Naslov
Generative modeling of spatio-temporal traffic sign trajectories

Autori
Brkić, Karla ; Šegvić, Siniša ; Kalafatić, Zoran ; Sikirić, Ivan ; Pinz, Axel

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Computer Vision and Pattern Recognition Workshops (CVPRW), 2010 IEEE Computer Society Conference on / Aghajan, Hamid ; Morency, Louis-Philippe ; Nijholt, Anton ; Yang, Ming-Hsuan ; Ivanov, Yuri ; Braspenning, Ralph - Washington (MD) : Institute of Electrical and Electronics Engineers (IEEE), 2010, 25-31

ISBN
978-1-4244-7029-7

Skup
Workshop on Use of Context in Video Processing, in conjuction with CVPR 2010

Mjesto i datum
San Francisco (CA), Sjedinjene Američke Države, 13.06.2010. - 18.06.2010

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
computer vision

Sažetak
We consider the task of automatic detection and recognition of traffic signs in video. We show that successful off-the-shelf detection (Viola- Jones) and classification (SVM) systems yield unsatisfactory results. Our main concern are high false positive detection rates which occur due to sparseness of the traffic signs in videos. We address the problem by enforcing spatio-temporal consistency of the detections corresponding to a distinct sign in video. We also propose a generative model of the traffic sign motion in the image plane, which is obtained by clustering the trajectories filtered by an appropriate procedure. The contextual information recovered by the proposed model will be employed in our future research on recognizing traffic signs in video.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA