% of recall, 100% of precision and 99.35% of prediction precision. / by Sebastian Possos Medellin. / Thesis (M.S.C.S.)--Florida Atlantic University, 2010. / Includes bibliography. / Electronic reproduction. Boca Raton, Fla., 2010. Mode of access: World Wide Web.

In this dissertation we apply sparse constraints to improve optical flow and trajectories. We apply sparsity in two ways. First, with 2-frame optical flow, we enforce a sparse representation of flow patches using a learned overcomplete dictionary. Second, we apply a low rank constraint to trajectories via robust coupling. We begin with a review of optical flow fundamentals. We discuss the commonly used flow estimation strategies and the advantages and shortcomings of each. We introduce the concepts associated with sparsity including dictionaries and low rank matrices. / Includes bibliography. / Dissertation (Ph.D.)--Florida Atlantic University, 2014. / FAU Electronic Theses and Dissertations Collection

Video identification or copy detection is a challenging problem and is becoming increasingly important with the popularity of online video services. The problem addressed in this thesis is the identification of a given video clip in a given set of videos. For a given query video, the system returns all the instance of the video in the data set. This identification system uses video signatures based on video tomography. A robust and low complexity video signature is designed and implemented. The nature of the signature makes it independent to the most commonly video transformations. The signatures are generated for video shots and not individual frames, resulting in a compact signature of 64 bytes per video shot. The signatures are matched using simple Euclidean distance metric. The results show that videos can be identified with 100% recall and over 93% precision. The experiments included several transformations on videos. / by Gustavo A. Leon. / Thesis (M.S.C.S.)--Florida Atlantic University, 2008. / Includes bibliography. / Electronic reproduction. Boca Raton, Fla., 2008. Mode of access: World Wide Web.

Perceptual video coding has been a promising area during the last years. Increases in compression ratios have been reported by applying foveated video coding techniques where the region of interest (ROI) is selected by using a computational attention model. However, most of the approaches for perceptual video coding only use visual features ignoring the auditory component. In recent physiological studies, it has been demonstrated that auditory stimuli affects our visual perception. In this work, we validate some of those physiological tests using complex video sequence. We designed and developed a web-based tool for video quality measurement. After conducting different experiments, we observed that in the general reaction time to detect video artifacts was higher when video was presented with the audio information. We observed that emotional information in audio guide human attention to particular ROI. We also observed that sound frequency change spatial frequency perception in still images. / by Freddy Torres. / Thesis (M.S.C.S.)--Florida Atlantic University, 2013. / Includes bibliography. / Mode of access: World Wide Web. / System requirements: Adobe Reader.

Recently, multimedia applications and their use have grown dramatically in popularity in strong part due to mobile device adoption by the consumer market. Applications, such as video conferencing, have gained popularity. These applications and others have a strong video component that uses the mobile device’s resources. These resources include processing time, network bandwidth, memory use, and battery life. The goal is to reduce the need of these resources by reducing the complexity of the coding process. Mobile devices offer unique characteristics that can be exploited for optimizing video codecs. The combination of small display size, video resolution, and human vision factors, such as acuity, allow encoder optimizations that will not (or minimally) impact subjective quality. The focus of this dissertation is optimizing video services in mobile environments. Industry has begun migrating from H.264 video coding to a more resource intensive but compression efficient High Efficiency Video Coding (HEVC). However, there has been no proper evaluation and optimization of HEVC for mobile environments. Subjective quality evaluations were performed to assess relative quality between H.264 and HEVC. This will allow for better use of device resources and migration to new codecs where it is most useful. Complexity of HEVC is a significant barrier to adoption on mobile devices and complexity reduction methods are necessary. Optimal use of encoding options is needed to maximize quality and compression while minimizing encoding time. Methods for optimizing coding mode selection for HEVC were developed. Complexity of HEVC encoding can be further reduced by exploiting the mismatch between the resolution of the video, resolution of the mobile display, and the ability of the human eyes to acquire and process video under these conditions. The perceptual optimizations developed in this dissertation use the properties of spatial (visual acuity) and temporal information processing (motion perception) to reduce the complexity of HEVC encoding. A unique feature of the proposed methods is that they reduce encoding complexity and encoding time. The proposed HEVC encoder optimization methods reduced encoding time by 21.7% and bitrate by 13.4% with insignificant impact on subjective quality evaluations. These methods can easily be implemented today within HEVC. / Includes bibliography. / Dissertation (Ph.D.)--Florida Atlantic University, 2014. / FAU Electronic Theses and Dissertations Collection

