Open Access. Powered by Scholars. Published by Universities.®
- Publication
- Publication Type
Articles 1 - 3 of 3
Full-Text Articles in Engineering
Deep Learning For Compressive Sar Imaging With Train-Test Discrepancy, Morgan R. Mccamey
Deep Learning For Compressive Sar Imaging With Train-Test Discrepancy, Morgan R. Mccamey
Browse all Theses and Dissertations
We consider the problem of compressive synthetic aperture radar (SAR) imaging with the goal of reconstructing SAR imagery in the presence of under sampled phase history. While this problem is typically considered in compressive sensing (CS) literature, we consider a variety of deep learning approaches where a deep neural network (DNN) is trained to form SAR imagery from limited data. At the cost of computationally intensive offline training, on-line test-time DNN-SAR has demonstrated orders of magnitude faster reconstruction than standard CS algorithms. A limitation of the DNN approach is that any change to the operating conditions necessitates a costly retraining …
Two Image Watermarkingmethodsbased On Compressive Sensing, Yidi Miao, Lü Ju, Xiumei Li
Two Image Watermarkingmethodsbased On Compressive Sensing, Yidi Miao, Lü Ju, Xiumei Li
Journal of System Simulation
Abstract: As an emerging sample theory, compressive sensing attracts wide attention because it breaks through the Nyquist sampling theorem. , Two different methods of watermark embedding and extraction are presented by measuring the carrier image and watermark image respectively based on compressive sensing. Moreover, the attack tests, such as the Gaussian noise, pepper and salt noise, filtering, compression, and cropping, are implemented to watermarked images. Experiment results show that although the two different methods for image watermarking have different processing procedure, both can guarantee the robustness and security of embedded digital watermark.
Improving Performance Of Indoor Localization Using Compressive Sensing Andnormal Hedge Algorithm, Saeid Hassanhosseini, Mohammad Reza Taban, Jamshid Abouei, Arash Mohammadi
Improving Performance Of Indoor Localization Using Compressive Sensing Andnormal Hedge Algorithm, Saeid Hassanhosseini, Mohammad Reza Taban, Jamshid Abouei, Arash Mohammadi
Turkish Journal of Electrical Engineering and Computer Sciences
Accurate indoor localization technologies are currently in high demand in wireless sensor networks, which strongly drive the development of various wireless applications including healthcare monitoring, patient tracking and endoscopic capsule localization. The precise position determination requires exact estimation of the time varying characteristics of wireless channels. In this paper, we address this issue and propose a three-phased scheme, which employs an optimal single stage TDOA/FDOA/AOA indoor localization based on spatial sparsity. The first contribution is to formulate the received unknown signals from the emitter as a compressive sensing problem. Then, we solve an $\ell_1$ minimization problem to localize the emitter's …