Electrical and Computer Engineering Commons^™

Design And Application Of An Image-Processing-Based Fuzzy Autopilot For Small-Boat Approaching Maneuvers, Sin-Der Lee, Ching-Yaw Tzeng, Young-Zehr Kehr, Chih-Kai Kang, Chi-Chun Huang

Journal of Marine Science and Technology–Taiwan

This paper presents an image-processing-based fuzzy autopilot scheme for accomplishing small-boat approaching maneuvers in a harbor environment. In the proposed approach, two canvas targets are arranged in cascade on the quayside to form a leading line. The targets are detected by a charge coupled device (CCD) camera mounted on the bow of the boat, and their geometric centers are computed by a Hue- and Saturation-based image-processing scheme. The autopilot system calculates the current heading deviation and tracking deviation angles of the boat by analyzing the displacements of the target centers relative to the CCD center line. These angles are then …

A Neighborhood Dependent Nonlinear Technique For Enhancement Of Color Images Captured Under Non-Uniform Lighting Conditions, Rupal Patel

Electrical & Computer Engineering Theses & Dissertations

The aim of image enhancement process is to improve the interpretability of the information in images for human viewers or to provide better input for automated image processing techniques. Many image processing applications begin with a nonlinear enhancement process to improve visual quality of video sequences captured under nonuniform lighting conditions. This improves the visibility of the scene captured from physical sensing devices which have limited dynamic range. This physical limitation causes the saturated region of the image to either shadow out or wash out the rest of the scene. When extremely bright and dark regions are present in an …

Novel Wavelength Diversity Technique For High-Speed Atmospheric Turbulence Compensation, William W. Arrasmith, Sean F. Sullivan

Electrical Engineering and Computer Science Faculty Publications

The defense, intelligence, and homeland security communities are driving a need for software dominant, real-time or near-real time atmospheric turbulence compensated imagery. The development of parallel processing capabilities are finding application in diverse areas including image processing, target tracking, pattern recognition, and image fusion to name a few. A novel approach to the computationally intensive case of software dominant optical and near infrared imaging through atmospheric turbulence is addressed in this paper. Previously, the somewhat conventional wavelength diversity method has been used to compensate for atmospheric turbulence with great success. We apply a new correlation based approach to the wavelength …

Expression Invariant Face Recognition Using Shifted Phase-Encoded Joint Transform Correlation Technique, Trisha Ahmed

Electrical & Computer Engineering Theses & Dissertations

A new face recognition algorithm using a synthetic discriminant function based shifted phase-encoded fringe-adjusted joint transform correlation (SDF-SPFJTC) technique is proposed. The dark region in an input image is enhanced by using a nonlinear technique named ratio enhancement in gaussian neighborhood (REIGN). Histogram equalization and Gaussian smoothing are then performed to the enhanced face images and the synthetic discriminant function (SDF) image before they are subjected to the joint transform correlation process. The two distinct correlation peaks produced on extreme ends of the SPFJTC plane signifies the recognition of a potential target. A post processing step utilizes the peak-to-clutter ratio …

Compressive Sensing With Prior Information Applied To Magnetic Resonance Imaging, Cristiano Jacques Miosso

Open Access Theses & Dissertations

This dissertation introduces the theory of compressive sensing with prior information about a signal's sparse representation. We show, mathematically and in numerical simulations, that prior information improves signal reconstruction, in terms of number of required measurements, computation time and signal-to-noise ratios. Following, we present a set of methods for enhanced magnetic resonance imaging and tomography that can be combined with prior information, for enhanced image quality.

