Ronny Hänsch

Ronny Hänsch
German Aerospace Center (DLR) | DLR · Microwaves and Radar Institute

Dr.-Ing.

About

106
Publications
25,027
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
951
Citations
Additional affiliations
May 2007 - present
Technische Universität Berlin
Position
  • Research Assistant
Education
October 2002 - March 2007
Technische Universität Berlin
Field of study
  • Computer Science

Publications

Publications (106)
Preprint
Random Ferns -- as a less known example of Ensemble Learning -- have been successfully applied in many Computer Vision applications ranging from keypoint matching to object detection. This paper extends the Random Fern framework to the semantic segmentation of polarimetric synthetic aperture radar images. By using internal projections that are defi...
Article
Full-text available
We present here the scientific outcomes of the 2021 Data Fusion Contest (DFC2021) organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. DFC2021 was dedicated to research on geospatial artificial intelligence (AI) for social good with a global objective of modeling the state and change...
Preprint
Full-text available
The synergistic combination of deep learning models and Earth observation promises significant advances to support the sustainable development goals (SDGs). New developments and a plethora of applications are already changing the way humanity will face the living planet challenges. This paper reviews current deep learning approaches for Earth obser...
Article
Random Ferns - as a less known example of Ensemble Learning - have been successfully applied in many Computer Vision applications ranging from keypoint matching to object detection. This paper extends the Random Fern framework to the semantic segmentation of polarimetric synthetic aperture radar images. By using internal projections that are define...
Article
Full-text available
In this paper, we elaborate on the scientific outcomes of the 2021 Data Fusion Contest (DFC2021), which was organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society, on the subject of geospatial artificial intelligence (AI) for social good. The ultimate objective of the contest was to mod...
Conference Paper
The creation of geospatial databases of large power infrastructure such as substations is essential for the planning and management of electricity transmission and distribution. Achieving this task through conventional mapping techniques involves great effort in terms of time, manpower and financial resources. Automatically extracting power infrast...
Article
Full-text available
In this paper, we introduce the 2020 Gaofen Challenge and relevant scientific outcomes. The 2020 Gaofen Challenge is an international competition, which is organized by the China High-Resolution Earth Observation Conference Committee and the Aerospace Information Research Institute, Chinese Academy of Sciences and technically co-sponsored by the IE...
Preprint
Full-text available
Annotated datasets have become one of the most crucial preconditions for the development and evaluation of machine learning-based methods designed for the automated interpretation of remote sensing data. In this paper, we review the historic development of such datasets, discuss their features based on a few selected examples, and address open issu...
Conference Paper
This paper summarizes study results obtained about the characteristics of sea ice in the Davis Strait off the coast of Baffin Island in 2019. The study, also referred to as ICESAR 2019, is based on multi-frequency and interferometric data collected by the DLR F-SAR airborne radar in the course of the PermASAR campaign in the Canadian Arctic with th...
Chapter
Context - i.e. information not contained in a particular measurement but in its spatial proximity - plays a vital role in the analysis of images in general and in the semantic segmentation of Polarimetric Synthetic Aperture Radar (PolSAR) images in particular. Nevertheless, a detailed study on whether context should be incorporated implicitly (e.g....
Article
Full-text available
This paper presents the scientific outcomes of the 2020 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The 2020 Contest addressed the problem of automatic global land-cover mapping with weak supervision, i.e. estimating high-resolution semantic maps while on...
Article
The Image Analysis and Data Fusion Technical Committee (IADF TC) of the IEEE Geoscience and Remote Sensing Society (GRSS) has organized the annual Data Fusion Contest (DFC) since 2006. The contest aims to establish new benchmarks for scientific challenges in remote sensing image analysis by promoting the use of multimodal data, leveraging new senso...
Article
Full-text available
We present the scientific outcomes of the 2019 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The contest included challenges with large-scale data sets for semantic 3D reconstruction from satellite images and also semantic 3D point cloud classification from...
Article
Full-text available
In this paper, we present the scientific outcomes of the 2019 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The 2019 Contest addressed the problem of 3D reconstruction and 3D semantic understanding on a large scale. Several competitions were organized to as...
Article
Full-text available
In the last years, vision-based systems have flourished at an unprecedented pace, fuelled by developments in hardware components (higher resolution and higher sensitivity imaging sensors, smaller and smarter micro controllers, just to name a few), as well as in software or processing techniques, with AI (Artificial Intelligence) leading to a landma...
Article
