LOG-a-TEC

testbeds with sensor platforms

UWB Localization Data Set

UWB localization data set contains measurements from four different indoor environments. The data set contains measurements that can be used for range-based localization evaluation in different indoor environments.

Measurement system

The measurements were made using 9 DW1000 UWB transceivers (DWM1000 modules) connected to the networked RaspberryPi computer using in-house radio board SNPN_UWB. 8 nodes were used as localization anchor nodes with fixed locations in individual indoor environment and one node was used as a mobile localization tag.

Each UWB node is designed arround the RaspberryPi computer and are wirelessly connected to the measurement controller (e.g. laptop) using Wi-Fi and MQTT communication technologies.

Figure 1 - Measurement system.

Measurement setup

All localization tag positions were generated beforehand to as closelly resemble the human walking path as possible. All walking path points are equally spaced to represent the equidistand samples of a walking path in a time-domain. On a Figure 2 there is an example of complete indoor localization measurement setup. Blue points represent tag positions and black crosses represent reference anchors positions. The sampled walking path (measurement TAG positions) are included in a downloadable data set file under downloads section.

Figure 2 - Example of one measurement setup.

Folder structure

Folder structure is represented below this text. Folder contains four subfolders named by the indoor environments measured during the measurement campaign. Each environment folder has a anchors.csv file with anchor names and locations, subfolder floorplan with floorplan.dxf (AutoCAD format) and floorplan.png, subfolder measurements and walking_path.csv file with tag measurement positions. Measurements subfolder contains subfolders named by the tag positions form the walking_path.csv. There is exactly the same number of folders in folder measurements as is the number of measurement points in the walking_path.csv. Each measurement subfolder contains 48 .csv files named by communication channel and anchor used for those measurements. For example: ch1_A1.csv contains all measurements at selected tag location with anchor A1 on UWB channel ch1.

apartment

anchors.csv
floorplan

floorplan.dxf
floorplan.png

measurements

1.07_9.37_1.2

ch1_A1.csv
ch7_A8.csv
...

1.37_9.34_1.2

walking_path.csv

house

industrial

office

Data format

Measurements are saved in .csv files. Each file starts with a header, where first line represents the version of the file and the second line represents the data column names. The column names have a missing column name. Actual column names included in the .csv files are:

TAG_ID
ANCHOR_ID
X_TAG
Y_TAG
Z_TAG
X_ANCHOR
Y_ANCHOR
Z_ANCHOR
NLOS
RANGE
FP_INDEX
RSS
RSS_FP
FP_POINT1
FP_POINT2
FP_POINT3
STDEV_NOISE
CIR_POWER
MAX_NOISE
RXPACC
CHANNEL_NUMBER
FRAME_LENGTH
PREAMBLE_LENGTH
BITRATE
PRFR
PREAMBLE_CODE
CIR (starts with this column; all columns until the end of the line represent the channel impulse response)

Download

Data set available for download: .zip, 1.9 GB

Citation

If you are using our data set in your research, citation of the following paper would be greatly appreciated.

Plain text:

K. Bregar and M. Mohorčič, "Improving Indoor Localization Using Convolutional Neural Networks on Computationally Restricted Devices," in IEEE Access, vol. 6, pp. 17429-17441, 2018. doi: 10.1109/ACCESS.2018.2817800 keywords: {Computational modeling;Convolutional neural networks;Distance measurement;Estimation;Heuristic algorithms;Performance evaluation;Prediction algorithms;Channel impulse response;convolutional neural network;deep learning;indoor localization;non-line-of-sight;ranging error mitigation;ultra-wide band}, URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8320781&isnumber=8274985

BibTex:

@ARTICLE{8320781,
author={K. Bregar and M. Mohorčič},
journal={IEEE Access},
title={Improving Indoor Localization Using Convolutional Neural Networks on Computationally Restricted Devices},
year={2018},
volume={6},
number={},
pages={17429-17441},
keywords={Computational modeling;Convolutional neural networks;Distance measurement;Estimation;Heuristic algorithms;Performance evaluation;Prediction algorithms;Channel impulse response;convolutional neural network;deep learning;indoor localization;non-line-of-sight;ranging error mitigation;ultra-wide band},
doi={10.1109/ACCESS.2018.2817800},
ISSN={},
month={},}

Authors and License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Funding

The research leading to these results has received funding from the European Horizon 2020 Programme project eWINE under grant agreement No. 688116.