Szczegóły publikacji
Opis bibliograficzny
Real-time detection of small objects in automotive thermal images with modern deep neural architectures / Tomasz Balon, Mateusz KNAPIK, Bogusław CYGANEK // W: FedCSIS 2023 [Dokument elektroniczny] : communication papers of the 18th conference on Computer science and intelligence systems : September 17–20, 2023, Warsaw / eds. Maria Ganzha, [et al.]. — Wersja do Windows. — Dane tekstowe. — Warszawa : Polskie Towarzystwo Informatyczne, cop. 2023. — (Annals of Computer Science and Information Systems ; ISSN 2300-5963 ; Vol. 37). — Dod. ISBN (USB): 978-83-969601-4-6. — e-ISBN: 978-83-969601-3-9. — S. 29–35. — Wymagania systemowe: Adobe Reader. — Tryb dostępu: https://annals-csis.org/proceedings/2023/drp/pdf/8409.pdf [2023-10-27]. — Bibliogr. s. 34–35, Abstr. — M. Knapik – dod. afiliacja: MyLED Inc.
Autorzy (3)
Dane bibliometryczne
ID BaDAP | 149798 |
---|---|
Data dodania do BaDAP | 2023-11-28 |
DOI | 10.15439/2023F8409 |
Rok publikacji | 2023 |
Typ publikacji | materiały konferencyjne (aut.) |
Otwarty dostęp | |
Konferencja | 18th conference on Computer Science and Intelligence Systems |
Czasopismo/seria | Annals of Computer Science and Information Systems |
Abstract
Thermal imaging has shown great potential for improving object detection in automotive settings, particularly in low light or adverse weather conditions. To help and further develop this industry, we extend our previously shared Thermal Automotive Dataset by more than 2000 new images and 2 novel object detecting models based on YOLOv5 and YOLOv7 architecture. We point how important is the size of the dataset. Additionally, we compare the performance of both models, to see which is more reliable and superior in terms of detecting small objects in thermal spectrum. Furthermore, we analysed how preprocessing affects thermal imaging dataset and models basing on it. The new dataset is available free from the Internet.