The estimation of soil permittivity under fully covered grassland is a challenging task that can be approached by either model-based polarimetric decomposition techniques or data-driven machine-learning (ML) methods. In this study, we test the benefits and limitations of those techniques when individually or jointly applied to estimate the permitti...
Conference Paper
Within the remote sensing domain, a diverse set of acquisition modalities exist, each with their own unique strengths and weaknesses. Yet, most of the current literature and open datasets only deal with electro-optical (optical) data for different detection and segmentation tasks at high spatial resolutions. optical data is often the preferred choi...
Conference Paper
Keypoints that do not meet the needs of a given application are a very common accuracy and efficiency bottleneck in many computer vision tasks, including keypoint matching and 3D reconstruction. Many computer vision and machine learning methods have dealt with this issue, trying to improve keypoint detection or the matching process. We introduce an...
Preprint
Full-text available
Within the remote sensing domain, a diverse set of acquisition modalities exist, each with their own unique strengths and weaknesses. Yet, most of the current literature and open datasets only deal with electro-optical (optical) data for different detection and segmentation tasks at high spatial resolutions. optical data is often the preferred choi...
Article
With the increasing importance of monitoring urban areas, the question arises which sensors are best suited to solve the corresponding challenges. This letter proposes novel node tests within the random forest (RF) framework, which allows them to apply them to optical RGB images, hyperspectral images, and light detection and ranging (LiDAR) data, e...
Conference Paper
In the last years, vision-based systems have flourished at an unprecedented pace, fuelled by developments in hardware components (higher resolution and higher sensitivity imaging sensors, smaller and smarter micro controllers, just to name a few), as well as in software or processing techniques, with AI (Artificial Intelligence) leading to a landma...
Article
Full-text available
The five papers in this special section focus on computer vision-based approaches for Earth observation. These papers followed a series of events promoting works at the interface between computer vision and remote sensing: the special sessions organized at the Living Planet Symposium1 and the Computer Vision and Pattern Recognition (CVPR) conferenc...
Conference Paper
The deployment of numerous air- and space-borne remote sensing sensors as well as new data policies led to a tremendous increase of available data. While methods such as neural networks are trained by online or batch processing, i.e. keeping only parts of the data in the memory, other methods such as Random Forests require offline processing, i.e....
Article
Full-text available
The extraction of heart rate and other vital parameters from video recordings of a person has attracted much attention over the last years. In this paper, we examine time differences between distinct spatial regions using remote photoplethysmography (rPPG) in order to extract the blood flow path through human skin tissue in the neck and face. We ca...
Chapter
The task of image colorization, i.e. assigninging color values to grayscale images, is usually addressed by either exploiting explicit user input or very large training data sets. In contrast, the proposed method is fully automatic and uses several orders of magnitude less training images. To this aim, a Random Forest is tailored to the task of reg...
Article
This paper presents the scientific outcomes of the 2018 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The 2018 Contest addressed the problem of urban observation and monitoring with advanced multi-source optical remote sensing (multispectral LiDAR, hyperspe...
Article
Presents information on the 2019 Data Fusion Contest.
Article
Reports on the Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee (IADFTC) of the IEEE Geoscience and Remote Sensing Society.
Article
Full-text available
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 Pol...
Conference Paper
Full-text available
Learning the proxy task of transcoding SAR images into optical images forces an employed conditional generative adversarial network (GAN) to distinguish between different land surfaces. Such a network can then be used to build a classifier with significantly fewer free parameters that generalizes well even when trained on a very small amount of lab...
Chapter
The potential to positively influence research developments in seemingly unrelated areas leads to an increasing interest in the analysis of video games. As game publishers rarely provide an open interface to gain access to in-game information, the proposed system relies on the availability of video game recordings and broadcasts and operates comple...
Article
Full-text available
Random Forests have continuously proven to be one of the most accurate, robust, as well as efficient methods for the supervised classification of images in general and polarimetric synthetic aperture radar data in particular. While the majority of previous work focus on improving classification accuracy, we aim for accelerating the training of the...
Article
Full-text available
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 dire...
Conference Paper
Full-text available
Image colorization refers to the task of assigning color values to grayscale images. While previous work is based on either user input or very large training data sets, the proposed method is fully automatic and based on several orders of magnitude less training data. A Random Forest variation is tailored towards the regression task of estimating t...
