Microsoft Indoor Localization Competition 2018 Overview

 
2018 Microsoft Indoor
Localization Competition
 
Dimitrios Lymberopoulos
 (Microsoft Research)
Jie Liu (Microsoft Research)
Vitor Sequeira (European Commission – Joint Research Center)
Vivek Jain (Bosch)
Niki Trigoni (University of Oxford)
Anthony Rowe (CMU)
Nader Moayeri (NIST)
 
Organizers
 
Competition Goals
 
Evaluate and compare technologies from academia and industry in the
same, unfamiliar space.
Bring teams working in this area together in a more effective way.
 
2014: Berlin
 
2015: Seattle
 
2016: Vienna
 
2017: Pittsburgh
 
2018: Porto
 
34
   
teams submitted abstracts
 
26
   
systems officially registered
 
25
   
systems showed up in Porto
 
22
   
systems were evaluated
 
Two Categories
 
2D Category
Report 
(X,Y)
 locations
Do not require the deployment of any infrastructure (WiFi and/or IMU based)
3D Category
Report 
(X,Y,Z)
 locations
Require custom hardware deployment (UWB, Ultrasound etc.)
Each team can deploy up to 10 anchor devices in the evaluation space
 
Evaluation Process
 
Day 1: Tuesday
Teams were given 8 hours to setup and
calibrate their systems.
Day 2: Wednesday
Each team mounted their systems on our
evaluation backpack and continuously logged
locations over a predetermined path.
Evaluation Metric
Average localization error across all recorded
points along the path.
The lower the error the better.
 
LiDAR
 
System under Test
 
Evaluation Area - Two Floors
 
Ground Truth Measurements & Evaluation
 
The ground truth environment and the test
points were acquired using multiple high
definition 3D scans using a tripod mounted laser
scanner (e.g. ZF 5006) and proprietary software
 
High Resolution 3D Acquisition and Registration
 
Pierluigi Taddei
 
Carlos Sanchez
 
JRC (
https://ec.europa.eu/jrc
), the winner of the
2015 competition, volunteered to provide its
expertise for ground truth measurements.
 
JRC has been deploying 3D laser scanning
technology to verify design information within
nuclear facilities for more than 10 years.
 
Vitor Sequeira
2D Results
PDR
PDR + Fingerprinting
WiFi ToF
Camera+PDR
Camera+PDR+Finger.
Teams that start with * require initialization.
Naviguy and Ariel Univ. were considered a tie!
 Ariel University is the winner as Naviguy required initialization while Ariel University did not.
 
Naviguy
 
Ariel Univ. (Step)
 
3D Results
 
Sound
 
Atmel
Phase
 
Sound+
ARKit
 
UWB+
ARKit
 
UWB
 
Camera+
LED + PDR
 
Teams that start with * require initialization. 
SND Smart Ltd and Yodel Labs are considered a tie!
 
3D Results
 
Sound
 
Atmel
Phase
 
Sound+
ARKit
 
UWB+
ARKit
 
UWB
 
Camera+
LED + PDR
 
3D Results
 
Sound
 
Atmel
Phase
 
Sound+
ARKit
 
UWB+
ARKit
 
UWB
 
Camera+
LED + PDR
 
3D Results
 
Sound
 
Atmel
Phase
 
Sound+
ARKit
 
UWB+
ARKit
 
UWB
 
Camera+
LED + PDR
 
3D Results
 
Sound
 
Atmel
Phase
 
Sound+
ARKit
 
UWB+
ARKit
 
UWB
 
Camera+
LED + PDR
 
3D Results
 
Sound
 
Atmel
Phase
 
Sound+
ARKit
 
UWB+
ARKit
 
UWB
 
Camera+
LED + PDR
1
st
2
nd
2
nd
 
2D Category
 
3D Category
$1000
$600
$600
Slide Note
Embed
Share

The Microsoft Indoor Localization Competition 2018 in Porto brought together 34 teams to evaluate and compare technologies for indoor localization. The competition aimed to assess systems in 2D and 3D categories without the need for infrastructure deployment. Teams utilized LiDAR technology and were evaluated based on average localization error. Ground truth measurements were conducted using high-resolution 3D scans. Naviguy from Ariel Univ. emerged with impressive results in the 2D category. The event facilitated collaboration among industry and academia experts in indoor localization technology.


Uploaded on Sep 08, 2024 | 0 Views


Download Presentation

Please find below an Image/Link to download the presentation.

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.

