Generalized Urban Traffic Surveillance (GUTS): World-Coordinate Tracking for Traffic Safety Applications

Martin Ahrnbom; Ivar Persson; Hakan Ardo; Mikael Nilsson

doi:10.1109/ITSC55140.2022.9921949

Generalized Urban Traffic Surveillance (GUTS): World-Coordinate Tracking for Traffic Safety Applications

Martin Ahrnbom, Ivar Persson, Hakan Ardo, Mikael Nilsson

Axis communications AB

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

Abstract

We present a new world-coordinate tracking algorithm for road users seen from static surveillance cameras, denoted GUTS. It is based upon the previously published UTS method but simplifies and replaces parts allowing association logic to work in world coordinates, by using a novel convolutional neural network denoted SAMHNet to convert every detection into world coordinates. Experimental evaluation on synthetic data shows a MOTA increase of 41 % or 153% depending on distance metric, compared to UTS. Furthermore, the system is verified to work on a real-world recording. We further introduce a synthetic dataset denoted UTOCS which is the first of its kind to be standardized and made publicly available, allowing fair comparison between methods.

Original language	English
Title of host publication	2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022
Publisher	IEEE - Institute of Electrical and Electronics Engineers Inc.
Pages	3813-3818
Number of pages	6
ISBN (Electronic)	9781665468800
DOIs	https://doi.org/10.1109/ITSC55140.2022.9921949
Publication status	Published - 2022
Event	25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022 - Macau, China Duration: 2022 Oct 8 → 2022 Oct 12

Publication series

Name	IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
Volume	2022-October

Conference

Conference	25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022
Country/Territory	China
City	Macau
Period	2022/10/08 → 2022/10/12

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Subject classification (UKÄ)

Mathematics

Access to Document

10.1109/ITSC55140.2022.9921949

Cite this

Ahrnbom, M., Persson, I., Ardo, H., & Nilsson, M. (2022). Generalized Urban Traffic Surveillance (GUTS): World-Coordinate Tracking for Traffic Safety Applications. In 2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022 (pp. 3813-3818). (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC; Vol. 2022-October). IEEE - Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITSC55140.2022.9921949

Ahrnbom, Martin ; Persson, Ivar ; Ardo, Hakan et al. / Generalized Urban Traffic Surveillance (GUTS) : World-Coordinate Tracking for Traffic Safety Applications. 2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022. IEEE - Institute of Electrical and Electronics Engineers Inc., 2022. pp. 3813-3818 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC).

@inproceedings{afe3ae716e0b4eecb9a7f398cbc62f7d,

title = "Generalized Urban Traffic Surveillance (GUTS): World-Coordinate Tracking for Traffic Safety Applications",

abstract = "We present a new world-coordinate tracking algorithm for road users seen from static surveillance cameras, denoted GUTS. It is based upon the previously published UTS method but simplifies and replaces parts allowing association logic to work in world coordinates, by using a novel convolutional neural network denoted SAMHNet to convert every detection into world coordinates. Experimental evaluation on synthetic data shows a MOTA increase of 41 % or 153% depending on distance metric, compared to UTS. Furthermore, the system is verified to work on a real-world recording. We further introduce a synthetic dataset denoted UTOCS which is the first of its kind to be standardized and made publicly available, allowing fair comparison between methods.",

author = "Martin Ahrnbom and Ivar Persson and Hakan Ardo and Mikael Nilsson",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022 ; Conference date: 08-10-2022 Through 12-10-2022",

year = "2022",

doi = "10.1109/ITSC55140.2022.9921949",

language = "English",

series = "IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC",

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

pages = "3813--3818",

booktitle = "2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022",

address = "United States",

}

Ahrnbom, M, Persson, I , Ardo, H & Nilsson, M 2022, Generalized Urban Traffic Surveillance (GUTS): World-Coordinate Tracking for Traffic Safety Applications. in 2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022. IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, vol. 2022-October, IEEE - Institute of Electrical and Electronics Engineers Inc., pp. 3813-3818, 25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022, Macau, China, 2022/10/08. https://doi.org/10.1109/ITSC55140.2022.9921949

Generalized Urban Traffic Surveillance (GUTS): World-Coordinate Tracking for Traffic Safety Applications. / Ahrnbom, Martin; Persson, Ivar ; Ardo, Hakan et al.
2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022. IEEE - Institute of Electrical and Electronics Engineers Inc., 2022. p. 3813-3818 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC; Vol. 2022-October).

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

TY - GEN

T1 - Generalized Urban Traffic Surveillance (GUTS)

T2 - 25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022

AU - Ahrnbom, Martin

AU - Persson, Ivar

AU - Ardo, Hakan

AU - Nilsson, Mikael

PY - 2022

Y1 - 2022

N2 - We present a new world-coordinate tracking algorithm for road users seen from static surveillance cameras, denoted GUTS. It is based upon the previously published UTS method but simplifies and replaces parts allowing association logic to work in world coordinates, by using a novel convolutional neural network denoted SAMHNet to convert every detection into world coordinates. Experimental evaluation on synthetic data shows a MOTA increase of 41 % or 153% depending on distance metric, compared to UTS. Furthermore, the system is verified to work on a real-world recording. We further introduce a synthetic dataset denoted UTOCS which is the first of its kind to be standardized and made publicly available, allowing fair comparison between methods.

AB - We present a new world-coordinate tracking algorithm for road users seen from static surveillance cameras, denoted GUTS. It is based upon the previously published UTS method but simplifies and replaces parts allowing association logic to work in world coordinates, by using a novel convolutional neural network denoted SAMHNet to convert every detection into world coordinates. Experimental evaluation on synthetic data shows a MOTA increase of 41 % or 153% depending on distance metric, compared to UTS. Furthermore, the system is verified to work on a real-world recording. We further introduce a synthetic dataset denoted UTOCS which is the first of its kind to be standardized and made publicly available, allowing fair comparison between methods.

U2 - 10.1109/ITSC55140.2022.9921949

DO - 10.1109/ITSC55140.2022.9921949

M3 - Paper in conference proceeding

AN - SCOPUS:85141824775

T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

SP - 3813

EP - 3818

BT - 2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022

PB - IEEE - Institute of Electrical and Electronics Engineers Inc.

Y2 - 8 October 2022 through 12 October 2022

ER -

Ahrnbom M, Persson I , Ardo H , Nilsson M. Generalized Urban Traffic Surveillance (GUTS): World-Coordinate Tracking for Traffic Safety Applications. In 2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022. IEEE - Institute of Electrical and Electronics Engineers Inc. 2022. p. 3813-3818. (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC). doi: 10.1109/ITSC55140.2022.9921949

Generalized Urban Traffic Surveillance (GUTS): World-Coordinate Tracking for Traffic Safety Applications

Abstract

Publication series

Conference

Bibliographical note

Subject classification (UKÄ)

Access to Document

Fingerprint

Cite this