PROGRAM:
MONDAY: RS for Forest Inventory/Machine Learning
- 8:30 Registration
- 9:00 Opening Session
- 9:15 Luka Jurjevic / Ivan Balenovic
- 10:30 Coffee break
- 10:45 Luka Jurjevic / Ivan Balenovic
- 12:30 Lunch
- 14:00 Selim Aksoy
- 15:30 Coffee break
- 15:45 Selim Aksoy
- 17:00 Icebreaker
TUESDAY: LiDAR
- 9:00 Xinlian Liang
- 10:30 Coffee break
- 10:45 Xinlian Liang
- 12:30 Lunch
- 14:00 Yunsheng Wang
- 15:30 Coffee break
- 15:45 Yunsheng Wang
- 17:30 Class ends / Poster Session
- 19:00 Zadar @ night
WEDNESDAY:Trip to PAG
- 9:00 Field trip toPag
- 10:30 Drone data acquisition – Balenovic, Jurjevic and Zoric
- 12:30-2:00 Lunch
- Pag Island Sightseeing
- 17:00 Return
THURSDAY: SAR
- 8:00 ! Mattia Callegari
- 10:30 Coffee break
- 10:45 Mattia Callegari
- 12:30 Lunch
- 14:00 Mattia Callegari
- 16:00 Class ends
- 20:30 Social dinner
FRIDAY: Drone
- 9:00 Luka Jurjevic / Joaquim Sousa
- 10:30 Coffee break
- 10:45 Joaquim Sousa
- 12:30 Lunch
- 14:00 Joaquim Sousa
- 15:30 Coffee break
- 15:45 Joaquim Sousa
- 18:00 Class ends
SATURDAY: Hyperspectral RS
- 9:00 Jochem Verrelst
- 10:30 Coffee break
- 10:45 Jochem Verrelst
- 12:30 Class ends
Expand each day for more information !
TOPICS AND PRESENTERS!
Jochem Verrelst
The ARTMO toolbox for analyzing and
processing of hyperspectral data
Luka Jurjevic and Ivan Balenovic
Remote Sensing for Forest Inventory
Claudia Notarnicola
Biophysical parameters from remotely
sensed imagery as a tool for monitoring
and evaluating ecosystem biodiversity
Yunsheng Wang and Xinlian Liang
Hands-on lecture on LiDAR data
processing and applications
Joaquim J. Sousa
Remote Sensing from Unmanned Aerial
Vehicles: A Review Focusing on the
Data, Processing and Potentialities
Mattia Callegari
Basics on SAR with a practical session
on preprocessing of SAR image
Selim Aksoy
Pattern Recognition and Machine
Learning for Remote Sensing
Ivan Balenovic, Luka Jurjevic and Nikola Zoric
Drone Data Acquisition
2022 POSTER CONTEST – BRING YOUR POSTER!
Discuss your project and poster with remote sensing experts.
ABSTRACTS:
Xinlian Liang and Yunsheng Wang
Hands-on lecture on LiDAR data processing and applications
This lecture will focus on laser scanning (LiDAR) as a rapidly developing 3D remote sensing technology. Main topics will cover four main topics including:
1) Technical background of laser scanning,
2) Development of laser scanning (LS) and its verities, such as terrestrial laser scanning (TLS), airborne laser scanning (ALS), mobile/portable laser scanning (MLS/PLS), and UAV laser scanning (UAV-LS),
3) Data collection with different LS systems and the basic characters of different types of LS data,
4) Applications of LS and fundamentals of point cloud processing.
A practical exercise will be provided for basic point cloud data loading, display, and simple processing using MATLAB. Students can start with zero knowledge on LiDAR but would require basic understanding of programming. The lecture will offer an insight understanding of typical characteristics of LS systems and their datasets, and a general concept of point cloud data processing.
Joaquim J. Sousa
Remote Sensing from Unmanned Aerial Vehicles: A Review Focusing on the Data, Processing and Potentialities
Remote Sensing (RS) provides several techniques that are able to measure different Earth physical properties using reflected or emitted energy, at a given time or period. Traditional RS technologies encompass satellite and manned aircraft platforms. These platforms are continuously improving in terms of spatial, spectral, and temporal resolutions. At its current stage, RS has been strongly influenced by the significant progress in several technologies, such as advanced data processing techniques, Geographical Information Systems and Global Navigation Satellite Systems, which contributed to improve and expand RS for all kind of applications.
The high spatial and temporal resolutions, flexibility and much lower operational costs make Unmanned Aerial Vehicles (UAVs) a good alternative to traditional RS platforms for a huge diversity of applications (agriculture, forestry, archeology, conservations, constructions, law enforcement, etc.). In those applications, UAV is one of the most suitable options to consider, mostly due to: (1) low material and operational costs and high-intensity data collection; (2) its capacity to host a wide range of sensors that could be adapted to be task-oriented; (3) its ability to plan data acquisition campaigns in a flexible manner, avoiding inadequate weather conditions and providing data availability on-demand and; (4) the possibility to be used in real-time operations.
This workshop aims to provide participants with the most significant UAV applications, identifying the appropriate sensors to be used in each situation as well as the data processing techniques commonly implemented.
Selim Aksoy
Pattern Recognition and Machine Learning for Remote Sensing
The constant increase in the amount of remotely sensed images as well as the urgent need for the extraction of useful information from such data sets have made the development of new pattern recognition and machine learning techniques a popular research topic for several decades. The complexity of the image content with high spectral as well as high spatial resolution necessitates a good understanding of both the
advantages and the limitations of the available methods. In this session, we will cover fundamentals of topics such as Bayesian decision theory, parametric and non-parametric density estimation, feature reduction and selection, non-Bayesian classification, clustering, and deep learning, through theoretical and hands-on lectures. We will also discuss quantitative performance evaluation methods.
Ivan Balenović, Luka Jurjević
Remote sensing for forest inventory
Sustainable forest management for the realization of their multiple functions and services requires spatially explicit information about their state and development, which is usually acquired through forest inventories. Although traditional field-based forest inventory can provide relatively accurate information, the process is time-consuming and labor intensive, and in some cases, access to certain areas is not possible. Therefore, the potential of remote sensing application in forest inventory has long been recognized by both researchers and practicing foresters. Over the last few decades, a rapid development of different remote sensing instruments has resulted in the development of various methods and techniques for retrieval of forest information from remote sensing data.
This lecture will provide:
- General insight in current field-based forest inventory;
- Overview of various pasive and active remote sensing technologies (platforms, sensors, products) that can be applied in forest inventory;
- Insight in methodologies for remote sensing-based forest inventory;
- Examples of previosly conducted studies and guidelines for further development of remote sensing-based forest inventory.
Mattia Callegari
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
Claudia Notarnicola
Biophysical parameters from remotely sensed imagery as a tool for monitoring and evaluating ecosystem biodiversity
Today together with Essential Climate Variable, it has started the process of the definition of Essential Biodiversity Variable which can support the monitoring and protection of ecosystem biodiversity.
In this context, the benefits of remotely sensed imagery for biodiversity indicators are related to the synoptic view, regular and repeatable acquisitions, multi-annual time series of observations and cost-effectiveness for remote and inaccessible areas. Moreover, the new satellite sensors (such as the Sentinel family) are notably increasing the remote sensing capabilities. Such large data availability has determined the necessity to develop accurate and robust retrieval methods to improve the estimation of these variables from remotely sensed imagery.
The retrieval process of these parameters from satellite images (optical and radar) is typically a challenging task and it falls in the category of ill-posed problem. This means that beyond the non-linearity of the relationship between input features (sensor measurements) and the target variables (soil moisture, biomass, etc.), more than one combination of soil characteristics may lead to the same electromagnetic response at the sensor. Furthermore, given a scene of interest, each system will provide information on a different aspect of the phenomena at the ground (e.g., the spatial patterns or the temporal dynamic) and could be also affected on different extents by different disturbing factors.
This suggests the importance of a synergic use of multiple available remote sensing systems (from satellite to drone based sensors) for a comprehensive, accurate and robust understanding and monitoring of the natural processes at the ground. On the other side the proper selection of the retrieval approach is a key issue.
In this context, the seminar will present currently available techniques for the retrieval of biophysical parameters from remotely sensed data addressing inversion of physical-based models, parametric and non-parametric approaches such as Bayesian procedure, Neural Networks, Support Vector Regression and Ensemble techniques. Each approach will be presented in specific applications indicating advantages, disadvantages and perspectives for the upcoming missions such as Sentinel 1 and 2. In addition the synergic use of different sensors (optical and radar) will be specifically addressed in the context of the retrieval process.
Jochem Verrelst
The ARTMO toolbox for analyzing and processing of hyperspectral data
This tutorial will focus on the use of ARTMO’s (Automated Radiative Transfer Models Operator) radiative transfer models (RTMs), retrieval toolboxes and post-processing tools (https://artmotoolbox.com/) for the generation and interpretation of hyperspectral data. ARTMO brings together a diverse collection of leaf, canopy and atmosphere RTMs into a synchronised user-friendly GUI environment. Essential tools are provided to create all kinds of look-up tables (LUT). These LUTs can then subsequently be used for mapping applications from optical images. A LUT, or user-collected field data, can subsequently be inserted into three types of mapping toolboxes: (1) through parametric regression (e.g. vegetation indices), (2) nonparametric methods (e.g. machine learning methods), or (3) through LUT-based inversion strategies. In each of these toolboxes various optimization algorithms are provided so that the best-performing strategy can be applied for mapping applications. When coupled with an atmosphere RTM retrieval can take place directly from top-of-atmosphere radiance data.
Further, ARTMO’s RTM post-processing tools include: (1) global sensitivity analysis, (2) emulation, i.e. approximating RTMs through machine learning, and (3) synthetic scene generation.
The proposed tutorial will consist of a theoretical introduction and a practical session, where the following topics will be addressed:
- Basics of leaf, canopy and atmosphere RTMs: generation of RTM simulations
- Overview of retrieval methods: parametric, nonparametric, inversion and hybrid methods.
- Principles of emulation of hyperspectral data, and applications such as global sensitivity analysis and scene generation.
In the practical session we will learn to work with the ARTMO toolboxes. They provide practical solutions dealing with the abovementioned topics. Step-by-step tutorials, demonstration cases and demo data will be provided. No prior knowledge is needed, however for the practical Matlab in Windows is required. In case no Matlab is available, students will be asked to team up in small groups.