Institut für Photogrammetrie und Fernerkundung (IPF)

Aerial Peruvian Andes Campaign (ALPACA)

 
The Aerial Peruvian Andes Campaign (ALPACA) dataset was acquired during a measurement campaign of the Institute of Photogrammetry and Remote Sensing (IPF) and the Institute of Water and River Basin Management - Hydrology (IWG) of the Karlsruhe Institute of Technology (KIT). The measurement campaign was conducted in Peru, in the catchment area of the river Lurín near Lima, in April 2019. Areas in five different locations between 2700 m and 3700 m above mean sea level are included. The ALPACA dataset consists of hyperspectral data in the range of 900 nm to 2500 nm and soil moisture point data in the range of 4 % to 89 %.
 
The hyperspectral data was acquired with a Headwall Hyperspec SWIR sensor, which was mounted on DJI Matrice 600 Pro an Unmanned Aerial Vehicle. About 27 600 square meters of hyperspectral data were acquired with a pixel edge length of about 3 cm. A detailed description of the data acquisition can be found in [1]. The soil moisture data was measured with a handheld ThetaProbe sensor. As a result, 236 soil moisture values are provided. The point measurements were performed in a grid of various distances between 5 m and 15 m. The processing of the dataset is described in [1] and published in [2].
 
License: CC BY 4.0 https://creativecommons.org/licenses/by/4.0/deed.de
Publication: Felix M. Riese, Samuel Schroers, Jan Wienhöfer and Sina Keller. Aerial Peruvian Andes Campaign (ALPACA) Dataset 2019. KITopen. 2020. https://doi.org/10.5445/IR/1000118082 
Contact: F. M. Riese, S. Keller
Source:

 

This dataset comprises data of an interdisciplinary pedon-scale irrigation experiment at a grassland site near Karlsruhe, Germany, including pedo-hydrological, geophysical, and remote sensing data. The objective of this experiment is to monitor soil moisture dynamics during a well-defined infiltration process with a combination of direct and non-invasive techniques.
 
Overall, the quantification of soil water dynamics and, in particular, its spatial distributions is essential for the understanding of land-atmosphere interactions. However, the precise measurement of soil water dynamics and its spatial distribution in a continuous manner is a challenging task. Pedo-hydrological monitoring techniques rely on direct, point-based measurement with buried probes for soil water content and matric potential. Non-invasive remote sensing (RS) and geophysical measurement techniques allow for spatially continuous measurements on different spatial scales and extents. This experiment provides a basis for the analyses of signal coherence between the measurement techniques and disciplines. It contributes to forthcoming developments of monitoring setups and modeling approaches to landscape-water dynamics.

For direct monitoring, an array of time-domain reflectometry (TDR) probes and tensiometers was used. As non-invasive techniques, we applied a ground-penetrating radar (GPR), a hyperspectral snapshot sensor, a long-wave infrared (LWIR) sensor, and a hyperspectral field spectroradiometer. We provide the data in nearly raw format, including information about the site properties and calibration references. The data are organized along with the different sensors and disciplines. Thus, the distinct sensor data can also be used independently of each other. In addition, exemplary scripts for reading and processing the data are included.
 
License: CC BY 4.0 https://creativecommons.org/licenses/by/4.0/deed.de
Publication: Sina Keller, Felix M. Riese, Niklas Allroggen and Conrad Jackisch. HydReSGeo: Field experiment dataset of surface-sub-surface infiltration dynamics acquired by hydrological, remote sensing, and geophysical measurement techniques. GFZ Data Services. 2020. https://doi.org/10.5880/fidgeo.2020.015 
Contact: S. Keller, F. M. Riese
Source:  https://publikationen.bibliothek.kit.edu/1000119116 

 

Karlsruhe Library of Urban Materials (KLUM)

Karlsruhe Library of Urban Materials (KLUM) is spectral library that contains 181 urban material samples and consists of 12 material classes and 33 material subclasses. KLUM contains façade, ground and roof spectra which were acquired in-situ during the summer of 2018 in Karlsruhe, Germany. The spectra and corresponding metadata and photos are all available on the provided GitHub link. If you use KLUM, please refer to the corresponding publication.