In developing the theory of compressive sensing with prior information, we provide a mathematical proof of the required condition (in terms of number of linear measurements) for reconstruction using the ideal approach of l0-minimization, …

A Robust Method To Detect Concealed Weapons, Anand Gone

Electrical & Computer Engineering Theses & Dissertations

Concealed weapons detection is a large problem that is faced by the Police Department nowadays. There are many disasters caused by poor detection of the weapons. Since public safety is at risk there is a need to design an efficient detector that can detect the weapons hidden under the clothing. This thesis presents a novel method for detecting concealed weapons under clothing using image processing techniques. In this thesis IR imagery is used to capture an image which works on the principle of law of black body radiation. Image thresholding is performed on the captured data using Sauvola's adaptive thresholding …

Three-Dimensional Target Modeling With Synthetic Aperture Radar, John R. Hupton

Master's Theses

Conventional Synthetic Aperture Radar (SAR) offers high-resolution imaging of a target region in the range and cross-range dimensions along the ground plane. Little or no data is available in the range-altitude dimension, however, and target functions and models are limited to two-dimensional images. This thesis first investigates some existing methods for the computation of target reflectivity data in the deficient elevation domain, and a new method is then proposed for three-dimensional (3-D) SAR target feature extraction.

Simulations are implemented to test the decoupled least-squares technique for high-resolution spectral estimation of target reflectivity, and the accuracy of the technique is assessed. …

Aerial And Satellite Image Processing Applications, Srinivas K. Jakkula

Electrical & Computer Engineering Theses & Dissertations

Aerial and satellite images are used extensively in many trip and mapping software packages, such as Google Earth etc. Aerial images differ significantly due to the variations in atmospheric clarity, atmospheric layer density, humidity, temperature, and season under which the aerial images are captured. Among the issues in effective utilization of aerial images, color tone discrepancy is the inconsistency in brightness, saturation, or color balance between images representing adjacent areas, causing adjacent areas appear significantly different that would otherwise be similar. Aenal images are also routinely used as ground textures to simulate Earth surface and 3D features on Earth in …

Live Wire Segmentation Tool For Osteophyte Detection In Lumbar Spine X-Ray Images, Santosh Seetharaman, R. Joe Stanley, Soumya De, Sameer Antani, L. Rodney Long, George R. Thoma

Electrical and Computer Engineering Faculty Research & Creative Works

Computer-assisted vertebra segmentation in x-ray images is a challenging problem. Inter-subject variability and the generally poor contrast of digitized radiograph images contribute to the segmentation difficulty. In this paper, a semi-automated live wire approach is investigated for vertebrae segmentation. The live wire approach integrates initially selected user points with dynamic programming to generate a closed vertebra boundary. In order to assess the degree to which vertebra features are conserved using the live wire technique, convex hull-based features to characterize anterior osteophytes in lumbar vertebrae are determined for live wire and manually segmented vertebrae. Anterior osteophyte discrimination was performed over 405 …

Joint Transform Correlation With A Synthetic Discrimination Function For Object Classification, Inder K. Purohit

Electrical & Computer Engineering Theses & Dissertations

A novel method using adaptive progressive thresholding (APT) and shifted phase-encoded fringe-adjusted joint transform correlation (SPFJTC) that employs a synthetic discriminant function (SDF) image for object classification is presented in this thesis. An adaptive progressive thresholding scheme first processes the given input scene to separate any objects present in the scene from the background. The preprocessing step results in an image having only the foreground objects, such as boats, trees and other cluttered regions, and hence reduces the search space for the correlation step significantly. The processed irμage is then fed to the shifted phase-encoded fringe-adjusted joint transform correlator, which …

Image Processing Technique For Runway Segmentation Using Color Spaces, Naresh Reddy Reddy

Electrical & Computer Engineering Theses & Dissertations

Aircrafts of the future now face the challenge of growing demand for safety which will require a more significant level of pilot assistance than is available today. During an approach to the airport runway, an algorithm that continuously segments the runway from the rest of the background with very little human intervention is very useful for both enhancing the landing safety and reducing the pilot's work load. This thesis presents a novel method for segmenting airport runways on a clear day and in poor visibility conditions using the color space components. In this thesis, collages were formed for both runway …

Robust Edge-Detection Algorithm For Runway Edge Detection, Swathi Tandra

Electrical & Computer Engineering Theses & Dissertations

Fog and other such weather conditions hamper the visibility of runway surfaces and any obstacles present on the runway, creating a situation where a pilot may not be able to safely land the aircraft. Assisting the pilot to land the aircraft safely in such conditions is an active area of research. A new method is being investigated that combines non-linear image enhancement with classification of runway edges to detect objects on the runway. The image is segmented into runway and non-runway regions, and objects that are found in the runway regions are deemed to constitute potential hazards. For runway edge …

