RUS  ENG
Full version
JOURNALS // Computer Optics // Archive

Computer Optics, 2015 Volume 39, Issue 5, Pages 795–800 (Mi co46)

This article is cited in 9 papers

IMAGE PROCESSING, PATTERN RECOGNITION

Tracking traffic signs in video sequences based on a vehicle velocity

P. Y. Yakimovab

a Image Processing Systems Institute, Russian Academy of Sciences, Samara, Russia
b Samara State Aerospace University, Samara, Russia

Abstract: The paper proposes an efficient algorithm for road sign detection in a video obtained from a car dash camera. The algorithms for road sign detection and recognition are implemented using CUDA and operate in real time. A vehicle velocity is used to predict the road sign position in adjacent frames in a video sequence. The paper shows that the road sign tracking of this type improves the system reliability. The experimental results have confirmed high efficiency of the developed road sign detection system.

Keywords: traffic sign detection, traffic sign tracking, image processing, computer vision system, GPU.

Received: 01.04.2015
Revised: 12.10.2015

DOI: 10.18287/0134-2452-2015-39-5-795-800



© Steklov Math. Inst. of RAS, 2026