FG Computer Vision & Remote Sensing

4 Items

Recent Submissions
Image-based tracking, quantification and exploration of cardiac dynamics

Tautz, Lennart (2020)

The heart is the central driver of blood circulation, which supplies the body with oxygen. Heart function is determined by a complex interaction between heart wall contraction, heart valves and respiration. Cardiac diseases and disease progression manifest often regionally and diversely across patients. Modern clinical imaging allows the acquisition of image data for the detailed assessment of...

Volcanic Hot-Spot Detection Using SENTINEL-2: A Comparison with MODIS−MIROVA Thermal Data Series

Massimetti, Francesco ; Coppola, Diego ; Laiolo, Marco ; Valade, Sébastien ; Cigolini, Corrado ; Ripepe, Maurizio (2020-03-03)

In the satellite thermal remote sensing, the new generation of sensors with high-spatial resolution SWIR data open the door to an improved constraining of thermal phenomena related to volcanic processes, with strong implications for monitoring applications. In this paper, we describe a new hot-spot detection algorithm developed for SENTINEL-2/MSI data that combines spectral indices on the SWIR ...

Exploiting SAR Tomography for Supervised Land-Cover Classification

D’Hondt, Olivier ; Hänsch, Ronny ; Wagener, Nicolas ; Hellwich, Olaf (2018-11-05)

In this paper, we provide the first in-depth evaluation of exploiting Tomographic Synthetic Aperture Radar (TomoSAR) for the task of supervised land-cover classification. Our main contribution is the design of specific TomoSAR features to reach this objective. In particular, we show that classification based on TomoSAR significantly outperforms PolSAR data provided relevant features are extract...

Classification of PolSAR Images by Stacked Random Forests

Hänsch, Ronny ; Hellwich, Olaf (2018-02-23)

This paper proposes the use of Stacked Random Forests (SRF) for the classification of Polarimetric Synthetic Aperture Radar images. SRF apply several Random Forest instances in a sequence where each individual uses the class estimate of its predecessor as an additional feature. To this aim, the internal node tests are designed to work not only directly on the complex-valued image data, but also...