Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Entire DC Network
Processing Of Wide-Angle Synthetic Aperture Radar Signals For Target Detection, Kurt W. Knurr
Processing Of Wide-Angle Synthetic Aperture Radar Signals For Target Detection, Kurt W. Knurr
Theses and Dissertations
This study investigated methods of targets detection using Wide-Angle Synthetic Aperture Radar (WASAR). WASAR uses multiple aspect angle Synthetic Aperture Radar (SAR) images of the same scene. The SAR images were generated using a pre-release software package from package from Loral Corporation. The software was able to generate 512 by 512 pixel SAR images that contained various vegetation return which for our purposes we classified as clutter. Within this clutter, targets (M35 trucks) could be placed at random location and orientations. The software also had the capability of generating fully- polarimetic WASAR images with multiple depression angles. This data was …
Three Dimensional Object Recognition Using A Complex Autoregressive Model, David E. Chelen
Three Dimensional Object Recognition Using A Complex Autoregressive Model, David E. Chelen
Theses and Dissertations
Based on an autoregressive model, Complex Partial Correlation CPARCOR features are known to provide exceptional Position, Scale, and Rotation Invariant PSRI properties for planar 2-Dimensional 2-D object recognition. Although autogressive models have been successfully applied to numerous spatio-temporal recognition tasks, the effects of out-of-plane image rotations were never considered. This study investigates application of the CPAR-COR model to a five class problem of nonplanar 2-D views of 3-D objects. Recognition based on CPAR-COR features is evaluated using a Template Matching algorithm, two K-Nearest-Neighbor KNN classifiers, and a Hidden Markov Model HMM. Direct comparisons to recognition based on Fourier features are …
Application Of Sequence Comparison Methods To Multisensor Data Fusion And Target Recognition, Edmund W. Libby
Application Of Sequence Comparison Methods To Multisensor Data Fusion And Target Recognition, Edmund W. Libby
Theses and Dissertations
This research addresses methods for exploiting the joint likelihood of observed kinematic and nonkinematic (sensor signature) physical events to improve dynamic object and target recognition. A principal direction is the application of dynamic programming sequence comparison techniques to condition matching of object signatures to known models according to observed kinematics. A second direction is the application of kinematic/aspect-angle Kalman filter trackers to condition kinematic tracking according to observed signatures. These conditioning processes dramatically reduce ambiguity in object recognition, and can be used together or separately to allow computation of a posterior probabilities of object class membership using Bayesian methods. Proposals …