by Lai Wai Kuen. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1993. / Includes bibliographical references (leaves [119-125]). / Abstract --- p.i / Acknowledgement --- p.ii / Table of Contents --- p.iii / Chapter Chapter 1 --- Introduction / Chapter 1.1 --- Background - The Need for Nonlinear Filtering --- p.1.1 / Chapter 1.2 --- Nonlinear Filtering --- p.1.2 / Chapter 1.3 --- Goal of the Work --- p.1.4 / Chapter 1.4 --- Organization of the Thesis --- p.1.5 / Chapter Chapter 2 --- An Overview of Robust Estimator Based Filters Morphological Filters / Chapter 2.1 --- Introduction --- p.2.1 / Chapter 2.2 --- Signal Representation by Sets --- p.2.2 / Chapter 2.3 --- Robust Estimator Based Filters --- p.2.4 / Chapter 2.3.1 --- Filters based on the L-estimators --- p.2.4 / Chapter 2.3.1.1 --- The Median Filter and its Derivations --- p.2.5 / Chapter 2.3.1.2 --- Rank Order Filters and Derivations --- p.2.9 / Chapter 2.3.2 --- Filters based on the M-estimators (M-Filters) --- p.2.11 / Chapter 2.3.3 --- Filter based on the R-estimators --- p.2.13 / Chapter 2.4 --- Filters based on Mathematical Morphology --- p.2.14 / Chapter 2.4.1 --- Basic Morphological Operators --- p.2.14 / Chapter 2.4.2 --- Morphological Filters --- p.2.18 / Chapter 2.5 --- Chapter Summary --- p.2.20 / Chapter Chapter 3 --- Multi-Structuring Element Erosion Filter / Chapter 3.1 --- Introduction --- p.3.1 / Chapter 3.2 --- Problem Formulation --- p.3.1 / Chapter 3.3 --- Description of Multi-Structuring Element Erosion Filter --- p.3.3 / Chapter 3.3.1 --- Definition of Structuring Element for Multi-Structuring Element Erosion Filter --- p.3.4 / Chapter 3.3.2 --- Binary multi-Structuring Element Erosion Filter --- p.3.9 / Chapter 3.3.3 --- Selective Threshold Decomposition --- p.3.10 / Chapter 3.3.4 --- Multilevel Multi-Structuring Element Erosion Filter --- p.3.15 / Chapter 3.3.5 --- A Combination of Multilevel Multi-Structuring Element Erosion Filter and its Dual --- p.3.21 / Chapter 3.4 --- Chapter Summary --- p.3.21 / Chapter Chapter 4 --- Properties of Multi-Structuring Element Erosion Filter / Chapter 4.1 --- Introduction --- p.4.1 / Chapter 4.2 --- Deterministic Properties --- p.4.2 / Chapter 4.2.1 --- Shape of Invariant Signal --- p.4.3 / Chapter 4.2.1.1 --- Binary Multi-Structuring Element Erosion Filter --- p.4.5 / Chapter 4.2.1.2 --- Multilevel Multi-Structuring Element Erosion Filter --- p.4.16 / Chapter 4.2.2 --- Rate of Convergence of Multi-Structuring Element Erosion Filter --- p.4.25 / Chapter 4.2.2.1 --- Convergent Rate of Binary Multi-Structuring Element Erosion Filter --- p.4.25 / Chapter 4.2.2.2 --- Convergent Rate of Multilevel Multi-Structuring Element Erosion Filter --- p.4.28 / Chapter 4.3 --- Statistical Properties --- p.4.30 / Chapter 4.3.1 --- Output Distribution of Multi-Structuring Element Erosion Filter --- p.4.30 / Chapter 4.3.1.1 --- One-Dimensional Statistical Analysis of Multilevel Multi-Structuring Element Erosion Filter --- p.4.31 / Chapter 4.3.1.2 --- Two-Dimensional Statistical Analysis of Multilevel Multi-Structuring Element Erosion Filter --- p.4.32 / Chapter 4.3.2 --- Discussions on Statistical Properties --- p.4.36 / Chapter 4.4 --- Chapter Summary --- p.4.40 / Chapter Chapter 5 --- Performance Evaluation / Chapter 5.1 --- Introduction --- p.5.1 / Chapter 5.2 --- Performance Criteria --- p.5.2 / Chapter 5.2.1 --- Noise Suppression --- p.5.5 / Chapter 5.2.2 --- Subjective Criterion --- p.5.16 / Chapter 5.2.3 --- Computational Requirement --- p.5.20 / Chapter 5.3 --- Chapter Summary --- p.5.23 / Chapter Chapter 6 --- Recapitulation and Suggestions for Further Work / Chapter 6.1 --- Recapitulation --- p.6.1 / Chapter 6.2 --- Suggestions for Further Work --- p.6.4 / Chapter 6.2.1 --- Probability Measure Function for the Two-Dimensional Filter --- p.6.4 / Chapter 6.2.2 --- Hardware Implementation --- p.6.5 / References / Appendices

by Kong Shao-hua. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1992. / Includes bibliographical references (leaves 113-116). / Chapter CHAPTER 1 --- INTRODUCTION --- p.1 / Chapter CHAPTER 2 --- REVIEW OF 3-D OBJECT RECOGNITION SYSTEMS --- p.8 / Chapter CHAPTER 3 --- FEATURE EXTRACTION AND OBJECT REPRESEN- TATION --- p.16 / Chapter 3.1 --- Preprocessing --- p.18 / Chapter 3.2 --- Extraction of Characteristic Points --- p.20 / Chapter 3.3 --- Characterization of Surface Patches --- p.28 / Chapter 3.4 --- Object Representation --- p.37 / Chapter 3.5 --- Model Formation --- p.42 / Chapter CHAPTER 4 --- OBJECT RECOGNITION AND OBJECT LOCATION AND ORIENTATION DETERMINATION --- p.45 / Chapter 4.1 --- RBM-Matching --- p.48 / Chapter 4.1.1 --- Rigid body model (RBM) --- p.48 / Chapter 4.1.2 --- RBM-matching --- p.55 / Chapter 4.2 --- Estimation of the Transformation Parameters --- p.63 / Chapter 4.3 --- Recognition Decision Making --- p.72 / Chapter CHAPTER 5 --- EXPERIMENTATION --- p.80 / Chapter 5.1 --- Automatic Model Building --- p.82 / Chapter 5.2 --- Recognition of Single Objects --- p.88 / Chapter 5.3 --- Recognition of Multiple Objects with Occlusion --- p.103 / Chapter CHAPTER 6 --- CONCLUSION AND DISCUSSION --- p.109 / REFERENCES --- p.113