Image Recognition to Improve Positioning in Smart Urban Environments

This paper describes a solution and algorithm to enhance positioning in outdoor environments with high buildings to be used in a mobile application to aid visually impaired people for navigation purposes. We used an image recognition algorithm and adjusted the android app algorithm to decrease the initial error average of 85 m (without any correction from GPS obtained signal) to a 5 m error, in the final version of our solution.

[1]  Gretchen A. Stevens,et al.  Magnitude, temporal trends, and projections of the global prevalence of blindness and distance and near vision impairment: a systematic review and meta-analysis. , 2017, The Lancet. Global health.

[2]  Xiaoji Niu,et al.  High-Accuracy Positioning in Urban Environments Using Single-Frequency Multi-GNSS RTK/MEMS-IMU Integration , 2018, Remote. Sens..

[3]  Hui Lin,et al.  UWB, Multi-sensors and Wifi-Mesh based precision positioning for urban rail traffic , 2010, 2010 Ubiquitous Positioning Indoor Navigation and Location Based Service.

[4]  Ana Filomena Curralo,et al.  A Case Study for the Promotion of Urban Mobility for Visually Impaired People , 2019 .

[5]  Yunhao Liu,et al.  Human Mobility Enhances Global Positioning Accuracy for Mobile Phone Localization , 2015, IEEE Transactions on Parallel and Distributed Systems.

[6]  Changdon Kee,et al.  Position Accuracy Improvement by Implementing the DGNSS-CP Algorithm in Smartphones , 2016, Sensors.

[7]  Bian Shaofeng,et al.  Research on BeiDou positioning performance in urban environments , 2013, 2013 IEEE International Conference on Signal Processing, Communication and Computing (ICSPCC 2013).

[8]  K. Rouabah,et al.  GNSS Multipath Reduction Using GPS and DGPS in the Real Case , 2017 .

[9]  Valérie Renaudin,et al.  Pedestrian track estimation with handheld monocular camera and inertial-magnetic sensor for urban augmented reality , 2017, 2017 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[10]  Mieczysław Bakuła,et al.  Study Of Differential Code GPS/GLONASS Positioning , 2014 .

[11]  Tomasz Adamek,et al.  Enhancing global positioning by image recognition , 2011 .

[12]  Valérie Renaudin,et al.  Hybrid visual and inertial position and orientation estimation based on known urban 3D models , 2016, 2016 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[13]  Mahdi Salarian,et al.  Accurate localization in dense urban area using Google street view images , 2014, 2015 SAI Intelligent Systems Conference (IntelliSys).

[14]  V. Satya Srinivas,et al.  Mobile position estimation with RSS Based techniques in an urban city with multiple multi-storied structures , 2014, 2014 USNC-URSI Radio Science Meeting (Joint with AP-S Symposium).

[15]  Piotr Korbel,et al.  POI explorer - A sonified mobile application aiding the visually impaired in urban navigation , 2014, 2014 Federated Conference on Computer Science and Information Systems.

[16]  Yunhao Liu,et al.  Footprints elicit the truth: Improving global positioning accuracy via local mobility , 2013, 2013 Proceedings IEEE INFOCOM.

[17]  Sara Paiva,et al.  Mobile solutions for visually impaired people: Case study in Viana do Castelo Historical Center , 2017, 2017 12th Iberian Conference on Information Systems and Technologies (CISTI).

[18]  Suhua Tang,et al.  Improvement of Pedestrian Positioning Precision by Using Spatial Correlation of Multipath Error , 2018, 2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES).

[19]  E. Duflos,et al.  Gnss performance enhancement in urban environment based on pseudo-range error model , 2008, 2008 IEEE/ION Position, Location and Navigation Symposium.

[20]  Julian Eggert,et al.  Camera to map alignment for accurate low-cost lane-level scene interpretation , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).