Master- und Aufbaustudiengänge

Beschreiben Sie kurz und prägnant, worum es in diesem Kurs geht.

Due to the technological advances in hardware and compute power nowadays the visual data is collected in huge amounts practically by everyone. The digital cameras are pervasive. Most of the smart devices include camera sensors and are capable of capturing stills and videos. With these large amounts of visual data there is a pressing need to automatically process, organize, interpret the data and refine the visual data in ways that humans are capable of. How to achieve such goals? What are the challenges? What are the solutions? What is state-of-the-art? How can we further improve the state-of-the-art? In this Praktikum Image Processing and Computational Photography, we work in groups (1 to maximum 3 participants per each group), hands-on, and for several image processing and computational photography tasks we review, explore and master the state-of-the-art under the form of the best open source solutions and further assess the pluses and minuses of these solutions and propose alternatives. Each participant will work on a specific computational photography topic of interest.

Beschreiben Sie kurz und prägnant, worum es in diesem Kurs geht.

Due to the technological advances in hardware and compute power nowadays the visual data is collected in huge amounts practically by everyone. The digital cameras are pervasive. Most of the smart devices include camera sensors and are capable of capturing stills and videos. With these large amounts of visual data there is a pressing need to automatically process, organize, interpret the data and refine the information in ways that humans are capable. Computer Vision is asked to provide such solutions.

How to achieve such goals? What are the challenges? What are the solutions? What is state-of-the-art? How can we further improve the state-of-the-art?

In this Praktikum Computer Vision, we work in groups (1 to maximum 3 participants per each group), hands-on, and for several computer vision topics we review, explore and master the state-of-the-art under the form of the best open source solutions and further assess the pluses and minuses of these solutions and propose alternatives.

Each participant will work on a specific computer vision topic of interest.

Due to the technological advances in hardware and compute power nowadays the visual data is collected in huge amounts practically by everyone. The digital cameras are pervasive. Most of the smart devices include camera sensors and are capable of capturing stills and videos. With these large amounts of visual data there is a pressing need to automatically process, organize, interpret the data and refine the information in ways that humans are capable. Computer Vision is asked to provide such solutions. How to achieve such goals? What are the challenges? What are the solutions? What is state-of-the-art? What are the benefits? What is the societal impact? How can we further improve the state-of-the-art? In this seminar, we review, explore and debate such questions based on the recent research at the intersection of Machine Learning, Computer Vision, Robotics and Artificial Intelligence. Each participant will be assigned one topic from a range of computer vision topics, including but not limited to those listed below. Each participant is expected to prepare a written review report covering the state-of-the-art on the particular topic (compiled from at least two research papers) and a corresponding oral presentation. At the same time, each participant is expected to interact, read and comment on the reports provided and presented by the other participants. Each participant will get skills on critical analysis, scientific discourse, and preparation, writing, and presentation on a research topic. Moreover, the participants will get acquainted with state-of-the-art computer vision.

Computer Vision is an interdisciplinary scientific field dealing with equipping computers with high-level understanding of digital images and videos. Automatizing tasks that the human visual system can do and going beyond human abilities are main research directions. Computer Vision relates to and overlaps with research fields such as: image processing, image analysis, machine vision, machine learning, deep learning, artificial intelligence, signal processing, information engineering, computer graphics, neurobiology. This course aims at offering a self-contained account of computer vision and its underlying concepts, including the recent use of deep learning. The topics that will be covered are: introduction to computer vision, image formation, feature description, feature detection, geometry, detection, motion and tracking, traditional object recognition, deep learning, generative methods, applications. Objectives: • Overview of the most important concepts of image formation, perception and analysis, and Computer Vision. • Gaining own experience through practical computer and programming exercises. Requirements: • Basic concepts of mathematical analysis and linear algebra. • Basic concepts of physics and optics. • The computer exercises are based on Python and TensorFlow / Keras. • The course language is English.

Beschreiben Sie kurz und prägnant, worum es in diesem Kurs geht.

Beschreiben Sie kurz und prägnant, worum es in diesem Kurs geht.

Beschreiben Sie kurz und prägnant, worum es in diesem Kurs geht.

Beschreiben Sie kurz und prägnant, worum es in diesem Kurs geht.

Beschreiben Sie kurz und prägnant, worum es in diesem Kurs geht.

Beschreiben Sie kurz und prägnant, worum es in diesem Kurs geht.

Beschreiben Sie kurz und prägnant, worum es in diesem Kurs geht.

Managing scientific projects as well as project proposals and developing them towards successful science is a common task for scientists as well as practitioner. In this course different approaches will be introduced and discussed. Research does mean much more than identifying crucial research question, finding appropriate data, developing algorithms and deriving new findings. While this course will contain all mentioned issues it will beyond highlight the challenges for raising money for research, writing proposals, building up networks, writing papers and doing presentations. All topics will be introduced by the examples of currently running research projects.

This year, we will have the following sessions and guest lectureres.

• 19.04. (in person) Introduction to the seminar (Prof. Dr. Hannes Taubenböck)
• 26.04. (in person) Earth Observation for Disaster Management Support (Dr. Torsten Riedlinger)
• 03.05. (online) Managing the Center for satellite-based crisis information (ZKI) (Dr. Monika Gähler)
• 10.05. (in person) Research from an Small and Medium Company (SME) perspective… (Dr. Tobias Leichtle)
• 17.05. (online) A research career in the domain of thermal and radar remote sensing for natural hazards (Dr. Simon Plank)
• 24.05. (online) Writing a proposal for a PhD project (Jeroen Staab)
• 31.05. no seminar due to Pfingsten
• 07.06. no seminar due to Pfingsten
• 14.06. (online/in person) Dissemination of science to the public and policy makers (Dr. Nikola Sander & Martin X)
• 21.06. (online) Managing large international research projects - importance, complexity and challenges (Dr. Elisabeth Schöpfer)
• 28.06. (online) Master’s, research associate, service staff, Phd – A career at a large scale research facility (Patrick Aravena)
• 05.07. (in person) The first year of my PhD (Johannes Mast)
• 12.07. (online) Earthquakes, Earth Observation and Machine Learning – one Decade of Research (Prof. Dr. C. Geiß)
• 12.07. Submission of the project proposal
• 19.07. (in person) Presentation of the Proposals (Prof. Dr. Hannes Taubenböck)

Beschreiben Sie kurz und prägnant, worum es in diesem Kurs geht.

Beschreiben Sie kurz und prägnant, worum es in diesem Kurs geht.

Beschreiben Sie kurz und prägnant, worum es in diesem Kurs geht.

Beschreiben Sie kurz und prägnant, worum es in diesem Kurs geht.

Beschreiben Sie kurz und prägnant, worum es in diesem Kurs geht.

Beschreiben Sie kurz und prägnant, worum es in diesem Kurs geht.