Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Institution
Articles 1 - 8 of 8
Full-Text Articles in Engineering
Robust Techniques And Applications In Fuzzy Clustering, Amit Banerjee
Robust Techniques And Applications In Fuzzy Clustering, Amit Banerjee
Dissertations
This dissertation addresses issues central to frizzy classification. The issue of sensitivity to noise and outliers of least squares minimization based clustering techniques, such as Fuzzy c-Means (FCM) and its variants is addressed. In this work, two novel and robust clustering schemes are presented and analyzed in detail. They approach the problem of robustness from different perspectives. The first scheme scales down the FCM memberships of data points based on the distance of the points from the cluster centers. Scaling done on outliers reduces their membership in true clusters. This scheme, known as the Mega-clustering, defines a conceptual mega-cluster which …
Wide-Angle Multistatic Synthetic Aperture Radar: Focused Image Formation And Aliasing Artifact Mitigation, Jonathan E. Luminati
Wide-Angle Multistatic Synthetic Aperture Radar: Focused Image Formation And Aliasing Artifact Mitigation, Jonathan E. Luminati
Theses and Dissertations
Traditional monostatic Synthetic Aperture Radar (SAR) platforms force the user to choose between two image types: larger, low resolution images or smaller, high resolution images. Switching to a Wide-Angle Multistatic Synthetic Aperture Radar (WAM-SAR) approach allows formation of large high-resolution images. Unfortunately, WAM-SAR suffers from two significant implementation problems. First, wavefront curvature effects, non-linear flight paths, and warped ground planes lead to image defocusing with traditional SAR processing methods. A new 3-D monostatic/bistatic image formation routine solves the defocusing problem, correcting for all relevant wide-angle effects. Inverse SAR (ISAR) imagery from a Radar Cross Section (RCS) chamber validates this approach. …
Improved Multinuclide Imaging Of Special Nuclear Material Using A High Purity Germanium Double Sided Strip Detector, Fred D. Rothenbush Jr.
Improved Multinuclide Imaging Of Special Nuclear Material Using A High Purity Germanium Double Sided Strip Detector, Fred D. Rothenbush Jr.
Theses and Dissertations
The purpose of this research is to improve the ability to image Special Nuclear Material (SNM) using a High Purity Germanium Double Sided Strip Detector (HPGeDSSD) for use in the field of nuclear nonproliferation. When used for gamma spectrometry, HPGe detectors can efficiently distinguish various isotopes because of their good energy resolution. The detector used for this research is a liquid nitrogen cooled germanium detector with five charge collection strips on each face. The strips are orthogonal to each other, creating a five by five array of data collection pixels. When the 25 mm by 25 mm detector array is …
Optimization Of Automatic Target Recognition With A Reject Option Using Fusion And Correlated Sensor Data, Trevor I. Laine
Optimization Of Automatic Target Recognition With A Reject Option Using Fusion And Correlated Sensor Data, Trevor I. Laine
Theses and Dissertations
This dissertation examines the optimization of automatic target recognition (ATR) systems when a rejection option is included. First, a comprehensive review of the literature inclusive of ATR assessment, fusion, correlated sensor data, and classifier rejection is presented. An optimization framework for the fusion of multiple sensors is then developed. This framework identifies preferred fusion rules and sensors along with rejection and receiver operating characteristic (ROC) curve thresholds without the use of explicit misclassification costs as required by a Bayes' loss function. This optimization framework is the first to integrate both "vertical" warfighter output label analysis and "horizontal" engineering confusion matrix …
Determination Of Structure From Motion Using Aerial Imagery, Paul R. Graham
Determination Of Structure From Motion Using Aerial Imagery, Paul R. Graham
Theses and Dissertations
The structure from motion process creates three-dimensional models from a sequence of images. Until recently, most research in this field has been restricted to land-based imagery. This research examines the current methods of land-based structure from motion and evaluates their performance for aerial imagery. Current structure from motion algorithms search the initial image for features to track though the subsequent images. These features are used to create point correspondences between the two images. The correspondences are used to estimate the motion of the camera and then the three-dimensional structure of the scene. This research tests current algorithms using synthetic data …
A Line-Of-Slight Sensor Network For Wide Area Video Surveillance: Simulation And Evaluation, Jamie R. Morrison
A Line-Of-Slight Sensor Network For Wide Area Video Surveillance: Simulation And Evaluation, Jamie R. Morrison
Theses and Dissertations
Substantial performance improvement of a wide area video surveillance network can be obtained with the addition of a Line-of-Sight sensor. The research described in this thesis shows that while the Line-of-Sight sensor cannot monitor areas with the ubiquity of video cameras alone, the combined network produces substantially fewer false alarms and superior location precision for numerous moving people than video. Recent progress in the fabrication of inexpensive, robust CMOS-based video cameras have triggered a new approach to wide area surveillance of busy areas such as modeling an airport corridor as a distributed sensor network problem. Wireless communication between these cameras …
Image Processing Techniques To Identify Predatory Birds In Aquacultural Settings, Uma Devi Nadimpalli
Image Processing Techniques To Identify Predatory Birds In Aquacultural Settings, Uma Devi Nadimpalli
LSU Master's Theses
Bird predation is a major problem in aquaculture. A novel method for dispersing birds is the use of a vehicle that can sense and chase birds. Image recognition software can improve their efficiency in chasing birds. Three recognition techniques were tested to identify birds 1) image morphology 2) artificial neural networks, and 3) template matching have been tested. A study was conducted on three species of birds 1) pelicans, 2) egrets, and 3) cormorants. Images were divided into 3 types 1) Type 1, 2) Type 2, and 3) Type 3 depending upon difficulty to separate from the others in the …
Image Quality Assessment Using Artificial Neural Networks, Alexander Havstad
Image Quality Assessment Using Artificial Neural Networks, Alexander Havstad
Theses: Doctorates and Masters
not available