Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 20 for “"MSTAR"”.
-
Application of Semantic Segmentation to an Automatic Target Recognition Problem
… Stationary Target Acquisition and Recognition (MSTAR) Mixed Target dataset. This research proposes a robust classification pipeline with the addition of a semantic segmentation model. The result is a classification model that is trained to extract identification features from only target and …
-
DATA AUGMENTATION FOR SYNTHETIC APERTURE RADAR USING ALPHA BLENDING AND DEEP LAYER TRAINING
… both real and synthetic single-object chips, and MSTAR Clutter, which is composed of real wide-FOV SAR images. Synthetic objects are extracted from SAMPLE using threshold-based segmentation before being alpha-blended onto patches from MSTAR Clutter. To validate the novel synthesis method, …
-
The Evolution of and Starburst-AGN Connection in Luminous and Ultraluminous Infrared Galaxies and their Link to Globular Cluster Formation
… the SFR, AGN contribution, D4000, stellar mass (Mstar), young stellar population age (i.e. the age of the most recent starburst activity), starburst mass fraction, luminosity absorbed by dust, and stellar mass-weighted age. Comparing the properties of the IR power sources in U/LIRGs with …
-
Discovery and characterization of substellar companions in stellar clusters using Karhunen-Loève Image Processing of HST data
… rates in the ONC up to-date. The dMacc - Mstar relationship exhibits two different regimes. On one side, we observe that more massive stars (Mstar > 0.3 Msun) display a rather shallow linear relation that agrees with that predicted in the context of centrally irradiated accretion disks …
-
Low-complexity convolutional neural networks for automatic target recognition
… a classification accuracy of >99% on the MSTAR dataset.
-
ATREngine: An Orientation-Based Algorithm for Automatic Target Recognition
… Stationary Target Acquisition and Recognition (MSTAR) database, target orientation was determined to be the best feature for ATR. A rotationally variant algorithm taking advantage of the combination of target orientation and pixel location for classification is proposed in this thesis. Extensive …
-
THE USE OF GENERATIVE ADVERSARIAL NETWORKS WITH THE MOVING AND STATIONARY TARGET ACQUISITION AND RECOGNITION DATASET
… An unconditional GAN was trained on the public MSTAR dataset and its generator network produced additional target chips that also mirrors real radar phenomenology. Two augmentation strategies were compared in our study. First, 17,000 synthetic images were indiscriminately merged with the eight …
-
AUTOENCODER-ENHANCED CONVOLUTIONAL NEURAL NETWORKS FOR TARGET RECOGNITION IN SYNTHETIC APERTURE RADAR IMAGERY
… Robustness was systematically tested using the MSTAR dataset with synthetically introduced speckle noise across a wide range of variances. Results demonstrate that while the baseline CNN collapses rapidly under noise, often defaulting to classes with dominant features, the AE-CNN sustains …
-
APPLYING DEEP LEARNING METHODS TO IDENTIFY TARGETS IN SYNTHETIC APERTURE RADAR IMAGES
… Target Acquisition and Recognition program (MSTAR). In this research, the SAR ATR concept and performance are analyzed using several CNN DL architectures. Specifically, this investigation examines the effects of a few variable parameters within CNN DL architectures to gain insight into …
-
Three-Dimensional Target Modeling with Synthetic Aperture Radar
… The radar shadow present in SAR images of MSTAR vehicle targets is extracted and used in conjunction with the radar beam depression angle to compute physical target heights along the range axis. Multiple inputs of elevation data are then merged to forge rough 3-D target models. The project …
-
Mixing processes in anti-solvent crystallisation
… of the system was modelled and simulated on Mstar CFD to predict mixing times. Local and global mixing times were calculated by using a simulated probe, and the tracer concentration relative standard deviation throughout the vessel respectively. Firstly, The predicted variability of mixing …
-
Low Surface Brightness Galaxies and the Galaxy Stellar Mass Function
… Mass Assembly (GAMA) survey down to a mass of $\mstar = 10^{8}\,\msun$. Below this mass the values produced so far can only be taken as lower limits on the distribution. One source of this incompleteness is failing to account for undetected low-surface-brightness galaxies (LSBGs) within the …
-
The interplay between the evolution and dynamics of stellar systems
… in conjunction with the $N$-body code \texttt{MSTAR}, I accurately classified triples and quadruples as stable or unstable by assessing their long-term boundedness. Specifically for triples, I refined and enhanced the accuracy of an existing analytical classification formula. This study sheds …
-
The Role of AGN and Bulges in Quenching the Galaxy Main Sequence
… ~60% of all star-formation in massive galaxies (Mstar > 10^10.5 Msun) is associated with galaxies whose optical diagnostic emission lines classify them as AGN - Composites (C), Seyferts (S), or LINERs (L). These AGN form a ‘quenching sequence’ of decreasing mean star-formation (C → S →L), which …
-
Synthetic Aperture Radar Imaging Simulated in MATLAB
… Surveillance and Target Acquisition Radar (MSTAR) images as most SAR images for military ATR are not released for public use. Also, with an in-house SAR image generation scheme the parameters of noise, target orientation, the elevation angle or look angle to the antenna from the target and …
-
Automatic target recognition using passive bistatic radar signals
… extra-trees method on the radar images of the MSTAR dataset, featuring ground vehicles. We then test the method on the images of the airplanes constructed from data acquired in the anechoic chamber, achieving a probability of correct recognition up to 0.99. We test the subspace methods on the …
-
High Resolution Simulation of Synthetic Aperture Radar Imaging
… Target Acquisition and Recognition Radar (MSTAR) images. Due to the unavailability of radar equipment or a greater range of SAR data, it has been necessary to create a SAR image generation scheme in which the parameters of the radar platform can be directly modified and controlled to be …
-
Transient variability and variability of massive stars with the Hubble space telescope
Massive stars (stars with Mstar >8 M⊙) are among the most enigmatic types of stars.They lie at the upper part of the Hertzsprung-Russell diagram and despite their scantnumber they play a major role in the evolution of the Universe. They are the progenitorsof various sub-classes of supernovae, …
-
The first H II regions in the universe
… from 2000 pc to 5000 pc in radius for 80 M < Mstar < 500 M . Of equal interest, they show the rise of shocked ionized flows capable of ejecting half of the baryons from the halo over the main sequence lifetime of the star, with important consequences to chemical enrichment of the early IGM and …
-
A multi-wavelength study of the interstellar medium in active galactic nuclei at cosmic noon
… is especially significant at high masses, log(Mstar) > 11. These observations demonstrated that the AGN may have an effect on the ISM of the hosts, although the exact mechanisms in place require further observations to be understood. These projects set the scene for future investigations, which …