Object Detection In Poor Visibility Conditions Using Image Segmentation, Triveni Vuppalapati

Electrical & Computer Engineering Theses & Dissertations

It can be dangerous for a pilot to attempt to land an aircraft safely in poor visibility conditions such as rain, fog, haze, snow and low light, but external imagery of a runway can be enhanced to provide increased situational awareness. Objects that are detected in a scene may or may not be a hazard, so interpretation is left to the pilot. In order to detect whether an object is a hazard to safe landing, it is necessary to determine whether the object is on the runway. For this purpose, two image segmentation algorithms: histogram based d-peak algorithm and local …

Image Pre-Processing Techniques For Hazard Detection In Poor Visibility Conditions, Girish Singh Rajput

Electrical & Computer Engineering Theses & Dissertations

Runway incursion is a persistent problem that has resulted in some of the most devastating accidents in aviation history. With ever increasing air traffic and more passengers, runway safety is of utmost priority to the Federal Aviation Administration (FAA) and other agencies concerned with aviation. As the issue of aviation safety becomes increasingly important, developing a consistent application that detects runway incursions in various visibility conditions is crucial for the aviation industry. This thesis presents a novel method for detecting runway hazards in poor visibility conditions using image processing techniques. The first step is to obtain images of a runway …

A Wide Area Bipolar Cascade Resonant Cavity Light Emitting Diode For A Hybrid Range-Intensity, Reginald J. Turner

Theses and Dissertations

This dissertation focused on the development of an illuminator for the HRIS. This illuminator enables faster image rendering and reduces the potential of errors in return signal data, that could be generated from extremely rough terrain. Four major achievements resulted from this work, which advance the field of 3-D image acquisition. The first is that the TJ is an effective current spreading layer for LEDs with mesa width up to 140 micrometers and current densities of approximately 1 x 10⁶ Amp/square centimeter. The TJ allows fabrication of an efficient illuminator, with required geometry for the HRIS to operate as …

Parallel Implementation Of High-Speed, Phase Diverse Atmospheric Turbulence Compensation Method On A Neural Network-Based Architecture, William W. Arrasmith, Sean F. Sullivan

Electrical Engineering and Computer Science Faculty Publications

Phase diversity imaging methods work well in removing atmospheric turbulence and some system effects from predominantly near-field imaging systems. However, phase diversity approaches can be computationally intensive and slow. We present a recently adapted, high-speed phase diversity method using a conventional, software-based neural network paradigm. This phase-diversity method has the advantage of eliminating many time consuming, computationally heavy calculations and directly estimates the optical transfer function from the entrance pupil phases or phase differences. Additionally, this method is more accurate than conventional Zernike-based, phase diversity approaches and lends itself to implementation on parallel software or hardware architectures. We use computer …

Direct, Object Brightness Estimation From Atmospheric Turbulence Degraded Images Using A New, High-Speed, Modified Phase Diversity Method, William W. Arrasmith

Electrical Engineering and Computer Science Faculty Publications

The well known phase diversity technique has long been used as a premier passive imaging method to mitigate the degrading effects of atmospheric turbulence on incoherent optical imagery. Typically, an iterative, slow method is applied that uses the Zernike basis set and 2-D Fourier transforms in the reconstruction process. In this paper, we demonstrate a direct method for estimating the un-aberrated object brightness from phase or phase difference estimates that 1) does not require the use of the Zernike basis set or the intermediate determination of the generalized pupil function, 2) directly determines the optical transfer function without the requirement …

Real-Time Forward Urban Environment Perception For An Autonomous Ground Vehicle Using Computer Vision And Lidar, Christopher Richard Greco

