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

Ahrnbom, Martin (author): Lund University,Lunds universitet,Mathematical Imaging Group,Forskargrupper vid Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Lund University Research Groups,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH

Persson, Ivar (author): Lund University,Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH

Nilsson, Mikael (author): Lund University,Lunds universitet,Mathematical Imaging Group,Forskargrupper vid Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,LTH profilområde: Teknik för hälsa,LTH profilområden,Lund University Research Groups,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH,LTH Profile Area: Engineering Health,LTH Profile areas,Faculty of Engineering, LTH

(creator_code:org_t)

2022
2022
English 6 s.
In: 2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022. - 9781665468800 ; 2022-October, s. 3813-3818

Related links:: http://dx.doi.org/10...; show more...; https://lup.lub.lu.s...; https://doi.org/10.1...; show less...

Abstract Subject headings

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.

By the author/editor: Ahrnbom, Martin; Persson, Ivar; Ardo, Hakan; Nilsson, Mikael

About the subject

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.