Naslov
Can we replace real-world with synthetic data in deep learning-based ADAS algorithm development?

Autori
Jelić, Borna ; Grbić, Ratko ; Vranješ, Mario ; Mijić, David

Vrsta, podvrsta
Radovi u časopisima, znanstveni

Izvornik
IEEE consumer electronics magazine (2021)

Status rada
Online first

Ključne riječi
ADAS ; deep-learning ; synthetic data

Sažetak
Deep learning models require vast amounts of annotated training data. Gathering and annotating the data from the real world is an expensive and time-consuming process. Thus, synthetically generated data is being researched more and more. This paper tries to answer the question of whether and to what extent synthetically generated data can help in developing the advanced driver-assistance system (ADAS) algorithms for autonomous vehicles, for the object detection task based on deep learning. Two state-of-the-art deep learning object detectors were trained on various combinations of real-world and synthetic data. A total of 12 detectors were tested on real-world test images. Results show that synthetic data can contribute to better detector performance until a certain ratio between real-world and synthetic data is reached.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo

POVEZANOST RADA