Pregled bibliografske jedinice broj: 1278466
Validation of Machine Learning-Based Lane Lines Detection Methods Using Different Datasets
Validation of Machine Learning-Based Lane Lines Detection Methods Using Different Datasets // Proceedings of IEEE ZINC 2023
Novi Sad, Srbija, 2023. str. 1-6 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 1278466 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Validation of Machine Learning-Based Lane Lines
Detection Methods Using Different Datasets
Autori
Jukić, Grgur ; Vranješ, Mario ; Vajak, Denis ; Vranješ, Denis
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of IEEE ZINC 2023
/ - Novi Sad, Srbija, 2023, 1-6
Skup
IEEE Zooming Innovation in Consumer Technology International Conference 2023 (ZINC 2023)
Mjesto i datum
Novi Sad, Srbija, 29.05.2023. - 31.05.2023
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
ADAS ; Lane Lines Detection ; Deep Learning ; CULane ; TuSimple ; LLAMAS ; SCNN
Sažetak
Advanced Driver Assistance System (ADAS) uses various sensors that exist in the vehicle to collect information about the vehicle and its surroundings. One of the most commonly used ADASs is the one designed to recognize driving lane lines. In this paper, analysis, and validation of freely available state-of-the art deep learning- based lane lines detection (LLD) methods are done using three different well-known datasets: CULane, TuSimple, and LLAMAS. To perform the validation, as part of this research, two converters of lane line label formats were made. Converters allow testing models that have been previously trained on a dataset that uses different lane line label formats so that their performances can be verified on other datasets with different lane line format types. The experimental results show that the adaptability of the model to the change of the dataset depends on the architecture used as the basis of the model for the LLD, and the similarity of the training set of the initially used dataset and the new, i.e. test dataset. All tested models showed shortcomings when tested on images from datasets on which they were not trained, which confirms that there is still no model that we can confidently say achieves high performance in all possible scenarios.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Računarstvo
POVEZANOST RADA
Projekti:
DGS-UNIOS-ZUP 2018-6 - Povećavanje razine pouzdanosti vožnje autonomnih vozila pomoću sustava kamera na vozilu (Vranješ, Mario, DGS - Interni natječaja Sveučilišta Josipa Jurja Strossmayera u Osijeku za znanstvenoistraživačke i umjetničke projekte UNIOS-ZUP 2018) ( CroRIS)
Ustanove:
Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek
