Abstract Ground Penetrating Radar (GPR) Data Analysis deals with the problem of shallow subsurface imaging, which is motivated by the daily work of engineers, \eg those of municipalities.The concrete problem tackled in this thesis is motivated by the fact, that, at least in Germany, municipalities have knowledge about the existence of supply lines such as gas and water pipelines to cross and follow urban streets, while their actual position is often uncertain.The consequences are obvious:once a street undergoes maintenance works, pipes are easily broken.This also causes heavy problems to residents who are cut off from some supplies for a period of time. This thesis approaches a solution to the object detection problem in GPR data by means of (semi-)automated data analysis techniques, using Machine Learning methods.The problem is treated as a specialized problem for object detection in image data.In this application context, it is possible to integrate certain background knowledge and processing techniques in well-known Machine Learning methods. The thesis formalizes the problem first.A technical framework for the analysis of Complex Engineering Raw Data – CERD -, as a generalization of our current data at hand, will be used for all analysis methods developed.From a thorough data analysis, it becomes clear that our data labels are unsuitable for directly applying supervised Machine Learning methods.Therefore, we will be obtaining suitable ground truth data by semi-manually labeling more than 700 images by hand.The second part of the thesis presents both, supervised and unsupervised Machine Learning techniques for the detection of buried object locations.Techniques are introduced within the general context of object detection techniques within image data.The integration of geometrical background knowledge is shown to be feasible in all methods developed. This thesis will contribute in the followings: *The methodology and suitability of high-quality ground truth data for GPR data analysis is presented. *A conceptual framework along with its technical framework for the analysis of CERD is presented. *Intuitive, state of the art analysis methods for the interpretation of GPR data are presented, discussed, and evaluated. Zusammenfassung Die Bodenradaranalyse (Ground Penetrating Radar – GPR) bezeichnet ein Forschungsfeld, welches nicht-destruktive Radartechnologie einsetzt, um unterirdische Strukturen sichtbar zu machen.Diese Arbeit beschäftigt sich mit dem Teilbereich der unterirdischen Leitungsortung unter Zuhilfenahme überwachter maschineller Lernverfahren (Machine Learning Methoden).Halb-automatische Lernverfahren werden eingesetzt, da es sich um sehr große Datenmengen handelt, die derzeit noch vorwiegend händisch von Ingenieuren analysiert werden.Dieses stellt wesentliche Zeit-, Kosten- und Fehlerfaktoren dar, welche es zu optimieren gilt.Eine manuelle Bestimmung auf Basis bestehender Versorgungsleitungspläne ist besonders in Deutschland nicht möglich, da diese auf teilweise mehrere Meter ungenau und unter Umständen sogar unvollständig sind. Diese Doktorarbeit versucht, die Analyse von Bodenradardaten mit Hilfe überwachter Lernverfahren des `Machine Learnings’ zu automatisieren.Das allgemeine Vorgehen orientiert sich dabei an bekannten Bildverarbeitungsmethoden.Domänenspezifische Eigenschaften werden als Hintergrundwissen in die angewandten Verfahren integriert. Diese Arbeit besteht im wesentlichen aus zwei Teilen.Der erste Teil, bestehend aus den Kapiteln eins bis vier, führt die Problemstellung ein (Kapitel eins) und formalisiert diese (Kapitel zwei).Kapitel drei definiert den technischen Rahmen.Die vorliegenden Daten werden in Kapitel vier analysiert und vorverarbeitet.Aufgrund anwendungsspezifischer Besonderheiten wird in Kapitel fünf eine Methode dargestellt und eingesetzt, um qualitativ hochwertige Annotationen zu gewinnen, die die Grundlage für zu entwickelnde Analyseverfahren darstellt.Der zweite Teil präsentiert und analysiert die Qualität von unüberwachten (Kapitel sieben) und überwachten (Kapitel sechs, acht, neun) Lernverfahren.Hintergrundwissen wird, wann immer möglich, für eine Qualitätsverbesserung integriert. Die wesentlichen Inhalte dieser Arbeit sind folgende: *Hochwertige Annotationen für komplexe Sensordaten werden erhoben und aus verschiedenen Perspektiven verglichen und analysiert. *Ein konzeptuelles Framework für die Analyse komplexer Sensordaten wird präsentiert und prototypisch implementiert. *Intuitive Verfahren für die Bodenradar-Datenanalyse werden entwickelt, angepasst, vorgestellt und qualitativ verglichen.

