Sliding Window Object Detection without Spatial Clustering of Raw Detection Responses (CROSBI ID 597599)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Šegvić, Siniša ; Kalafatić, Zoran ; Kovaček, Ivan
engleski
Sliding Window Object Detection without Spatial Clustering of Raw Detection Responses
Sliding window object detection has received remarkable attention in recent years due to great versatility and extraordinary detection performance. However, straightforward applications of the concept fail to meet criteria of real applications due to insufficient precision and inaccurate localization. Localization accuracy is especially important when the detection needs to be followed by recognition. In this paper, we present a detection approach which completely obviates the need for blind spatial clustering of nearby detection responses, which is known as a major factor of localization inaccuracy. The approach has been evaluated on traffic sign detection, where we consider the superclass of triangular warning signs. The obtained results confirm the viability of the approach and provide useful directions for future work.
object detection; sliding window; bootstrap training
DOI 978-3-902823-11-3
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
114-119.
2012.
objavljeno
Podaci o matičnoj publikaciji
Proceedings of 10th IFAC Symposium on Robot Control SYROCO2012
Petrovic, Ivan, Korondi, Peter
Kidlington: Elsevier
978-3-902823-11-3
Podaci o skupu
10th IFAC Symposium on Robot Control 2012 (SYROCO 2012)
predavanje
05.09.2012-07.09.2012
Dubrovnik, Hrvatska