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.
Originalspråk | engelska |
---|---|
Titel på värdpublikation | 2022 IEEE 25th International Conference on Intelligent Transportation Systems, ITSC 2022 |
Förlag | IEEE - Institute of Electrical and Electronics Engineers Inc. |
Sidor | 3813-3818 |
Antal sidor | 6 |
ISBN (elektroniskt) | 9781665468800 |
DOI | |
Status | Published - 2022 |
Evenemang | 25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022 - Macau, Kina Varaktighet: 2022 okt. 8 → 2022 okt. 12 |
Publikationsserier
Namn | IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC |
---|---|
Volym | 2022-October |
Konferens
Konferens | 25th IEEE International Conference on Intelligent Transportation Systems, ITSC 2022 |
---|---|
Land/Territorium | Kina |
Ort | Macau |
Period | 2022/10/08 → 2022/10/12 |
Bibliografisk information
Publisher Copyright:© 2022 IEEE.
Ämnesklassifikation (UKÄ)
- Matematik