This package contains the datasets and supplementary materials used in the IPIN 2021 Competition. Contents: IPIN2021_Track03_TechnicalAnnex_V1-02.pdf: Technical annex describing the competition 01-Logfiles: This folder contains a subfolder with the 105 training logfiles, 80 of them single floor indoors, 10 in outdoor areas, 10 of them in the indoor auditorium with floor-trasitio and 5 of them in floor-transition zones, a subfolder with the 20 validation logfiles, and a subfolder with the 3 blind evaluation logfile as provided to competitors. 02-Supplementary_Materials: This folder contains the matlab/octave parser, the raster maps, the files for the matlab tools and the trajectory visualization. 03-Evaluation: This folder contains the scripts used to calculate the competition metric, the 75th percentile on the 82 evaluation points. It requires the Matlab Mapping Toolbox. The ground truth is also provided as 3 csv files. Since the results must be provided with a 2Hz freq. starting from apptimestamp 0, the GT files include the closest timestamp matching the timing provided by competitors for the 3 evaluation logfiles. It contains samples of reported estimations and the corresponding results. Please, cite the following works when using the datasets included in this package: Torres-Sospedra, J.; et al. Datasets and Supporting Materials for the IPIN 2021 Competition Track 3 (Smartphone-based, off-site). http://dx.doi.org/10.5281/zenodo.5948678

Information on water depth in river channels is important for a number of applications in water resource management but can be difficult to obtain via conventional field methods, particularly over large spatial extents and with the kind of frequency and regularity required to support monitoring programs. Remote sensing methods could provide a viable alternative means of mapping river bathymetry (i.e., water depth). The purpose of this study was to develop and test new, spectrally based techniques for estimating water depth from satellite image data. More specifically, a neural network-based temporal ensembling approach was evaluated in comparison to several other neural network depth retrieval (NNDR) algorithms. These methods are described in a manuscript titled "Neural Network-Based Temporal Ensembling of Water Depth Estimates Derived from SuperDove Images" and the purpose of this data release is to make available the depth maps produced using these techniques. The images used as input were acquired by the SuperDove cubesats comprising the PlanetScope constellation, but the original images cannot be redistributed due to licensing restrictions; the end products derived from these images are provided instead. The large number of cubesats in the PlanetScope constellation allows for frequent temporal coverage and the neural network-based approach takes advantage of this high density time series of information by estimating depth via one of four NNDR methods described in the manuscript: 1. Mean-spec: the images are averaged over time and the resulting mean image is used as input to the NNDR. 2. Mean-depth: a separate NNDR is applied independently to each image in the time series and the resulting time series of depth estimates is averaged to obtain the final depth map. 3. NN-depth: a separate NNDR is applied independently to each image in the time series and the resulting time series of depth estimates is then used as input to a second, ensembling neural network that essentially weights the depth estimates from the individual images so as to optimize the agreement between the image-derived depth estimates and field measurements of water depth used for training; the output from the ensembling neural network serves as the final depth map. 4. Optimal single image: a separate NNDR is applied independently to each image in the time series and only the image that yields the strongest agreement between the image-derived depth estimates and the field measurements of water depth used for training is used as the final depth map. MATLAB (Version 24.1, including the Deep Learning Toolbox) source code for performing this analysis is provided in the function NN_depth_ensembling.m and the figure included on this landing page provides a flow chart illustrating the four different neural network-based depth retrieval methods. As examples of the resulting models, MATLAB *.mat data files containing the best-performing neural network model for each site are provided below, along with a file that lists the PlanetScope image identifiers for the images that were used for each site. To develop and test this new NNDR approach, the method was applied to satellite images from three rivers across the U.S.: the American, Colorado, and Potomac. For each site, field measurements of water depth available through other data releases were used for training and validation. The depth maps produced via each of the four methods described above are provided as GeoTIFF files, with file name suffixes that indicate the method employed: X_mean-spec.tif, X_mean-depth.tif, X_NN-depth.tif, and X-single-image.tif, where X denotes the site name. The spatial resolution of the depth maps is 3 meters and the pixel values within each map are water depth estimates in units of meters.

This package contains the datasets and supplementary materials used in the IPIN 2023 Competition.

Contents

• Track-3_TA-2023.pdf: Technical annexe describing the competition (Version 2)
• 01 Logfiles: This folder contains a subfolder with the 54 training trials, a subfolder with the 4 testing trials (validation), and a subfolder with the 2 blind scoring trials (test) as provided to competitors.
• 02 Supplementary_Materials: This folder contains the Matlab/octave parser, the raster maps, the files for the Matlab tools and the trajectory visualization.
• 03 Evaluation: This folder contains the scripts we used to calculate the competition metric, the 75th percentile on the 69 evaluation points. It requires the Matlab Mapping Toolbox. We also provide the ground truth as 2 CSV files. It contains samples of reported estimations and the corresponding results.

We provide additional information on the competition at: https://evaal.aaloa.org/2023/call-for-competition

Citation Policy

Please cite the following works when using the datasets included in this package:

Torres-Sospedra, J.; et al. Datasets and Supporting Materials for the IPIN 2023
Competition Track 3 (Smartphone-based, off-site), Zenodo 2023
http://dx.doi.org/10.5281/zenodo.8362205

Check the updated citation policy at: http://dx.doi.org/10.5281/zenodo.8362205

Contact

For any further questions about the database and this competition track, please contact:

Joaquín Torres-Sospedra
Centro ALGORITMI,
Universidade do Minho, Portugal
info@jtorr.es - jtorres@algoritmi.uminho.pt

Antonio R. Jiménez
Centre of Automation and Robotics (CAR)-CSIC/UPM, Spain
antonio.jimenez@csic.es

Antoni Pérez-Navarro
Faculty of Computer Sciences, Multimedia and Telecommunication, Universitat Oberta de Catalunya, Barcelona, Spain
aperezn@uoc.edu

Acknowledgements

We thank Maximilian Stahlke and Christopher Mutschler at Fraunhofer ISS, as well as Miguel Ortiz and Ziyou Li at Université Gustave Eiffel, for their invaluable support in collecting the datasets. And last but certainly not least, Antonino Crivello and Francesco Potortì for their huge effort in georeferencing the competition venue and evaluation points.

We extend our appreciation to the staff at the Museum for Industrial Culture (Museum Industriekultur) for their unwavering patience and invaluable support throughout our collection days.

We are also grateful to Francesco Potortì, the ISTI-CNR team (Paolo, Michele & Filippo), and the Fraunhofer IIS team (Chris, Tobi, Max, ...) for their invaluable commitment to organizing and promoting the IPIN competition.

This work and competition belong to the IPIN 2023 Conference in Nuremberg (Germany).

Parts of this work received the financial support received from projects and grants:

• ORIENTATE (H2020-MSCA-IF-2020, Grant Agreement 101023072)
• GeoLibero (from CYTED)
• INDRI (MICINN, ref. PID2021-122642OB-C42, PID2021-122642OB-C43, PID2021-122642OB-C44, MCIU/AEI/FEDER UE)
• MICROCEBUS (MICINN, ref. RTI2018-095168-B-C55, MCIU/AEI/FEDER UE)
• TARSIUS (TIN2015-71564-C4-2-R, MINECO/FEDER)
• SmartLoc(CSIC-PIE Ref.201450E011)
• LORIS (TIN2012-38080-C04-04)

This package contains the datasets and supplementary materials used in the IPIN 2024 Competition.

Contents:- IPIN2024_Track4_CallForCompetition_v1.4.pdf: Call for competition including the technical annex describing the competition

• 01-Logfiles: This folder contains 2 files for each Trials (Testing, Scoring01, Scoring02) - IPIN2024_T4_xxx.txt : data file containing ACCE, ROTA, MAGN, PRES, TEMP, GSBS, GOBS, POSI frames - IPIN2024_T4_xxx_gnss_ephem.nav : GNSS navigation files for trajectory estimation. - 02-Supplementary_Materials: This folder contains the datasheet files of the different sensors, a static logfile of about 14 hours that can be used for sensors bias estimation (Allan Variance) and a logfile of about 1 minute that can be used to calibrate the magnetometer sensor (Magnetometer Calibration).

