Comprehensive Parameter Sweep for Learning-based Detector on Traffic Lights

Morten Bornø Jensen, Mark Philip Philipsen, Mohan M. Trivedi, Thomas B. Moeslund

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

1 Citationer (Scopus)
285 Downloads (Pure)

Abstrakt

Determining the optimal parameters for a given detection algorithm is not straightforward and what ends up as the final values is mostly based on experience and heuristics. In this paper we investigate the influence of three basic parameters in the widely used Aggregate Channel Features (ACF) object detector applied for traffic light detec- tion. Additionally, we perform an exhaustive search for the optimal pa- rameters for the night time data from the LISA Traffic Light Dataset. The optimized detector reaches an Area-Under-Curve of 66.63 % on cal- culated precision-recall curve.
OriginalsprogEngelsk
TitelAdvances in Visual Computing. ISVC 2016 : Lecture Notes in Computer Science (LNCS)
Vol/bind10073
ForlagSpringer
Publikationsdato10 dec. 2016
Sider92-100
DOI
StatusUdgivet - 10 dec. 2016
BegivenhedISVC16: 12th International Symposium on Visual Computing - Monte Carlo Resort & Casino, Las Vegas, USA
Varighed: 12 dec. 201614 dec. 2016
http://www.isvc.net

Konference

KonferenceISVC16: 12th International Symposium on Visual Computing
LokationMonte Carlo Resort & Casino
LandUSA
ByLas Vegas
Periode12/12/201614/12/2016
Internetadresse

Fingeraftryk Dyk ned i forskningsemnerne om 'Comprehensive Parameter Sweep for Learning-based Detector on Traffic Lights'. Sammen danner de et unikt fingeraftryk.

Citationsformater