License: GNU GPLv2
Publication: Rebecca Ilehag, Andreas Schenk, Yilin Huang, Stefan Hinz (2019) KLUM: A VNIR and SWIR Spectral Library Consisting of Building Materials. Remote Sensing, 11 (18), 2149 [https://doi.org/10.3390/rs11182149]
Contact: R. Ilehag, A. Schenk
Source: https://github.com/rebeccailehag/KLUM_library
  top

 

Automatic Extrinsic Self-Calibration of Mobile Mapping Systems Based on Geometric 3D Features

 

Many existing extrinsic calibration approaches require the use of artificial targets in a time-consuming calibration procedure. Moreover, they are usually designed for a specific combination of sensors and are, thus, not universally applicable. We introduce a novel Extrinsic Self-Calibration algorithm, which is fully automatic and completely data-driven. The fundamental assumption of the self-calibration is that the calibration parameters are estimated the best when the derived point cloud represents the real physical circumstances the best. The cost function we use to evaluate this is based on geometric features which rely on the 3D structure tensor derived from the local neighborhood of each point.

Detailed instructions on how to use the tool FeatCalibr are provided in GitHub. If you make use of our tool, please refer to the corresponding publication.

Licence: GNU GPLv3
Publication: Markus Hillemann, Martin Weinmann, Markus S. Mueller and Boris Jutzi (2019) Automatic Extrinsic Self-Calibration of Mobile Mapping Systems Based on Geometric 3D Features. Remote Sensing 2019, 11 (16), 1955 [doi:10.3390/rs11161955]
Contact: , B. Jutzi
Source: https://github.com/markushillemann/FeatCalibr
top

 

Hyperspectral benchmark dataset on soil moisture

Description: This dataset was measured in a five-day field campaign in May 2017 in Karlsruhe, Germany. An undisturbed soil sample is the centerpiece of the measurement setup. The soil sample consists of bare soil without any vegetation and was taken in the area near Waldbronn, Germany.
License: GNU GPLv2
Contact: F. Riese, M.Sc., Dr. S. Keller
Source: https://github.com/felixriese/hyperspectral-soilmoisture-dataset
Citation: Citation of the dataset: Riese, Felix M. and Keller, Sina. (2018). Hyperspectral benchmark dataset on soil moisture (Version v1.0.0) [Data set]. Zenodo. http://doi.org/10.5281/zenodo.1227837
  top

 

3D Scene Analysis

 

Neighborhood Selection (Source optNESS.zip)

This is our tool optNESS (optimal NEighborhood Size Selection) for deriving optimal 3D neighborhoods via eigenentropy-based scale selection. Detailed instructions on how to use the tool are provided in readme.txt. If you make use of our tool, please refer to the corresponding publication:

M. Weinmann, B. Jutzi, and C. Mallet (2014): Semantic 3D scene interpretation: a framework combining optimal neighborhood size selection with relevant features. In: K. Schindler and N. Paparoditis (Eds.), ISPRS Technical Commission III Symposium. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. II-3, pp. 181-188. PCV 2014 Best Paper Honorable Mention.

Feature Extraction (Source geoFEX.zip)

This is our tool geoFEX (geometric Feature EXtraction) for extracting low-level geometric 2D and 3D features. Detailed instructions on how to use the tool are provided in readme.txt. If you make use of our tool, please refer to the corresponding publication:

M. Weinmann, S. Urban, S. Hinz, B. Jutzi, and C. Mallet (2015): Distinctive 2D and 3D features for automated large-scale scene analysis in urban areas. Computers & Graphics, Vol. 49, pp. 47-57.