• 03-Evaluation: This folder contains the scripts used to calculate the competition metric, the 75th percentile on all evaluation points. It requires Matlab Mapping Toolbox. We also provide ground truth of the all trials (1 Testing + 2 Scorings) as 2 MAT and KML files. It contains samples of reported estimations and the corresponding results. Just run script_Eval_IPIN2024.mat

We provide additional information on the competition at: https://competition.ipin-conference.org/2024/call-for-competition

Citation Policy:Please, cite the following works when using the datasets included in this package:

Ortiz, M.; Ziyou L.; Zhu, N.; Renaudin, V. Datasets and Supporting Materials for the IPIN 2024 Competition Track 4 (Foot-Mounted IMU based Positioning, offsite-online), Zenodo 2024https://doi.org/10.5281/zenodo.14501047

Check the citation policy at: https://doi.org/10.5281/zenodo.14501047

Contact:For any further questions about the database and this competition track, please contact:

Miguel Ortiz (miguel.ortiz@univ-eiffel.fr) at the University Gustave Eiffel, France.  Ni Zhu (ni.zhu@univ-eiffel.fr) at the University Gustave Eiffel, France.

Acknowledgements:We thank the staff at "La Cité des Congrès" based in Nantes for their unwavering patience and invaluable support throughout our collection days.

This package contains the datasets and supplementary materials used in the IPIN 2022 Competition.

Contents:- IPIN2022_Track4_CallForCompetition_v1.3.pdf: Call for competition including the technical annex describing the competition

• 01-Logfiles: This folder contains 2 files for each Trials (Testing, Scoring01, Scoring02) - IPIN2022_T4_xxx.txt : data file containing ACCE, ROTA, MAGN, PRES, TEMP, GSBS, GOBS, POSI frames - IPIN2022_T4_xxx_yyy_ephem.nav : for trajectory estimation. - 02-Supplementary_Materials: This folder contains the datasheet files of the different sensors, a static logfile of about 12 hours that can be used for sensors bias estimation (Allan Variance) and a logfile of about 1 minute that can be used to calibrate the magnetometer sensor (Magnetometer Calibration).

• 03-Evaluation: This folder contains the scripts used to calculate the competition metric, the 75th percentile on all evaluation points. It requires Matlab Mapping Toolbox. We also provide ground truth of the 2 scoring trials as CSV files (with full rate @60Hz and with evaluation point only). It contains samples of reported estimations and the corresponding results. Just run script_Eval_IPIN2022.mat

We provide additional information on the competition at: https://evaal.aaloa.org/2022/call-for-competitions

Citation Policy:Please, cite the following works when using the datasets included in this package:

Ortiz, M.; Zhu, N.; Ziyou L.; Renaudin, V. Datasets and Supporting Materials for the IPIN 2022 Competition Track 4 (Foot-Mounted IMU based Positioning, offsite-online), Zenodo 2022https://doi.org/10.5281/zenodo.10497364

Check the citation policy at: https://doi.org/10.5281/zenodo.10497364

Contact:

For any further questions about the database and this competition track, please contact:

Miguel Ortiz (miguel.ortiz@univ-eiffel.fr) at the University Gustave Eiffel, France.  Ni Zhu (ni.zhu@univ-eiffel.fr) at the University Gustave Eiffel, France.

Acknowledgements:

We thank Frederic Le-Bourhis and Aravind Ramseh from Univ-Eiffel for their support in collecting the datasets.

We extend our appreciation to the staff at the Nantes Central station for their invaluable support throughout our collection days.

This package contains the datasets and supplementary materials used in the IPIN 2024 Competition.

Contents

Track-3_TA-2024.pdf: Technical annex describing the competition (Version 1)

01 Logfiles: This folder contains a subfolder with the 54 training trials, a subfolder with the 4 testing trials (validation), and a subfolder with the 2 blind scoring trials (test) as provided to competitors.

02 Supplementary_Materials: This folder contains the Matlab/octave parser, the raster maps, the files for the Matlab tools and the trajectory visualization.

03 Evaluation: This folder contains the scripts we used to calculate the competition metric, the 75th percentile on the 69 evaluation points. It requires the Matlab Mapping Toolbox. We also provide the ground truth as 2 CSV files. It contains samples of reported estimations and the corresponding results.

