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

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceedingPeer review

Sammanfattning

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.

Originalspråkengelska
Titel på värdpublikation2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022
FörlagIEEE - Institute of Electrical and Electronics Engineers Inc.
Sidor3813-3818
Antal sidor6
ISBN (elektroniskt)9781665468800
DOI
StatusPublished - 2022
Evenemang25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022 - Macau, Kina
Varaktighet: 2022 okt. 82022 okt. 12

Publikationsserier

NamnIEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
Volym2022-October

Konferens

Konferens25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022
Land/TerritoriumKina
OrtMacau
Period2022/10/082022/10/12

Bibliografisk information

Publisher Copyright:
© 2022 IEEE.

Ämnesklassifikation (UKÄ)

  • Matematik

Fingeravtryck

Utforska forskningsämnen för ”Generalized Urban Traffic Surveillance (GUTS): World-Coordinate Tracking for Traffic Safety Applications”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här