Conference Paper
Full-text available
Data used to train models for semantic segmentation have the same spatial structure as the image data, are mostly densely labeled, and thus contain contextual information such as class geometry and cooccurrence. We aim to exploit this information for structured prediction. Multiple structured label spaces, representing different aspects of context...
Article
The typical processing chain for pixel-wise classification from PolSAR images starts with an optional preprocessing step (e.g. speckle reduction), continues with extracting features projecting the complex-valued data into the real domain (e.g. by polarimetric decompositions) which are then used as input for a machine-learning based classifier, and...
Article
Full-text available
Multi-view stereo has been shown to be a viable tool for the creation of realistic 3D city models. Nevertheless, it still states significant challenges since it results in dense, but noisy and incomplete point clouds when applied to aerial images. 3D city modelling usually requires a different representation of the 3D scene than these point clouds....
Thesis
Full-text available
In this thesis I analyse the state of the art of Structure from Motion and 3D reconstruction algorithms to develop a framework, that improves the process of working with these algorithms. This framework allows reusing existing parts of a processing chain, as well as developing new algorithms efficiently. This is done by providing a data model and...
Chapter
Random Forests und deren Varianten gehören zu den erfolgreichsten Methoden des maschinellen Lernens. Ihre Einfachheit, Effizienz, Robustheit, Genauigkeit und Allgemeinheit führten sowohl zu mannigfaltigen Adaptionen des zugrunde-liegenden Konzepts als auch zu vielen erfolgreichen Anwendungen auf verschiedene Problemstellungen. Dieser Artikel versuc...
Conference Paper
Benchmark datasets are the foundation of experimental evaluation in almost all vision problems. In the context of 3D reconstruction these datasets are rather difficult to produce. The field is mainly divided into datasets created from real photos with difficult experimental setups and simple synthetic datasets which are easy to produce, but lack ma...
Article
Full-text available
The automatic classification of land cover types from hyperspectral images is a challenging problem due to (among others) the large amount of spectral bands and their high spatial and spectral correlation. The extraction of meaningful features, that enables a subsequent classifier to distinguish between different land cover classes, is often limite...
Article
Full-text available
The automatic classification of land cover types from hyperspectral images is a challenging problem due to (among others) the large amount of spectral bands and their high spatial and spectral correlation. The extraction of meaningful features, that enables a subsequent classifier to distinguish between different land cover classes, is often limite...
Article
Full-text available
The reconstruction of the 3D geometry of a scene based on image sequences has been a very active field of research for decades. Nevertheless, there are still existing challenges in particular for homogeneous parts of objects. This paper proposes a solution to enhance the 3D reconstruction of weakly-textured surfaces by using standard cameras as wel...
Article
Full-text available
The task to compute 3D reconstructions from large amounts of data has become an active field of research within the last years. Based on an initial estimate provided by structure from motion, bundle adjustment seeks to find a solution that is optimal for all cameras and 3D points. The corresponding nonlinear optimization problem is usually solved b...
Article
Full-text available
The task to compute 3D reconstructions from large amounts of data has become an active field of research within the last years. Based on an initial estimate provided by structure from motion, bundle adjustment seeks to find a solution that is optimal for all cameras and 3D points. The corresponding nonlinear optimization problem is usually solved b...
Article
Full-text available
The reconstruction of the 3D geometry of a scene based on image sequences has been a very active field of research for decades. Nevertheless, there are still existing challenges in particular for homogeneous parts of objects. This paper proposes a solution to enhance the 3D reconstruction of weakly-textured surfaces by using standard cameras as wel...
Article
Full-text available
The fundamental analysis of drop coalescence probability in liquid/liquid systems is necessary to reliably predict drop size distributions in technical applications. For this crucial investigation two colliding oil drops in continuous water phase were recorded with different high speed camera set-ups under varying conditions. In order to analyse th...
Conference Paper
This paper addresses the problem of detecting and segmenting human instances in a point cloud. Both fields have been well studied during the last decades showing impressive results, not only in accuracy but also in computational performance. With the rapid use of depth sensors, a resurgent need for improving existing state-of-the-art algorithms, in...
Article
This paper implements a pipeline to automatically register point clouds captured by depth sensors like the Microsoft Kinect. The method neither makes assumptions about the view order of the sensors, nor uses any kind of other task-dependent prior knowledge. All point clouds within the input set are aligned in a common, global coordinate system by a...