Licence: GNU GPLv2
Contact: Dr.-Ing. M. Weinmann
top

 

Fisheye calibration image data set

This data set contains fisheye images of a checkerboard recorded with different lenses and sensors.  
Licence: GNU GPLv2
Contact: Dipl.-Ing. S. Urban
Source: https://github.com/urbste/ImprovedOcamCalib
top

 

The EnMAP Contest

The dataset for the EnMAP Contest originates from the simulated EnMAP Alpine Foreland image covering the area around the Ammersee in Bavaria, Germany. Based on the original dataset, 20 different land use classes have been defined on the screen by focussing on visual differences in the images (considering several channel combinations) but also by checking pixels’ individual spectra.
Licence: GNU GPLv2
Publication: Braun, A.C.; Weinmann, M.; Keller, S.; Müller, R.; Reinartz, P.; Hinz, S. (2015): The EnMAP contest: developing and comparing classification approaches for the Environmental Mapping and Analysis Programme - Dataset and first results. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. XL-3/W3, pp. 169-175. [pdf]
Contact: Dipl.-Ing. M. Weinmann
Source: EnMAP_Contest.zip (1.57 GB)
Instructions for participating in the EnMAP Contest

(pdf, 26 kB)

Exemplary MATLAB-script for classification (zip, 1 kB)

Evaluation: The evaluation procedure will be similar to the ones of the Middlebury Stereo Vision benchmark, the ISPRS Test Project on Urban Classification, 3D Building Reconstruction and Semantic Labeling and the IQmulus & TerraMobilita Contest, i.e. if you are interested in participating, please submit the achieved quality measures and the classified image. After submitting these data, your results will be evaluated and you can request that your results are added to the permanent table. For the latter, it is mandatory to provide (1) a short description of the algorithm or the reference to a paper where this algorithm has been published and (2) respective code fragments or hints on the involved software packages.
Deadline of the first EnMAP Contest: 15th Feburary 2016
top

Improved Wide-Angle, Fisheye and Omnidirectional Camera Calibration

This is an add-on to the online available omnidirectional camera calibration toolbox OCamCalib of Scaramuzza et al. The 3 image data sets necessary to run all test calibrations can be found below. Please consult the readme.txt on how to install the add-on. If you make use of our extended version, please cite the corresponding paper.  
Licence: GNU GPLv2
Publication: Urban, S.; Leitloff, J.; Hinz, S. (2015): Improved Wide-Angle, Fisheye and Omnidirectional Camera Calibration. ISPRS Journal of Photogrammetry and Remote Sensing 108, 72-79.
Contact: Dipl.-Ing. S. Urban
Source: https://github.com/urbste/ImprovedOcamCalib
top

 

Tracking Vehicles in Aerial Image Sequences

The following data set comprises aerial image sequences and a xml files with manually labeled trajectories of all visible vehicles.
The data set on this page is available under the following license: Creative Commons Lizenzvertrag

If you use the data, please refer to this web page or to the KIT AIS Data Set.

 

Many thanks to the German Aerospace Center  for providing the aerial image sequences.

DLR-Logo

 
Licence:  Creative Commons Lizenzvertrag
Publication:
Contact: Dipl.-Ing. F. Schmidt
Source: Training sequences  --- C++ code  (for easy import and further processing of the AIS CVML files)
top

 

Tracking People in Aerial Image Sequences

The following datasets have been created for the research project VABENE - People Traing in Aerial Image Sequences. Each dataset comprises of an aerial image sequence and a xml file with manually labeled trajectories of all visible persons.

All datasets on this page are available under the following license: Creative Commons Lizenzvertrag
If you use the data, please refer to this web page or to the KIT AIS Data Set.

 

 
Licence:  Creative Commons Lizenzvertrag
Publication:
Contact: Dipl.-Ing. F. Schmidt
Source: click here for further information
top

 

LaFiDa - A Laserscanner Multi-Fisheye Camera Dataset

We provide test data for applying Simultaneous Localization and Mapping (SLAM) algorithms. The Laserscanner Multi-Fisheye Camera Dataset (LaFiDa) includes fully synchronized laserscanner data and image sequences for three diverge fisheye cameras, aswell as ground truth trajectory.

Each dataset consist of:

  • three image sequences, each sequence captured with a fisheye camera
  • the laserscanner data
  • an interactive 3D point cloud of the laserscanner data
  • the data conventions
  • a video of the scene to get first impressions
  • a link to download the complete test data

LaFiDa is supported by master students of Geodesy and Geoinformatics at KIT during a student project in "Project Computer Vision".

Note: LaFida is currently in a release candidate state. The use of LaFiDa is for free, but please refer to the publication below.