A real-world guide to practical applications of ground penetrating radar (GPR) The nondestructive nature of ground penetrating radar makes it an important and popular method of subsurface imaging, but it is a highly specialized field, requiring a deep understanding of the underlying science for successful application. Introduction to Ground Penetrating Radar: Inverse Scattering and Data Processing provides experienced professionals with the background they need to ensure precise data collection and analysis. Written to build upon the information presented in more general introductory volumes, the book discusses the fundamental mathematical, physical, and engineering principles upon which GPR is built. Real-world examples and field data provide readers an accurate view of day-to-day GPR use. Topics include: 2D scattering for dielectric and magnetic targets 3D scattering equations and migration algorithms Host medium characterization and diffraction tomography Time and frequency steps in GPR data sampling The Born approximation and the singular value decomposition The six appendices contain the mathematical proofs of all examples discussed throughout the book. Introduction to Ground Penetrating Radar: Inverse Scattering and Data Processing is a comprehensive resource that will prove invaluable in the field.

Advances in Near-surface Seismology and Ground-penetrating Radar (SEG Geophysical Developments Series No. 15) is a collection of original papers by renowned and respected authors from around the world. Technologies used in the application of near-surface seismology and ground-penetrating radar have seen significant advances in the last several years. Both methods have benefited from new processing tools, increased computer speeds, and an expanded variety of applications. This book, divided into four sections--"Reviews," "Methodology," "Integrative Approaches," and "Case Studies"--Captures the most significant cutting-edge issues in active areas of research, unveiling truly pertinent studies that address fundamental applied problems. This collection of manuscripts grew from a core group of papers presented at a post-convention workshop, "Advances in Near-surface Seismology and Ground-penetrating Radar," held during the 2009 SEG Annual Meeting in Houston, Texas. This is the first cooperative publication effort between the near-surface communities of SEG, AGU, and EEGS. It will appeal to a large and diverse audience that includes researchers and practitioners inside and outside the near-surface geophysics community. --Publisher description.

Data analysis, machine learning and knowledge discovery are research areas at the intersection of computer science, artificial intelligence, mathematics and statistics. They cover general methods and techniques that can be applied to a vast set of applications such as web and text mining, marketing, medicine, bioinformatics and business intelligence. This volume contains the revised versions of selected papers in the field of data analysis, machine learning and knowledge discovery presented during the 36th annual conference of the German Classification Society (GfKl). The conference was held at the University of Hildesheim (Germany) in August 2012. ​

Ground-penetrating radar is a near-surface geophysical technique that can provide three-dimensional maps and other images of buried archaeological features and associated stratigraphy in a precise way. This revised edition, by the expert in the field, provides the basics of the physics, chemistry, geology, and archaeology in a clear fashion, unburdened by complex equations or theory. Additions to the forth edition include: Updates to recent hardware and software advances in three-dimensional antenna array systems and antenna offset technology; Expanded data processing methods that explains how to get more from your raw data, with examples to show why this is necessary and the results obtained; Expanded examples from around the world and in various environmental settings that explains how non-traditional data analysis steps can provide clarity to results in ways that are not usually done with traditional. The reader will be able to understand how the latest equipment and software and the results of data collection and processing can be used effectively in a number of different settings. Both potential pitfalls and successes and the reasons for them are discussed. With over 100 images and important tables and graphs, this book is a useful reference in the field and for data processing in GPR.

This book offers an overview of modern advances in Ground Penetrating Radar (GPR) for the reader hoping to understand comprehensive electromagnetic culture, combining instrumental development of radar, signal processing, imaging, and calibration/correction of measured data. GPR has a multi-disciplinary character that can bring together a diverse and broad community. Of concern are the design and optimization of innovative radars, by virtue of the antennas and associated electronics, imaging algorithms, methodological diversity, calibration procedures, and the development of tools for the interpretation of data in mono-static or multi-static configurations within frequency or transient domains. This book provides illustrations in civil engineering for the diagnosis of transport infrastructures and buildings, archeological surveys for the appreciation of cultural heritage, detection of underground pipes and cavities, estimation of soil water content for agriculture, and mapping of root trees developing underground, and in planetology, the analysis of the internal structure of planets and other celestial bodies through electromagnetic waves.

Ground-penetrating radar (GPR) is a rapidly developing field that has seen tremendous progress over the past 15 years. The development of GPR spans aspects of geophysical science, technology, and a wide range of scientific and engineering applications. It is the breadth of applications that has made GPR such a valuable tool in the geophysical consulting and geotechnical engineering industries, has lead to its rapid development, and inspired new areas of research in academia. The topic of GPR has gone from not even being mentioned in geophysical texts ten years ago to being the focus of hundreds of research papers and special issues of journals dedicated to the topic. The explosion of primary literature devoted to GPR technology, theory and applications, has lead to a strong demand for an up-to-date synthesis and overview of this rapidly developing field. Because there are specifics in the utilization of GPR for different applications, a review of the current state of development of the applications along with the fundamental theory is required. This book will provide sufficient detail to allow both practitioners and newcomers to the area of GPR to use it as a handbook and primary research reference. *Review of GPR theory and applications by leaders in the field*Up-to-date information and references*Effective handbook and primary research reference for both experienced practitioners and newcomers