Theses and Dissertations

The field of autonomous vehicle research is growing rapidly. The Congressional mandate for the military to use unmanned vehicles has, in large part, sparked this growth. In conjunction with this mandate, DARPA sponsored the Urban Challenge, a competition to create fully autonomous vehicles that can operate in urban settings. An extremely important feature of autonomous vehicles, especially in urban locations, is their ability to perceive their environment. The research presented in this thesis is directed toward providing an autonomous vehicle with real-time data that efficiently and compactly represents its forward environment as it navigates an urban area. The information extracted …

Multi-Reference Frame Image Registration For Rotation, Translation, And Scale, Christopher S. Costello

Theses and Dissertations

This thesis investigates applications of multi-reference frame image registration for image sets with various translation, rotation, and scale combinations. It focuses on registration accuracy improvement over traditional pairwise registration, and also compares the quality of scene estimation from frame averaging. Three experiments are developed which use cross-correlation to estimate translation, the Radon transform to estimate translation and rotation, and the Fourier-Mellin transform to estimate translation, rotation, and scale. Results from applying multi-reference frame registration in these experiments show distinct improvements in both registration accuracy and quality of frame averaging compared to single-reference frame registration. Furthermore, it is shown that the …

Evaluation Of An Image Processing Algorithm For Scene Change Detection, Daniel Flores

Open Access Theses & Dissertations

Despite the efforts to reduce traffic accidents by government entities and automobile manufactures, the numbers of accidents are not considerably reduced. An evaluation of an algorithm based on the fly's eye is done on this research applying its principles to detect scene change on images for printed circuit boards providing initial steps to implement this algorithm on vehicular traffic to keep track of objects moving on the field for collision avoidance purposes. The effectiveness of the algorithm is addressed through a comparison of its performance with that found in experimental data.

An Adaptive And Non-Linear Technique For Enhancement Of High Contrast Images, Saibabu Arigela

Electrical & Computer Engineering Theses & Dissertations

In night time surveillance, there is a possibility of having extremely bright and dark regions in some image frames of a video sequence. Neither the object details in the low intensity areas nor in the high intensity areas can be clearly interpreted. Several image processing techniques have been developed to retrieve meaningful information under low lighting conditions. The algorithm based on integrated neighborhood dependency of pixel characteristics, and that based on the illuminance reflectance model perform well for improving the visual quality of digital images captured under extremely low and nonuniform lighting conditions. But these techniques cannot perform well in …

A Resolution Enhancement Technique In Digital Images, Mehmet R. Ormanoglu

Electrical & Computer Engineering Theses & Dissertations

Image enhancement is the processing of images to increase their usefulness. The image enhancement methods and objectives vary with the application. When images are enhanced for human viewers, as in television, the objective is mostly to improve perceptual aspects: image quality, intelligibility, or visual appearance. The aim of this research work is to make the processed image better in the visual sense than the unprocessed image. An image can often be enhanced by modifying its contrast or dynamic range, increasing the sharpness of edges, reducing the noise, or reducing the blurring. The most commonly used contrast enhancement technique is histogram …

Power-Aware Design Methodologies For Fpga-Based Implementation Of Video Processing Systems, Hau Trung Ngo

Electrical & Computer Engineering Theses & Dissertations

The increasing capacity and capabilities of FPGA devices in recent years provide an attractive option for performance-hungry applications in the image and video processing domain. FPGA devices are often used as implementation platforms for image and video processing algorithms for real-time applications due to their programmable structure that can exploit inherent spatial and temporal parallelism. While performance and area remain as two main design criteria, power consumption has become an important design goal especially for mobile devices. Reduction in power consumption can be achieved by reducing the supply voltage, capacitances, clock frequency and switching activities in a circuit. Switching activities …

Fusion Of Imaging And Inertial Sensors For Navigation, Michael J. Veth

Theses and Dissertations

The motivation of this research is to address the limitations of satellite-based navigation by fusing imaging and inertial systems. The research begins by rigorously describing the imaging and navigation problem and developing practical models of the sensors, then presenting a transformation technique to detect features within an image. Given a set of features, a statistical feature projection technique is developed which utilizes inertial measurements to predict vectors in the feature space between images. This coupling of the imaging and inertial sensors at a deep level is then used to aid the statistical feature matching function. The feature matches and inertial …

