Competitors

September 28-29, 2019 - CNR Area of Pisa, Italy

On-site Tracks

Track 1 - Smartphone-based

Team Name

SNU-NESL

Corresponding Author

Hyunwoong Kang

Affiliation

Description
 

Team Name

MITLab

Corresponding Author

Jing-Wen Liu

Affiliation

Description
 

Team Name

STEPS

Corresponding Author

Boaz Ben-Moshe

Affiliation

Description
 

Team Name

Tencent TLBS

Corresponding Author

Ye Tian

Affiliation

Description

Indoor localization together with pervasive outdoor localization supports a lot of services and applications. We are a team from Location Based Service (LBS) department of Tencent Ltd. Localization service deployed by our department fused RF signals, magnetic field, and multiple mobile sensors available on commercial smartphones, which has been serving more than a million user each day. Reliable localization is provided with low power consumption and low data traffic both indoors and outdoors, which switches seamlessly. Location services developed by our team has been used in smart business, intelligent mobility, online-to-offline services and LBS based games.

Team Name

YNU-MCL

Corresponding Author

Chanseok-Lee

Affiliation

Description

We propose a system which incorpo rates multiple resources available in the environment for Indoor Position System (IPS). Our system is based on four kinds of commonly available resources: Wi-Fi infrastructure, Motion sensors, Geo-Magnetism and Camera. Fingerprinting technique is used for Wi-Fi bases positioning which provides the initial location information for Pedestrian Dead Reckoning (PDR) approach of motion tracking using inertial sensors commonly available in handheld devices. To compensate the non-ideal situations, we also employed geomagnetic field positioning and image recognition positioning in case of inappropriate or no Wi-Fi facility. Proposed IPS is a smart mobile-based system to estimate position locally, whereas for the fingerprinting survey of Wi-Fi, Geo-Magnetism and Camera are performed prior using a desktop system and mobile phone as a scanning device.

Team Name

INDORA

Corresponding Author

Miroslav Opiela

Affiliation

Description

Project INDORA originated from a few student research projects and final theses, especially the author's dissertation. Various bachelor and master theses have reviewed different aspects of a comprehensive indoor positioning system during recent years. Pedestrian dead-reckoning, map model and bayesian filtering are essential components of the proposed localization system. The main research focus is on a low-dimensional grid-based bayesian filtering, as a less elaborated alternative to Kalman and Particle filters widely used for the positioning. A semi-automatically generated map model helps to reduce the localization error introduced by noisy sensor measurements and inaccurate system configuration, e.g., a step length estimation. The considered use case involves the user with handheld smartphone. It relies mostly on the map and no additional infrastructure is required in the building. The floor transition detection based on barometer measurements allows the system to estimate the user position within a single floor.

Track 2 - Video based

Team Name

HanaMicron_where

Corresponding Author

Jisu Ha

Affiliation

Description

 

Team Name

Ariel Robotics

Corresponding Author

Boaz Ben-Moshe

Affiliation

Description

 

Team Name

Xiamen Univ.

Corresponding Author

Lingxiang Zheng

Affiliation

Description

Team Name

Kyushu Univ.

Corresponding Author

Hideaki Uchiyama

Affiliation

Description

 

Off-site Tracks

Track 3 - Smartphone based

Team Name

Yai

Corresponding Author

Ying-Ren(NIU-EE)

Affiliation
Department of Electrical Engineering, Yuan Ze University, Zhongli 32003, Taiwan MOST Joint Research Center for AI Technology and All Vista Healthcare, Taipei 10617, Taiwan Research Center for Information Technology Innovation, Academia Sinica, Taipei 11529, Taiwan Department of Electrical Engineering, National Ilan University, Yilan 26047, Taiwan

Description

 YAI team is consisted of Yuan Ze University, Academia Sinica, and National Ilan University, and is led by Prof. Shih-Hau Fang, Dr. Yu Taso, and Prof. Ying-Ren Chien, respectively. We are interested in developing algorithms for indoor positioning systems based on the sensor fusion, machine learning, and statistical signal processing perspective.

Team Name

XiheTech

Corresponding Author

Tian Xiaochun

Affiliation
Beijing Xihe Technology Co., Ltd.

Description

  Xihe Technology provides more accurate and convenient indoor and outdoor location access services, and is committed to making life easier and better for everyone. Our indoor and outdoor positioning method is achieved effective by integrating multi-source fusion positioning methods and various kinds of sensors including accelerometer, gyroscope, magnetic sensor, WIFI, Bluetooth, light and other sensors. Our products and solutions have been used in hospitals, supermarkets, transportation hubs and many other occasions.

Team Name

Echo State

Corresponding Author

Dario Angelone

Affiliation

Description

Team Name

UGent

Corresponding Author

Jens Trogh

Affiliation
UGent - WAVES

Description

The core of this location tracking system is a route mapping filter that is based on a motion model and the Viterbi principle, a technique related to Hidden Markov Models and backward belief propagation. The physical layout of a building is used to construct the most likely path instead of a sequence of independent, instantaneous estimates. Each paths consists of a chain of grid points and a cost that indicates the probability of this path at this time step. The path with the lowest cost after processing all sensor data is the most likely trajectory. The cost of a path is the sum of costs based on WiFi RSS measurements, barometer, accelerometer, and gyroscope data. This post-processing filter ensures physically realistic trajectories.