Licence: Creative Commons Lizenzvertrag

Contact: 

Boris Jutzi
Steffen Urban

Source: click here for further information.

Publication: S. Urban, B. Jutzi (2017) LaFiDa - A Laserscanner Multi-Fisheye Camera Dataset. Special Issue "3D Imaging". Open Access Journal of Imaging 2017, 3(1), 5 [doi: 10.3390/jimaging3010005]

top

 

Workflow of LaFiDa
Workflow of LaFiDa
Helmet with rigid body labels

MLPnP – A maximum likelihood solution to the Perspective-N-Point problem

MLPnP offers the possibility to integrate observation uncertainty into the direct solution of the PnP problem. This is especially useful if an estimate of the observation covariance is available. Given that estimate MLPnP outperforms the given state-of-the-art PnP solutions (see Figure on the right). If equal observation uncertainty is assumed MLPnP still outperforms the best polynomial solvers in terms of speed and accuracy.

The C++ version of MLPnP is integrated in a fork of OpenGV. You can find the link to the fork below. In addition we provide Matlab Code which is slower, but produces the same results. The toolbox provides all PnP solvers in a Matlab toolbox to reproduce the results presented in the paper.
 
Licence: 
Publication: Urban, S.; Leitloff, J.; Hinz, S. (2016): MLPnP - A Real-Time Maximum Likelihood Solution to the Perspective-n-Point Problem. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. (pdf)
Contact: Dipl.-Ing. S. Urban
Source C++
Source Matlab
Source Matlab Toolbox
top

 

MultiCol-SLAM:  A Multi-Fisheye Camera System SLAM System

MultiCol-SLAM is a full multi-fisheye camera SLAM system build upon ORB-SLAM. It extends ORB-SLAM with some novel concepts and methods. First, keyframes are exchanged by multi-keyframes modelling the fact, that multiple images exist at each keyframe position. The multi-camera system is modeled using MultiCol and the camera projections within these model are calibrated using a generic polynomial model. Bundle adjustment is formulated as an optimization of a hyper graph and implemented in g2o. Furthermore, new types of descriptors are included, i.e. a distorted and an online learned, masked version of BRIEF. The loop closing mechanisms and re-localization capabilites of ORB-SLAM are extended for multi-camera systems.
 
Licence: GNU GPLv3
Publication: Urban, S.; Wursthorn, S.; Leitloff, J.; Hinz, S. (2016): MultiCol Bundle Adjustment: A Generic Method for Pose Estimation, Simultaneous Self-Calibration and Reconstruction for Arbitrary Multi-Camera Systems./ International Journal of Computer Vision (IJCV), pages 1-19, 2016.
Contact: Dipl.-Ing. S. Urban
Source C++
top

 

Building event histories of dead files

About the dataset.
The dataset ehist.txt is a random sample taken from 'dead' building insurance files recording the history of insurance-relevant events occurring to insured buildings in Baden (Germany) between 1936 and 1993. A 'dead' file corresponds to addresses whose buildings were no longer insured under that address, e.g. because of demolition or property splitting.

  event classes
  a demolition
  e owner change
  f function change
  n new construction
  v other change, e.g. refurbishment
  w post-war reconstruction
  z war destruction
     
  urbanity
  r
rural (Gemeinde)
  u
urban (kreisfreie Stadt)

 

Contact: Dr. rer.nat. Patrick Erik Bradley

 

 

Building event histories of dead files 2

The three datasets dfnobmfe.sp, dfnobmfe.tse, dfnobmf.tse contain the building histories from the random sample taken from the dead files.

The first dataset dfnobmfe.sp is in SPELL-format, where each spell begins with the year in column "from" and ends in the year in column "to". The state can be any other column.

The second dataset dfnobmfe.tse is in TSE-format, where the duration of each state is in the column "arxtime". The event is written in column "EK" and is one of

  A
demolition
  N new construction
  V improvement
  W post-war reconstruction
  Z
war destruction

The third dataset dfnobmf.tse is the same as dfnobmfe.tse with the only difference that also an event

  E owner change

is recorded in column "EK".

 

Contact: Dr. rer.nat. Patrick Erik Bradley