PROGRAM:
MONDAY: SAR Day
- 8:45 Registration
- 9:15 Opening Session
- 9:30 Opening Scientific Talk by prof. Roland Psenner:
Climate Change at High Elevations – The Last 11,000 Years - 10:00 Coffee break
- 10:15 Basics on SAR with a practical session on preprocessing of SAR image
- 12:30 Lunch
- 2:00 Basics on SAR with a practical session on preprocessing of SAR image
- 6:00 End of classes
- 7:00 Alto Adige Icebreaker of Bolzano
TUESDAY: Corvara Trip
- 9:00 Leave for the field trip to Corvara
- 12:30-2:00 Lunch
- 6:00 Return
WEDNESDAY:LiDAR Day
- 9:00 Hands-on course on LiDAR processing with LAStools
- 10:30 Coffee break
- 10:45 Hands-on course on LiDAR processing with LAStools
- 12:30 Lunch
- 2:00 Hands-on course on LiDAR processing with LAStools
- 3:30 Coffee break
- 3:45 Hands-on course on LiDAR processing with LAStools
- 6:00 End of classes and Poster Session
THURSDAY: Land Cover Day
- 9:00 Land cover mapping based on optical and radar images
- 10:30 Coffee break
- 10:45 Land cover mapping based on optical and radar images
- 12:30 Lunch
- 2:00 Land cover mapping based on optical and radar images
- 3:30 Coffee break
- 3:45 Land cover mapping based on optical and radar images
- 6:00 End of classes
FRIDAY: UAV & Deep Learning Day
- 9:00 Landslide monitoring using UAVs
- 10:30 Coffee break
- 10:45 Landslide monitoring using UAVs
- 12:30 Lunch
- 2:00 Deep Learning for Earth Remote Sensing
- 3:30 Coffee break
- 3:45 Deep Learning for Earth Remote Sensing
- 6:00 End of classes
SATURDAY: Hyperspectral Day
- 9:00 Mapping mountain areas with hyperspectral data
- 10:30 Coffee break
- 10:45 Mapping mountain areas with hyperspectral data
- 12:30 Concluding remarks
- 12:45 Lunch
- 2:00 Visit to South Tyrol Museum of Archaeology
Expand each day for more information !
TOPICS AND PRESENTERS!
Opening Scientific Talk by the President of Eurac Research prof. Roland Psenner:
Climate Change at High Elevations – The Last 11,000 Years
Martin Isenburg
Hands-on course on LiDAR processing with LAStools
Ribana Roscher
Deep Learning for Earth Remote Sensing
Alexander Jacob & Ruth Sonnenschein
Land cover mapping based on optical and radar images
Mattia Callegari & Giovanni Cuozzo & Carlo Marin
Basics on SAR with a practical session on preprocessing of SAR image
Giovanni Cuozzo & Christian Kofler & Abraham Mejia-Aguilar & Stefan Steger
Field Trip To Corvara – Drone flight
Abraham Mejia-Aguilar
Landslide monitoring using UAVs
Monica Pepe and Loredana Pompilio
Mapping mountain areas using hyperspectral data
BRING YOUR POSTER!
Discuss your project and poster with remote sensing experts. A cash prize of €200 will be awarded to the author of the winning poster.
ABSTRACTS:
Martin Isenburg
Hands-on Course to LiDAR processing with LAStools
This course will include both theoretical and hands-on lectures on the LiDAR processing tools, which are widely known for their blazing speeds and high productivity. The software combines robust algorithms with efficient I/O and clever memory management to achieve high throughput for data sets containing billions of points. The LAStools software suite has deep market penetration and is heavily used in the commercial sector, government agencies, research labs, and educational institutions alike — filtering, tiling, rasterizing, triangulating, converting, clipping, quality-checking, etc. More information can be found at: http://rapidlasso.com/2015/09/21/creating-dtms-from-dense-matched-points-of-uav-imagery-from-senseflys-ebee/
Ribana Roscher
Deep Learning for Earth Remote Sensing
Advances in the field of deep learning have led to a development in machine learning methods such as deep neural networks, which outperform classical methods in many fields. One of the main reasons of their success is the ability to uncover hidden and complex structures in the data, where layered architectures are employed to extract a deep and rich hierarchical feature representation, which is particularly suitable for solving certain tasks. Also the remote sensing community started to use deep learning approaches for their application tasks including land cover classification and forecasting of bio- and geophysical parameters. This course will include both a lecture about fundamental and advanced concepts in deep learning and a hands-on session demonstrating practical aspects.