Development Of A Cost Effective Mini Autonomous Underwater Vehicle, Chiu-Feng Lin, Chyuan-Yow Tseng

Journal of Marine Science and Technology–Taiwan

This paper describes the development of a cost effective mini autonomous underwater vehicle. The mini size of the vehicle is achieved by extracting the control module hardware out from the vehicle vessel and by reducing the on-board sensors. The control of the vehicle is conducted by a base station wirelessly telecommunicating with the vehicle. Furthermore, the reduction of the sensors also reduces the cost of the vehicle. For the purpose, in the vehicle, a single sensor featuring a CCD camera is mounted at the front of the vehicle. The images taken by this CCD camera are used both for obstacle …

Fast Video Stabilization Algorithms, Mohammed A. Alharbi

Theses and Dissertations

A fast and robust electronic video stabilization algorithm is presented in this thesis. It is based on a two-dimensional feature-based motion estimation technique. The method tracks a small set of features and estimates the movement of the camera between consecutive frames. It is used to characterize the motions accurately including camera rotations between two imaging instants. An affine motion model is utilized to determine the parameters of translation and rotation between images. The determined affine transformation is then exploited to compensate for the abrupt temporal discontinuities of input image sequences. Also, a frequency domain approach is developed to estimate translations …

Unconventional Optical Imaging Using A High Speed, Neural Network Based Smart Sensor, William W. Arrasmith

Electrical Engineering and Computer Science Faculty Publications

The advancement of neural network methods and technologies is finding applications in many fields and disciplines of interest to the defense, intelligence, and homeland security communities. Rapidly reconfigurable sensors for real or near-real time signal or image processing can be used for multi-functional purposes such as image compression, target tracking, image fusion, edge detection, thresholding, pattern recognition, and atmospheric turbulence compensation to name a few. A neural network based smart sensor is described that can accomplish these tasks individually or in combination, in real-time or near real-time. As a computationally intensive example, the case of optical imaging through volume turbulence …

A Non-Linear Technique For The Enhancement Of Extremely Non-Uniform Lighting Images, Ender Oguslu

Electrical & Computer Engineering Theses & Dissertations

At night scenes, either the low intensity areas that are under poor light or the high intensity areas that are overexposed cannot be clearly seen. Various image processing techniques have been developed to recover the meaningful information under extremely low lighting conditions. Among these, the algorithms based on integrated neighborhood dependency of pixel characteristics and based on the illuminance reflectance model perform well for improving the visual quality of digital images captured under nonuniform and extremely low lighting conditions. Although these techniques perform well in low lighting conditions, they cannot perform well in overexposed regions under dark environments such as …

Image Processing Resource Allocation Methods For Multi-Target Tracking Of Dismounted Targets In Urban Environments, Jonathan P. Champion

Theses and Dissertations

Dismounted targets can be tracked in urban environments with video sensors. Real-time systems are unable to process all of the imagery, demanding some method for prioritization of the processing resources. Furthermore, various segmentation algorithms exist within image processing, each algorithm possesses unique capabilities, and each algorithm has an associated computational cost. Additional complexity arises in the prioritization problem when targets become occluded (e.g., by a building) and when the targets are intermixed with other dismounted entities. This added complexity leads to the question "which portions of the scene warrant both low cost and high cost processing?" The approach presented in …

The Influence Of Quantization Process On The Performance Of Global Entropic Thresholding Algorithms Using Electrical Capacitance Tomography Data, A. J. Mwambela

Tanzania Journal of Science

In measuring component fraction in multiphase flows using tomographic techniques, it is desirable to use a high speed tomography system capable of generating 100 tomograms per second. The electrical capacitance tomography system in this regard is considered to be the best among the available tomographic techniques. However, due to its inherent limitations the system generates distorted reconstructed tomograms necessitating the use of extra signal processing techniques such as thresholding to minimize these distortions. Whilst thresholding technique has been effective in minimizing distortions, the additional computation associated with the process limits the speed of tomogram generation desired from the system. Further, …