Learning to Detect Traffic Signs: Comparative Evaluation of Synthetic and Real-World Datasets

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

22 Citationer (Scopus)
302 Downloads (Pure)

Abstrakt

This study compares the performance of sign detection based on synthetic training data to the performance of detection based on real-world training images. Viola-Jones detectors are created for 4 different traffic signs with both synthetic and real data, and varying numbers of training samples. The detectors are tested and compared. The result is that while others have successfully used synthetic training data in a classification context, it does not seem to be a good solution for detection. Even when the synthetic data covers a large part of the parameter space, it still performs significantly worse than real-world data.
OriginalsprogEngelsk
Titel21st International Conference on Pattern Recognition
ForlagIEEE
Publikationsdato11 nov. 2012
Sider3452-3455
ISBN (Trykt)978-1-4673-2216-4
StatusUdgivet - 11 nov. 2012
BegivenhedInternation Conference on Pattern Recognition - Tsukuba International Congress Center, Tsukuba Science City, Japan
Varighed: 11 nov. 201215 nov. 2012
Konferencens nummer: 21

Konference

KonferenceInternation Conference on Pattern Recognition
Nummer21
LokationTsukuba International Congress Center
Land/OmrådeJapan
ByTsukuba Science City
Periode11/11/201215/11/2012

Fingeraftryk

Dyk ned i forskningsemnerne om 'Learning to Detect Traffic Signs: Comparative Evaluation of Synthetic and Real-World Datasets'. Sammen danner de et unikt fingeraftryk.

Citationsformater