AI-Based Visual Odometry Implementation on an Embedded System

Oguzhan Büyüksolak; Ece Olcay Günes

doi:10.1109/ICEEE59925.2023.00016

AI-Based Visual Odometry Implementation on an Embedded System

Oguzhan Büyüksolak
, Ece Olcay Günes

Elektronik ve Hab.Müh.Bölümü

Istanbul Technical University

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

1 Atıf (Scopus)

Özet

Embedded visual odometry(VO) implementation may provide a low-power, small-size alternative or compan-ion positioning system to the Global Navigation Satellite Systems(GNSS) and Inertial Navigation System(INS). As the em-bedded systems are memory scarce, in this paper, a new low-memory footprint neural network-based visual odometry method that is implementable on embedded systems is introduced and evaluated. To deploy the neural network, MAX78002 [1] artificial intelligence microcontroller has been chosen as the embedded platform. To the best of our knowledge, this is the first study that provides a microcontroller-based visual odometry solution.

Orijinal dil	İngilizce
Ana bilgisayar yayını başlığı	Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023
Yayınlayan	Institute of Electrical and Electronics Engineers Inc.
Sayfalar	47-51
Sayfa sayısı	5
ISBN (Elektronik)	9798350304299
DOI'lar	https://doi.org/10.1109/ICEEE59925.2023.00016
Yayın durumu	Yayınlandı - 2023
Etkinlik	10th International Conference on Electrical and Electronics Engineering, ICEEE 2023 - Istanbul, Türkiye Süre: 8 May 2023 → 10 May 2023

Yayın serisi

Adı	Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	10th International Conference on Electrical and Electronics Engineering, ICEEE 2023
Ülke/Bölge	Türkiye
Şehir	Istanbul
Periyot	8/05/23 → 10/05/23

Bibliyografik not

Publisher Copyright:
© 2023 IEEE.

Belgeye Erişim

10.1109/ICEEE59925.2023.00016

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

Büyüksolak, O., & Günes, E. O. (2023). AI-Based Visual Odometry Implementation on an Embedded System. In Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023 (pp. 47-51). (Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICEEE59925.2023.00016

Büyüksolak, Oguzhan ; Günes, Ece Olcay. / AI-Based Visual Odometry Implementation on an Embedded System. Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 47-51 (Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023).

@inproceedings{fa11e296cd6a4086a39aca67ce7771e8,

title = "AI-Based Visual Odometry Implementation on an Embedded System",

abstract = "Embedded visual odometry(VO) implementation may provide a low-power, small-size alternative or compan-ion positioning system to the Global Navigation Satellite Systems(GNSS) and Inertial Navigation System(INS). As the em-bedded systems are memory scarce, in this paper, a new low-memory footprint neural network-based visual odometry method that is implementable on embedded systems is introduced and evaluated. To deploy the neural network, MAX78002 [1] artificial intelligence microcontroller has been chosen as the embedded platform. To the best of our knowledge, this is the first study that provides a microcontroller-based visual odometry solution.",

keywords = "CNN, Deep Learning, Embedded System, KITTI, Visual Odometry",

author = "Oguzhan B{\"u}y{\"u}ksolak and G{\"u}nes, \{Ece Olcay\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023 ; Conference date: 08-05-2023 Through 10-05-2023",

year = "2023",

doi = "10.1109/ICEEE59925.2023.00016",

language = "English",

series = "Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "47--51",

booktitle = "Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023",

address = "United States",

}

Büyüksolak, O & Günes, EO 2023, AI-Based Visual Odometry Implementation on an Embedded System. in Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023. Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023, Institute of Electrical and Electronics Engineers Inc., pp. 47-51, 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023, Istanbul, Türkiye, 8/05/23. https://doi.org/10.1109/ICEEE59925.2023.00016

AI-Based Visual Odometry Implementation on an Embedded System. / Büyüksolak, Oguzhan; Günes, Ece Olcay.
Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 47-51 (Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023).

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

TY - GEN

T1 - AI-Based Visual Odometry Implementation on an Embedded System

AU - Büyüksolak, Oguzhan

AU - Günes, Ece Olcay

PY - 2023

Y1 - 2023

N2 - Embedded visual odometry(VO) implementation may provide a low-power, small-size alternative or compan-ion positioning system to the Global Navigation Satellite Systems(GNSS) and Inertial Navigation System(INS). As the em-bedded systems are memory scarce, in this paper, a new low-memory footprint neural network-based visual odometry method that is implementable on embedded systems is introduced and evaluated. To deploy the neural network, MAX78002 [1] artificial intelligence microcontroller has been chosen as the embedded platform. To the best of our knowledge, this is the first study that provides a microcontroller-based visual odometry solution.

AB - Embedded visual odometry(VO) implementation may provide a low-power, small-size alternative or compan-ion positioning system to the Global Navigation Satellite Systems(GNSS) and Inertial Navigation System(INS). As the em-bedded systems are memory scarce, in this paper, a new low-memory footprint neural network-based visual odometry method that is implementable on embedded systems is introduced and evaluated. To deploy the neural network, MAX78002 [1] artificial intelligence microcontroller has been chosen as the embedded platform. To the best of our knowledge, this is the first study that provides a microcontroller-based visual odometry solution.

KW - CNN

KW - Deep Learning

KW - Embedded System

KW - KITTI

KW - Visual Odometry

UR - https://www.scopus.com/pages/publications/85178997920

U2 - 10.1109/ICEEE59925.2023.00016

DO - 10.1109/ICEEE59925.2023.00016

M3 - Conference contribution

AN - SCOPUS:85178997920

T3 - Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023

SP - 47

EP - 51

BT - Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023

Y2 - 8 May 2023 through 10 May 2023

ER -

Büyüksolak O, Günes EO. AI-Based Visual Odometry Implementation on an Embedded System. In Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 47-51. (Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023). doi: 10.1109/ICEEE59925.2023.00016

AI-Based Visual Odometry Implementation on an Embedded System

Özet

Yayın serisi

???event.eventtypes.event.conference???

Bibliyografik not

Belgeye Erişim

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap