Life Cycle of a SLAM System: Implementation, Evaluation and Port to the Project Tango Device

Thulio Araujo; Rafael Roberto; Jo o.Marcelo Teixeira; Franciso Simoes; Veronica Teichrieb; Joao Paulo Lima; Ermano Arruda

doi:10.1109/SVR.2016.13

Life Cycle of a SLAM System: Implementation, Evaluation and Port to the Project Tango Device

Thulio Araujo, Rafael Roberto, Jo o.Marcelo Teixeira, Franciso Simoes, Veronica Teichrieb, Joao Paulo Lima, Ermano Arruda

Department of Mechanical Engineering

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

7 Citations (SciVal)

Abstract

Augmented Reality (AR) applications are becoming popular recently. Among other things, AR requires a precise real-time tracking to work properly. Simultaneous Localization and Mapping (SLAM) is one way to perform this task. Commonly used in robotics applications, SLAM creates a map of the environment to use it as input to compute the pose while uses the pose to increment the map. At the same time, mobile devices are evolving faster lately. Along with more processing power and memory capabilities, they are being embedded with several powerful resources, such as depth sensors. Taking this into account, this work introduces STAM, a Simple Tracking and Mapping system that was developed in desktop and evaluated in a challenging scenario. Additionally, STAM was ported to a mobile version, using the Android platform and Google's Tango tablet device. Finally, the system was evaluated concerning its desktop version. The desktop version presented better tracking performance in simple scenarios with respect to reprojection error, but it presented a few drawbacks when dealing with the most complex ones. Regarding the mobile version, it proved to be slower than its desktop counterpart. However, it was more precise.

Original language	English
Title of host publication	Proceedings - 18th Symposium on Virtual and Augmented Reality, SVR 2016
Publisher	IEEE
Pages	10-19
Number of pages	10
ISBN (Electronic)	9781509041497
DOIs	https://doi.org/10.1109/SVR.2016.13
Publication status	Published - 21 Jul 2016
Event	18th Symposium on Virtual and Augmented Reality, SVR 2016 - Gramado, Brazil Duration: 21 Jun 2016 → 24 Jun 2016

Publication series

Name	Proceedings - 18th Symposium on Virtual and Augmented Reality, SVR 2016

Conference

Conference	18th Symposium on Virtual and Augmented Reality, SVR 2016
Country/Territory	Brazil
City	Gramado
Period	21/06/16 → 24/06/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

Google Project Tango
mobile devices
SLAM
tracking

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Media Technology
Computer Science Applications

Access to Document

10.1109/SVR.2016.13

Cite this

Araujo, T., Roberto, R., Teixeira, J. O. M., Simoes, F., Teichrieb, V., Lima, J. P., & Arruda, E. (2016). Life Cycle of a SLAM System: Implementation, Evaluation and Port to the Project Tango Device. In Proceedings - 18th Symposium on Virtual and Augmented Reality, SVR 2016 (pp. 10-19). Article 7517247 (Proceedings - 18th Symposium on Virtual and Augmented Reality, SVR 2016). IEEE. https://doi.org/10.1109/SVR.2016.13

Life Cycle of a SLAM System: Implementation, Evaluation and Port to the Project Tango Device. / Araujo, Thulio; Roberto, Rafael; Teixeira, Jo o.Marcelo et al.
Proceedings - 18th Symposium on Virtual and Augmented Reality, SVR 2016. IEEE, 2016. p. 10-19 7517247 (Proceedings - 18th Symposium on Virtual and Augmented Reality, SVR 2016).

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

Araujo, T, Roberto, R, Teixeira, JOM, Simoes, F, Teichrieb, V, Lima, JP & Arruda, E 2016, Life Cycle of a SLAM System: Implementation, Evaluation and Port to the Project Tango Device. in Proceedings - 18th Symposium on Virtual and Augmented Reality, SVR 2016., 7517247, Proceedings - 18th Symposium on Virtual and Augmented Reality, SVR 2016, IEEE, pp. 10-19, 18th Symposium on Virtual and Augmented Reality, SVR 2016, Gramado, Brazil, 21/06/16. https://doi.org/10.1109/SVR.2016.13

Araujo T, Roberto R, Teixeira JOM, Simoes F, Teichrieb V, Lima JP et al. Life Cycle of a SLAM System: Implementation, Evaluation and Port to the Project Tango Device. In Proceedings - 18th Symposium on Virtual and Augmented Reality, SVR 2016. IEEE. 2016. p. 10-19. 7517247. (Proceedings - 18th Symposium on Virtual and Augmented Reality, SVR 2016). doi: 10.1109/SVR.2016.13