Team Name

Teleria

Corresponding Author

Abdallah SOBEHY

Affiliation

Description

Team Name

WiMag

Corresponding Author

Chen Zhang

Affiliation

Description

Team Name

Tencent

Corresponding Author

Ye Tian

Affiliation

Description

Team Name

Fineway

Corresponding Author

Ming Lyu

Affiliation

Description

Team Name

IOT2US

Corresponding Author

Bang Wu

Affiliation
Queen Mary University of London

Description

IoT2US Lab belongs to School of Electronic Engineering and Computer Science (EECS) of Queen Mary University of London. IoT2US is the abbreviation of IoT towards Ubiquitous, computing and, Science by all. IoT2US Lab’s overall aim is to use IoT as an enabler to promote a more inclusive, cross-disciplinary vision of science and computer technology by all. Our team members are Bang Wu (QMUL), Chengqi Ma (UCL), Stefan Poslad (supervisor, QMUL), David Selviah (supervisor, UCL), Wei Wu (WHU), Xiaoshuai Zhang (QMUL) , Guangyuan Zhang (QMUL) , Zixiang Ma (QMUL). Our research interests mainly includes indoor positioning and navigation, human activitiy recognition, spatio-temporal big data mining and pattern recognition and other IoT related areas. More informtion refers to iot.eecs.qmul.ac.uk.

Team Name

UMinho

Corresponding Author

Cristiano Pendao

Affiliation
Algoritmi Research Centre, University of Minho, Portugal

Description

The UMinho Team is a group of researchers from the University of Minho in Portugal, all members of the Algoritmi Research Centre – Group of Computer Communications and Pervasive Media. This group has been working in indoor positioning and navigation for more than ten years, with emphasis in Wi-Fi fingerprinting and solutions for healthcare and industrial applications. Members of this team have attended all IPIN conferences since its first edition in 2010, in Zurich, Switzerland. The University of Minho hosted IPIN 2011. A former team, integrating most of the members of this team competed at the 2015, 2016 and 2017 IPIN competition. For this competition (Track 3), the UMinho Team is experimenting with a completely new approach where data from multiple sensors are fused in an innovative way to estimate the trajectory followed by the user.

Team Name

Indora

Corresponding Author

Miroslav Opiela

Affiliation
Institute of Computer Science, Faculty of Science, P.J. Šafárik University (UPJS), Košice, Slovakia

Description

Project INDORA originated from a few student research projects and final theses, especially the author's dissertation. Various bachelor and master theses have reviewed different aspects of a comprehensive indoor positioning system during recent years. Pedestrian dead-reckoning, map model and bayesian filtering are essential components of the proposed localization system. The main research focus is on a low-dimensional grid-based bayesian filtering, as a less elaborated alternative to Kalman and Particle filters widely used for the positioning. A semi-automatically generated map model helps to reduce the localization error introduced by noisy sensor measurements and inaccurate system configuration, e.g., a step length estimation. The considered use case involves the user with handheld smartphone. It relies mostly on the map and no additional infrastructure is required in the building. The floor transition detection based on barometer measurements allows the system to estimate the user position within a single floor.

Team Name

Naverlabs

Corresponding Author

Leonid Antsfeld

Affiliation

Description

Team Name

Tonjgi

Corresponding Author

Liu Liu

Affiliation

Description

Team Name

AraraDS

Corresponding Author

Tomás Lungenstrass

Affiliation
Arara Chile

Description

Arara is engaged in developing advanced knowledge solutions and producing high-quality technology to address modern business and industry challenges.

Team Name

Intel Labs

Corresponding Author

Jeongsik Khoi

AffiliationIntel Labs, Intel Corporation, USA

Description

Our team has mainly focused on the range-based positioning techniques for Wi-Fi system. Using the received signal strength (RSS) or the round trip time (RTT) of wireless signal, the distances from neighboring access points (APs) can be measured, and consequently, the coordinates of the device can be obtained using the trilateration techniques. In this competition, we combine the positioning results with the pedestrian dead reckoning (PDR) techniques to improve the accuracy.

Track 4 - Foot-mounted IMU-based

Team Name

KIT

Corresponding Author

nicolai kronenwett

Affiliation

Description

Team Name

KIU-SNU

Corresponding Author

Seong Yun Cho

Affiliation

Description

Team Name

KYUSHU

Corresponding Author

Hideaki Uchiyama

Affiliation

Description

Team Name

SNU

Corresponding Author

Jae Hong Lee

Affiliation

Description

Team Name

AOE

Corresponding Author

Wenchao Zhang

Affiliation

Description

Track 5 - xDR in industrial scenarios

Team Name

KisekioL

Corresponding Author

Takayuki Saitou

Affiliation

Description

Team Name

Eurasia IoT

Corresponding Author

Gan Mathew Kien Lim

Affiliation

Description

Team Name

Kawaguchi Lab

Corresponding Author

Takuto Yoshida

Affiliation

Description

Team Name

Xihe Technology

Corresponding Author

TianXiaochun

Affiliation

Description

Team Name

Kyushu Univ.

Corresponding Author

Hideaki Uchiyama

Affiliation

Description