Pregled bibliografske jedinice broj: 1193776
HistWind2 - An Algorithm for Efficient Lane Detection in Highway and Suburban Environments
HistWind2 - An Algorithm for Efficient Lane Detection in Highway and Suburban Environments // IEEE consumer electronics magazine, (2022), 1-9 doi:10.1109/MCE.2022.3171929 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 1193776 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
HistWind2 - An Algorithm for Efficient Lane
Detection in Highway and Suburban Environments
Autori
Vajak, Denis ; Vranješ, Mario ; Grbić, Ratko ; Vranješ, Denis
Izvornik
IEEE consumer electronics magazine (2162-2248)
(2022);
1-9
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
lane detection ; automotive ; computer vision
Sažetak
Lane Detection (LD) plays an important role in several Advanced Driver Assistance Systems (ADASs). In this paper, a new solution for LD, dubbed HistWind2, is presented. HistWind2 solution is based on processing image captured by a front view camera and is comprised of three algorithm processing blocks: Image Pre-Processing Block, Histogram Peak Identification Block, and Sliding Window Block. Parameters of the algorithms within processing blocks are adjusted using particle swarm optimization on a training data set, after which the performance of the solution is compared against a freely available and well-known state- of-the-art deep learning-based solution on a test data set. The results show that HistWind2 achieves a higher F1-measure and precision while running on a CPU in real time. HistWind2 can be implemented on hardware with limited resources, making it suitable for use in modern vehicles. HistWind2 can process up to 21 frames per second when using 1640x590 pixel frames and running on AMD Ryzen 5 1600 CPU with 24 GB of RAM.
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)
MZO Ustanova-Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek-IZIP FERIT 2022 - Prilagodba modela dubokog učenja za primjenu u ADAS algoritmima (Vranješ, Mario, MZO Ustanova ) ( CroRIS)
Ustanove:
Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek
