Implementation and Accuracy Evaluation of Fixed Camera-Based Object Positioning System Employing CNN-Detector

Tero Partanen; Philipp Muller; Jussi Collin; Jani Björklund

doi:10.1109/EUVIP50544.2021.9483987

Implementation and Accuracy Evaluation of Fixed Camera-Based Object Positioning System Employing CNN-Detector

Tero Partanen, Philipp Muller, Jussi Collin, Jani Björklund

Tietotekniikka

Tutkimustuotos: Konferenssiartikkeli › Scientific › vertaisarvioitu

17 Lataukset (Pure)

Abstrakti

Today, different positioning applications such as location-based services and autonomous navigation are requiring more and more precision. Especially fully autonomous navigation requires accurate positioning solution, not only for the vehicle but also for the surrounding objects. Thus, many new positioning techniques, algorithms and fusion schemes have been developed. One essential technique is visual positioning. Thanks to intensive research in neural networks and deep learning, Convolutional Neural Network-based (CNN) object detectors have evolved greatly in recent years. This paper proposes a widely deployable scheme of fixed camera-based (e.g. surveillance camera) object positioning utilizing the CNN-detector. The accuracy of the implemented positioning solution is evaluated with precise Real-Time Kinematic (RTK) satellite positioning receiver. The implemented system can be used in indoors and outdoors, and it can estimate simultaneously positions from multiple camera views for multiple objects in real-Time. When positioning a person, the measured mean positioning error was 10.7-15.6 cm with a simple bias correction and a standard deviation was 6.7-8.7 cm. Thus, the accuracy is excellent and would be sufficient to wide variety of applications.

Alkuperäiskieli	Englanti
Otsikko	Proceedings of the 2021 9th European Workshop on Visual Information Processing, EUVIP 2021
Toimittajat	A. Beghdadi, F. Alaya Cheikh, J.M.R.S. Tavares, A. Mokraoui, G. Valenzise, L. Oudre, M.A. Qureshi
Kustantaja	IEEE
Sivumäärä	6
ISBN (elektroninen)	9781665432306
ISBN (painettu)	9781665432313
DOI - pysyväislinkit	https://doi.org/10.1109/EUVIP50544.2021.9483987
Tila	Julkaistu - 2021
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	European Workshop on Visual Information Processing - Paris, Ranska Kesto: 23 kesäk. 2021 → 25 kesäk. 2021

Julkaisusarja

Nimi	European Workshop on Visual Information Processing
ISSN (painettu)	2164-974X
ISSN (elektroninen)	2471-8963

Conference

Conference	European Workshop on Visual Information Processing
Maa/Alue	Ranska
Kaupunki	Paris
Ajanjakso	23/06/21 → 25/06/21

Julkaisufoorumi-taso

Jufo-taso 1

!!ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Information Systems
Signal Processing

Pääsy asiakirjaan

10.1109/EUVIP50544.2021.9483987

CameraPositioningSystem_final
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Accepted author manuscript, 435 KB

http://urn.fi/URN:NBN:fi:tuni-202109227192

Siteeraa tätä

Partanen, T., Muller, P., Collin, J., & Björklund, J. (2021). Implementation and Accuracy Evaluation of Fixed Camera-Based Object Positioning System Employing CNN-Detector. teoksessa A. Beghdadi, F. A. Cheikh, J. M. R. S. Tavares, A. Mokraoui, G. Valenzise, L. Oudre, & M. A. Qureshi (Toimittajat), Proceedings of the 2021 9th European Workshop on Visual Information Processing, EUVIP 2021 [9483987] (European Workshop on Visual Information Processing). IEEE. https://doi.org/10.1109/EUVIP50544.2021.9483987

Partanen, Tero ; Muller, Philipp ; Collin, Jussi et al. / Implementation and Accuracy Evaluation of Fixed Camera-Based Object Positioning System Employing CNN-Detector. Proceedings of the 2021 9th European Workshop on Visual Information Processing, EUVIP 2021. Toimittaja / A. Beghdadi ; F. Alaya Cheikh ; J.M.R.S. Tavares ; A. Mokraoui ; G. Valenzise ; L. Oudre ; M.A. Qureshi. IEEE, 2021. (European Workshop on Visual Information Processing).

