User: Guest  Login
Original title:
Deep Learning in Synthetic Aperture Radar Tomographic Inversion
Translated title:
Deep Learning in der Synthetik Apertur Radar Tomographische Inversion
Author:
Qian, Kun
Year:
2024
Document type:
Dissertation
Faculty/School:
TUM School of Engineering and Design
Institution:
Data Science in Earth Observation (Prof. Zhu)
Advisor:
Zhu, Xiaoxiang (Prof. Dr. habil.)
Referee:
Zhu, Xiaoxiang (Prof. Dr. habil.); Wang, Yuanyuan (Ph.D.); Fornaro, Gianfranco (Ph.D.)
Language:
en
Subject group:
GEO Geowissenschaften
Keywords:
Synthetic Aperture Radar Tomography (TomoSAR), Deep Learning, Algorithm Unrolling, Super Resolution
TUM classification:
BAU 967; MSR 915
Abstract:
Synthetic aperture radar tomography (TomoSAR) emerges as an advanced interferometric SAR (InSAR) technique for 3D imaging as well as deformation monitoring. The state-of-the-art TomoSAR algorithms harness the capabilities of compressive sensing (CS)-based sparse reconstruction, showing unprecedented super-resolution power and location accuracy. However, the computational demands of CS-based TomoSAR algorithms render them impractical for large-scale processing. Addressing this challenge, this dis...     »
Translated abstract:
Synthetik Apertur Radar Tomographie (TomoSAR) ist eine fortgeschrittene interferometrische SAR (InSAR) Methode für die 3-D-Abbildung sowie die Deformationsüberwachung. Die modernsten TomoSAR-Algorithmen nutzen die Fähigkeiten der compressive sensing (CS) basierenden spärlichen Rekonstruktion. Diese ist jedoch aufgrund hoher rechnerischer Kosten nicht für die großflächige Verarbeitung geeignet. In Anbetracht dieser Herausforderung entwirft die vorliegende Dissertation innovative deep learning-bas...     »
WWW:
https://mediatum.ub.tum.de/?id=1721688
Date of submission:
28.09.2023
Oral examination:
18.01.2024
File size:
73246566 bytes
Pages:
136
Urn (citeable URL):
https://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:91-diss-20240118-1721688-1-3
Last change:
15.02.2024
 BibTeX