E N D

Presentation Transcript


  1. 2018 Microsoft Indoor Localization Competition Organizers Dimitrios Lymberopoulos (Microsoft Research) Jie Liu (Microsoft Research) Vitor Sequeira (European Commission Joint Research Center) Vivek Jain (Bosch) Niki Trigoni (University of Oxford) Anthony Rowe (CMU) Nader Moayeri (NIST)

  2. Competition Goals Evaluate and compare technologies from academia and industry in the same, unfamiliar space. Bring teams working in this area together in a more effective way. 2014: Berlin 2015: Seattle 2016: Vienna 2017: Pittsburgh

  3. 2018: Porto 34 teams submitted abstracts 26 systems officially registered 25 systems showed up in Porto 22 systems were evaluated

  4. Two Categories 2D Category Report (X,Y) locations Do not require the deployment of any infrastructure (WiFi and/or IMU based) 3D Category Report (X,Y,Z) locations Require custom hardware deployment (UWB, Ultrasound etc.) Each team can deploy up to 10 anchor devices in the evaluation space

  5. System under Test LiDAR Evaluation Process Day 1: Tuesday Teams were given 8 hours to setup and calibrate their systems. Day 2: Wednesday Each team mounted their systems on our evaluation backpack and continuously logged locations over a predetermined path. Evaluation Metric Average localization error across all recorded points along the path. The lower the error the better.

  6. Evaluation Area - Two Floors

  7. Ground Truth Measurements & Evaluation High Resolution 3D Acquisition and Registration Pierluigi Taddei Carlos Sanchez Vitor Sequeira JRC (https://ec.europa.eu/jrc), the winner of the 2015 competition, volunteered to provide its expertise for ground truth measurements. The ground truth environment and the test points were acquired using multiple high definition 3D scans using a tripod mounted laser scanner (e.g. ZF 5006) and proprietary software JRC has been deploying 3D laser scanning technology to verify design information within nuclear facilities for more than 10 years.

  8. Naviguy Ariel Univ. (Step) 2D Results PDR + Fingerprinting 20 12.5 18 16 Mean Localization Error (m) 9.4 14 12 WiFi ToF 10 Camera+PDR+Finger. 5.3 8 4.3 Camera+PDR PDR 6 3.2 2.3 2.4 4 2 0 *Naviguy Ariel Univ. (Step) *Ali et al. Ariel Univ. (GoIn) Team Rea et al. Naviguy (Fusion) *Fineway Teams that start with * require initialization. Naviguy and Ariel Univ. were considered a tie! Ariel University is the winner as Naviguy required initialization while Ariel University did not.

  9. 3D Results Sound 25 16.64 20 15 UWB 6.94 10 3.79 Camera+ LED + PDR Atmel Phase 5 Sound+ ARKit UWB+ ARKit 1.49 1.7 1.16 0.94 1.21 0.7 0.99 0.73 0.71 0.47 0.4 0.27 0 Teams that start with * require initialization. SND Smart Ltd and Yodel Labs are considered a tie!

  10. 3D Results Sound 25 16.64 20 15 UWB 6.94 10 3.79 Camera+ LED + PDR Atmel Phase 5 Sound+ ARKit UWB+ ARKit 1.49 1.7 1.16 0.94 1.21 0.7 0.99 0.73 0.71 0.47 0.4 0.27 0

  11. 3D Results Sound 25 16.64 20 15 UWB 6.94 10 3.79 Camera+ LED + PDR Atmel Phase 5 Sound+ ARKit UWB+ ARKit 1.49 1.7 1.16 0.94 1.21 0.7 0.99 0.73 0.71 0.47 0.4 0.27 0

  12. 3D Results Sound 25 16.64 20 15 UWB 6.94 10 3.79 Camera+ LED + PDR Atmel Phase 5 Sound+ ARKit UWB+ ARKit 1.49 1.7 1.16 0.94 1.21 0.7 0.99 0.73 0.71 0.47 0.4 0.27 0

  13. 3D Results Sound 25 16.64 20 15 UWB 6.94 10 3.79 Camera+ LED + PDR Atmel Phase 5 Sound+ ARKit UWB+ ARKit 1.49 1.7 1.16 0.94 1.21 0.7 0.99 0.73 0.71 0.47 0.4 0.27 0

  14. 3D Results Sound 25 16.64 20 15 UWB 6.94 10 3.79 Camera+ LED + PDR Atmel Phase 5 Sound+ ARKit UWB+ ARKit 1.49 1.7 1.16 0.94 1.21 0.7 0.99 0.73 0.71 0.47 0.4 0.27 0

  15. 3D Category 2D Category Steps An Accurate Relative Positioning Method for First-Responders Landau et al. (Ariel University) Realty and Reality: Where Location Matters Miller et al. (CMU) 1st 0.27m error $1000 2.4m error Inertial Sensing Approach for Indoor Localization Qu et al. (Naviguy/Tongji University) NavInThings An Indoor Localization and Navigation UWB System Gao et al. (SND Smart Ltd/ATE Electronics Ltd) 2nd $600 0.40m error 2.3m error ALPS: The Acoustic Location Processing System Lazik et al. (Yodel Labs) 2nd 0.47m error $600

Related


More Related Content

giItT1WQy@!-/#giItT1WQy@!-/#giItT1WQy@!-/#giItT1WQy@!-/#