@inproceedings{acc0606194064a9ebd3f797a88c43b01,

title = "Implementation and Accuracy Evaluation of Fixed Camera-Based Object Positioning System Employing CNN-Detector",

abstract = "Today, different positioning applications such as location-based services and autonomous navigation are requiring more and more precision. Especially fully autonomous navigation requires accurate positioning solution, not only for the vehicle but also for the surrounding objects. Thus, many new positioning techniques, algorithms and fusion schemes have been developed. One essential technique is visual positioning. Thanks to intensive research in neural networks and deep learning, Convolutional Neural Network-based (CNN) object detectors have evolved greatly in recent years. This paper proposes a widely deployable scheme of fixed camera-based (e.g. surveillance camera) object positioning utilizing the CNN-detector. The accuracy of the implemented positioning solution is evaluated with precise Real-Time Kinematic (RTK) satellite positioning receiver. The implemented system can be used in indoors and outdoors, and it can estimate simultaneously positions from multiple camera views for multiple objects in real-Time. When positioning a person, the measured mean positioning error was 10.7-15.6 cm with a simple bias correction and a standard deviation was 6.7-8.7 cm. Thus, the accuracy is excellent and would be sufficient to wide variety of applications. ",

keywords = "Camera-based positioning, convolutional neural networks (CNN), object detection, RTK GNSS, visual localization",

author = "Tero Partanen and Philipp Muller and Jussi Collin and Jani Bj{\"o}rklund",

note = "JUFOID=71968 Funding Information: This Research was financially supported by Business Finland as part of the AUTOPORT project. More details on the project and partners are available at [50]. Publisher Copyright: {\textcopyright} 2021 IEEE.; European Workshop on Visual Information Processing ; Conference date: 23-06-2021 Through 25-06-2021",

year = "2021",

doi = "10.1109/EUVIP50544.2021.9483987",

language = "English",

isbn = "9781665432313",

series = "European Workshop on Visual Information Processing",

publisher = "IEEE",

editor = "A. Beghdadi and Cheikh, {F. Alaya} and J.M.R.S. Tavares and A. Mokraoui and G. Valenzise and L. Oudre and M.A. Qureshi",

booktitle = "Proceedings of the 2021 9th European Workshop on Visual Information Processing, EUVIP 2021",

}

Partanen, T , Muller, P, Collin, J & Björklund, J 2021, Implementation and Accuracy Evaluation of Fixed Camera-Based Object Positioning System Employing CNN-Detector. julkaisussa A Beghdadi, FA Cheikh, JMRS Tavares, A Mokraoui, G Valenzise, L Oudre & MA Qureshi (toim), Proceedings of the 2021 9th European Workshop on Visual Information Processing, EUVIP 2021., 9483987, European Workshop on Visual Information Processing, IEEE, European Workshop on Visual Information Processing, Paris, Ranska, 23/06/21. https://doi.org/10.1109/EUVIP50544.2021.9483987

Implementation and Accuracy Evaluation of Fixed Camera-Based Object Positioning System Employing CNN-Detector. / Partanen, Tero ; Muller, Philipp; Collin, Jussi et al.

Proceedings of the 2021 9th European Workshop on Visual Information Processing, EUVIP 2021. toim. / A. Beghdadi; F. Alaya Cheikh; J.M.R.S. Tavares; A. Mokraoui; G. Valenzise; L. Oudre; M.A. Qureshi. IEEE, 2021. 9483987 (European Workshop on Visual Information Processing).

Tutkimustuotos: Konferenssiartikkeli › Scientific › vertaisarvioitu

TY - GEN

T1 - Implementation and Accuracy Evaluation of Fixed Camera-Based Object Positioning System Employing CNN-Detector

AU - Partanen, Tero

AU - Muller, Philipp

AU - Collin, Jussi

AU - Björklund, Jani

N1 - JUFOID=71968 Funding Information: This Research was financially supported by Business Finland as part of the AUTOPORT project. More details on the project and partners are available at [50]. Publisher Copyright: © 2021 IEEE.

PY - 2021

Y1 - 2021

N2 - Today, different positioning applications such as location-based services and autonomous navigation are requiring more and more precision. Especially fully autonomous navigation requires accurate positioning solution, not only for the vehicle but also for the surrounding objects. Thus, many new positioning techniques, algorithms and fusion schemes have been developed. One essential technique is visual positioning. Thanks to intensive research in neural networks and deep learning, Convolutional Neural Network-based (CNN) object detectors have evolved greatly in recent years. This paper proposes a widely deployable scheme of fixed camera-based (e.g. surveillance camera) object positioning utilizing the CNN-detector. The accuracy of the implemented positioning solution is evaluated with precise Real-Time Kinematic (RTK) satellite positioning receiver. The implemented system can be used in indoors and outdoors, and it can estimate simultaneously positions from multiple camera views for multiple objects in real-Time. When positioning a person, the measured mean positioning error was 10.7-15.6 cm with a simple bias correction and a standard deviation was 6.7-8.7 cm. Thus, the accuracy is excellent and would be sufficient to wide variety of applications.

AB - Today, different positioning applications such as location-based services and autonomous navigation are requiring more and more precision. Especially fully autonomous navigation requires accurate positioning solution, not only for the vehicle but also for the surrounding objects. Thus, many new positioning techniques, algorithms and fusion schemes have been developed. One essential technique is visual positioning. Thanks to intensive research in neural networks and deep learning, Convolutional Neural Network-based (CNN) object detectors have evolved greatly in recent years. This paper proposes a widely deployable scheme of fixed camera-based (e.g. surveillance camera) object positioning utilizing the CNN-detector. The accuracy of the implemented positioning solution is evaluated with precise Real-Time Kinematic (RTK) satellite positioning receiver. The implemented system can be used in indoors and outdoors, and it can estimate simultaneously positions from multiple camera views for multiple objects in real-Time. When positioning a person, the measured mean positioning error was 10.7-15.6 cm with a simple bias correction and a standard deviation was 6.7-8.7 cm. Thus, the accuracy is excellent and would be sufficient to wide variety of applications.

KW - Camera-based positioning

KW - convolutional neural networks (CNN)

KW - object detection

KW - RTK GNSS

KW - visual localization

U2 - 10.1109/EUVIP50544.2021.9483987

DO - 10.1109/EUVIP50544.2021.9483987

M3 - Conference contribution

AN - SCOPUS:85111416300

SN - 9781665432313

T3 - European Workshop on Visual Information Processing

BT - Proceedings of the 2021 9th European Workshop on Visual Information Processing, EUVIP 2021

A2 - Beghdadi, A.

A2 - Cheikh, F. Alaya

A2 - Tavares, J.M.R.S.

A2 - Mokraoui, A.

A2 - Valenzise, G.

A2 - Oudre, L.

A2 - Qureshi, M.A.

PB - IEEE

T2 - European Workshop on Visual Information Processing

Y2 - 23 June 2021 through 25 June 2021

ER -

Partanen T , Muller P, Collin J, Björklund J. Implementation and Accuracy Evaluation of Fixed Camera-Based Object Positioning System Employing CNN-Detector. julkaisussa Beghdadi A, Cheikh FA, Tavares JMRS, Mokraoui A, Valenzise G, Oudre L, Qureshi MA, toimittajat, Proceedings of the 2021 9th European Workshop on Visual Information Processing, EUVIP 2021. IEEE. 2021. 9483987. (European Workshop on Visual Information Processing). https://doi.org/10.1109/EUVIP50544.2021.9483987

Implementation and Accuracy Evaluation of Fixed Camera-Based Object Positioning System Employing CNN-Detector

Abstrakti

Julkaisusarja

Conference

Julkaisufoorumi-taso

!!ASJC Scopus subject areas

Pääsy asiakirjaan

Sormenjälki

Siteeraa tätä