@inproceedings{952407f6fb434c8395a81802e2e60f28,

title = "Life Cycle of a SLAM System: Implementation, Evaluation and Port to the Project Tango Device",

abstract = "Augmented Reality (AR) applications are becoming popular recently. Among other things, AR requires a precise real-time tracking to work properly. Simultaneous Localization and Mapping (SLAM) is one way to perform this task. Commonly used in robotics applications, SLAM creates a map of the environment to use it as input to compute the pose while uses the pose to increment the map. At the same time, mobile devices are evolving faster lately. Along with more processing power and memory capabilities, they are being embedded with several powerful resources, such as depth sensors. Taking this into account, this work introduces STAM, a Simple Tracking and Mapping system that was developed in desktop and evaluated in a challenging scenario. Additionally, STAM was ported to a mobile version, using the Android platform and Google's Tango tablet device. Finally, the system was evaluated concerning its desktop version. The desktop version presented better tracking performance in simple scenarios with respect to reprojection error, but it presented a few drawbacks when dealing with the most complex ones. Regarding the mobile version, it proved to be slower than its desktop counterpart. However, it was more precise.",

keywords = "Google Project Tango, mobile devices, SLAM, tracking",

author = "Thulio Araujo and Rafael Roberto and Teixeira, {Jo o.Marcelo} and Franciso Simoes and Veronica Teichrieb and Lima, {Joao Paulo} and Ermano Arruda",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 18th Symposium on Virtual and Augmented Reality, SVR 2016 ; Conference date: 21-06-2016 Through 24-06-2016",

year = "2016",

month = jul,

day = "21",

doi = "10.1109/SVR.2016.13",

language = "English",

series = "Proceedings - 18th Symposium on Virtual and Augmented Reality, SVR 2016",

publisher = "IEEE",

pages = "10--19",

booktitle = "Proceedings - 18th Symposium on Virtual and Augmented Reality, SVR 2016",

address = "USA United States",

}

TY - GEN

T1 - Life Cycle of a SLAM System

T2 - 18th Symposium on Virtual and Augmented Reality, SVR 2016

AU - Araujo, Thulio

AU - Roberto, Rafael

AU - Teixeira, Jo o.Marcelo

AU - Simoes, Franciso

AU - Teichrieb, Veronica

AU - Lima, Joao Paulo

AU - Arruda, Ermano

PY - 2016/7/21

Y1 - 2016/7/21

N2 - Augmented Reality (AR) applications are becoming popular recently. Among other things, AR requires a precise real-time tracking to work properly. Simultaneous Localization and Mapping (SLAM) is one way to perform this task. Commonly used in robotics applications, SLAM creates a map of the environment to use it as input to compute the pose while uses the pose to increment the map. At the same time, mobile devices are evolving faster lately. Along with more processing power and memory capabilities, they are being embedded with several powerful resources, such as depth sensors. Taking this into account, this work introduces STAM, a Simple Tracking and Mapping system that was developed in desktop and evaluated in a challenging scenario. Additionally, STAM was ported to a mobile version, using the Android platform and Google's Tango tablet device. Finally, the system was evaluated concerning its desktop version. The desktop version presented better tracking performance in simple scenarios with respect to reprojection error, but it presented a few drawbacks when dealing with the most complex ones. Regarding the mobile version, it proved to be slower than its desktop counterpart. However, it was more precise.

AB - Augmented Reality (AR) applications are becoming popular recently. Among other things, AR requires a precise real-time tracking to work properly. Simultaneous Localization and Mapping (SLAM) is one way to perform this task. Commonly used in robotics applications, SLAM creates a map of the environment to use it as input to compute the pose while uses the pose to increment the map. At the same time, mobile devices are evolving faster lately. Along with more processing power and memory capabilities, they are being embedded with several powerful resources, such as depth sensors. Taking this into account, this work introduces STAM, a Simple Tracking and Mapping system that was developed in desktop and evaluated in a challenging scenario. Additionally, STAM was ported to a mobile version, using the Android platform and Google's Tango tablet device. Finally, the system was evaluated concerning its desktop version. The desktop version presented better tracking performance in simple scenarios with respect to reprojection error, but it presented a few drawbacks when dealing with the most complex ones. Regarding the mobile version, it proved to be slower than its desktop counterpart. However, it was more precise.

KW - Google Project Tango

KW - mobile devices

KW - SLAM

KW - tracking

UR - http://www.scopus.com/inward/record.url?scp=84986184197&partnerID=8YFLogxK

U2 - 10.1109/SVR.2016.13

DO - 10.1109/SVR.2016.13

M3 - Chapter in a published conference proceeding

AN - SCOPUS:84986184197

T3 - Proceedings - 18th Symposium on Virtual and Augmented Reality, SVR 2016

SP - 10

EP - 19

BT - Proceedings - 18th Symposium on Virtual and Augmented Reality, SVR 2016

PB - IEEE

Y2 - 21 June 2016 through 24 June 2016

ER -

Life Cycle of a SLAM System: Implementation, Evaluation and Port to the Project Tango Device

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this