Alexander Jacob and Ruth Sonnenschein
Land cover mapping based on optical and radar images
This training session focus on satellite-based land cover mapping using optical and radar images. The session starts with a theoretical part on land cover classification, which gives an overview on the opportunities that remote sensing data and their synergies offer for land cover mapping. It will then continue with an in-depth discussion about the various components that have an impact on the result such as remote sensing data selection, preprocessing, classification strategy, choice of classifier, quality and quantity of reference data, sampling strategies and accuracy estimation. In the last part of the session the participants will work on a practical exercise and derive a land cover map using Sentinel-1 and Sentinel-2 data.
Mattia Callegari & Giovanni Cuozzo & Carlo Marin
Basics on SAR with a practical session on preprocessing of SAR image
Synthetic aperture radar (SAR) are active systems that exploit an electromagnetic wave in the microwave spectrum to characterize the geometric and dielectric characteristics of a target object. The active nature and the working frequency of the SAR systems render them independent from the sunlight and almost insensitive to the presence of clouds. Therefore, SAR is of paramount importance from an application point of view.This lecture provides the basic notions on Synthetic Aperture Radar, including an introduction on SAR interferometry, SAR data processing and examples of applications exploiting past and current SAR satellite missions.
- SAR basics
- SAR Interferometry
- SAR processing
- SAR missions
- SAR application
Giovanni Cuozzo & Christian Kofler & Abraham Mejia-Aguilar & Stefan Steger
Field trip to Corvara & drone flights
Landslide monitoring using UAVs flight and hands-on session
The field trip will lead us to the Corvara landslide. After an introduction to the environmental context of this complex phenomena (e.g. geomorphology, movement dynamics), past and current monitoring activities (i.e. in-situ measurements, UAV and remote sensing based monitoring) will be explained in the field. An introduction to multitemporal SAR interferometry will be also carried out prior to the trip.On-site discussions on the currently installed instrumentation (e.g. corner reflectors, GPS stations) and on associated research activities will give insights into the potentials and limitations of above-ground displacement monitoring of large and complex landslides. During the field trip, a flight with a drone will be carried out.The participant will learn how to plan and conduct an UAV flight campaign by using and applying some specific instrumentation and techniques. We will collect the necessary data to process and obtain high resolution digital elevation models (DEMs).
Finally, we will use the updated DEMs to compare with previous campaigns in order to create Digital Models of Differences (DoD) that quantifies the volumetric change between successive topographic surveys.The acquired images will be analyzed to understand the landslides movement in a practical session the day or two after the trip. This practical session focuses on monitoring mass movements, particularly on landslides, by evaluating proximal and ground sensing methods.
Monica Pepe and Loredana Pompilio
Mapping mountain areas using hyperspectral data
Hyperspectral remote sensing is receiving an increasing interest both in the scientific community and at the decision making level, especially for its versatility and effectiveness in the characterization of surfaces. Hyperspectral sensors typically collect measurements in hundreds of narrow and contiguous spectral bands within the visible, near-infrared and short wavelength infrared intervals, thus allowing to quickly collect significant information about the target materials, even at subtle scales of investigation. For these reasons, hyperspectral sensing has been successfully applied in laboratory, field and remote studies, and addressed to different disciplines (e.g., geology, agricolture, cultural heritage, landscape sciences) and planetary surfaces, as well (e.g., Earth, Mars, small Solar System Objects). This course will basically focus on the principles of hyperspectral remote sensing in the reflectance domain, including examples of data analysis techniques, classification and applications to real contexts, especially targeted to the alpine environment. The main goal is to provide the end-users with the basic knowledge of hyperspectral sensing and how it could be used for mapping tasks in a mountain environment.
Note that field hyperspectral data using hand-held spectroradiometer will be collected during the field trip to Corvara. Data will be analysed during the hyperspectral session.