We provide additional information on the competition at: https://competition.ipin-conference.org/2024/call-for-competition

Citation Policy

Please cite the following works when using the datasets included in this package:

Torres-Sospedra, J.; et al. Datasets and Supporting Materials for the IPIN 2024Competition Track 3 (Smartphone-based, off-site), Zenodo 2024http://dx.doi.org/10.5281/zenodo.13931119

Check the updated citation policy at: http://dx.doi.org/10.5281/zenodo.13931119

Contact

For any further questions about the database and this competition track, please contact:

Joaquín Torres-Sospedra Departament d'Informatica, Universitat de València, 46100 Burjassot, SpainValgrAI - Valencian Graduate School and Research Network of Artificial Intelligence, Camí de Vera s/n, 46022 Valencia, SpainJoaquin.Torres@uv.es - info@jtorr.es Antonio R. Jiménez Centre of Automation and Robotics (CAR)-CSIC/UPM, Spain antonio.jimenez@csic.es

Antoni Pérez-NavarroFaculty of Computer Sciences, Multimedia and Telecommunication, Universitat Oberta de Catalunya, Barcelona, Spainaperezn@uoc.edu

Acknowledgements

We thank Maximilian Stahlke and Christopher Mutschler at Fraunhofer ISS, as well as Miguel Ortiz and Ziyou Li at Université Gustave Eiffel, for their invaluable support in collecting the datasets. And last but certainly not least, Antonino Crivello and Francesco Potortì for their huge effort in georeferencing the competition venue and evaluation points.

We extend our appreciation to the staff at the Museum for Industrial Culture (Museum Industriekultur) for their unwavering patience and invaluable support throughout our collection days.

We are also grateful to Francesco Potortì, the ISTI-CNR team (Paolo, Michele & Filippo), and the Fraunhofer IIS team (Chris, Tobi, Max, ...) for their invaluable commitment to organizing and promoting the IPIN competition.

This work and competition are part of the IPIN 2023 Conference in Nuremberg (Germany) and the IPIN 2024 Conference in Hong Kong.

Parts of this work received the financial support received from projects and grants:

POSITIONATE (CIDEXG/2023/17, Conselleria d’Educació, Universitats i Ocupació, Generalitat Valenciana)

ORIENTATE (H2020-MSCA-IF-2020, Grant Agreement 101023072)

GeoLibero (from CYTED)

INDRI (MICINN, ref. PID2021-122642OB-C42, PID2021-122642OB-C43, PID2021-122642OB-C44, MCIU/AEI/FEDER UE)

MICROCEBUS (MICINN, ref. RTI2018-095168-B-C55, MCIU/AEI/FEDER UE)

TARSIUS (TIN2015-71564-C4-2-R, MINECO/FEDER)

SmartLoc(CSIC-PIE Ref.201450E011)

LORIS (TIN2012-38080-C04-04)

This package contains the datasets and supplementary materials used in the IPIN 2022 Competition. Contents: Track-3_TA-2022.pdf: Technical annex describing the competition (Version 2) 01 Logfiles: This folder contains a subfolder with the 89 training trials a subfolder with the 24 testing trials (validation), and a subfolder with the 3 blind scoring trials (test) as provided to competitors. 02 Supplementary_Materials: This folder contains the matlab/octave parser, the raster maps, the files for the matlab tools and the trajectory visualization. 03 Evaluation: This folder contains the scripts used to calculate the competition metric, the 75th percentile on the 31|61|61 evaluation points. It requires the Matlab Mapping Toolbox. The ground truth is also provided as 3 csv files. Since the results must be provided with a 2Hz freq. starting from apptimestamp 0, the GT files include the closest timestamp matching the timing provided by competitors for the 3 evaluation logfiles. It contains samples of reported estimations and the corresponding results. Please, cite the following works when using the datasets included in this package: Torres-Sospedra, J.; et al. Datasets and Supporting Materials for the IPIN 2022 Competition Track 3 (Smartphone-based, off-site), Zenodo 2022. http://dx.doi.org/10.5281/zenodo.7612915