Real-Time Digital Image Segmentation and Object Classification

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F09%3APU81454" target="_blank" >RIV/00216305:26220/09:PU81454 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Real-Time Digital Image Segmentation and Object Classification

Original language description

This paper proposes a new method for the detection and classification of road signs from video sequences captured by digital video camera. The method can be divided into two main steps. In the first step, the road signs are detected, where a method for color segmentation improved by Canny edge detecting is used for this purpose. Detected signs are normalized in size in order to be classified in the second step, where a linear classifier is used to determine the type of the detected sign in combination with Kalman filtering which provide the prediction of the possible position of the road sign in the captured video frames. This processing improves the classification performance because it enables the classifier to determine the type of the sign from each captured frame separately. This procedure enables the proposed algorithm to combine the classification results obtained from each frame in order to make the final decision.

Czech name

Real-Time Digital Image Segmentation and Object Classification

Czech description

This paper proposes a new method for the detection and classification of road signs from video sequences captured by digital video camera. The method can be divided into two main steps. In the first step, the road signs are detected, where a method for color segmentation improved by Canny edge detecting is used for this purpose. Detected signs are normalized in size in order to be classified in the second step, where a linear classifier is used to determine the type of the detected sign in combination with Kalman filtering which provide the prediction of the possible position of the road sign in the captured video frames. This processing improves the classification performance because it enables the classifier to determine the type of the sign from each captured frame separately. This procedure enables the proposed algorithm to combine the classification results obtained from each frame in order to make the final decision.

Type

D - Article in proceedings

CEP classification

JA - Electronics and optoelectronics

OECD FORD branch

—

Project

<a href="/en/project/2B06111" target="_blank" >2B06111: New Diagnostic Methods of Circulatory System Parameters Recognition Based on Infra-Red Scanning of Blood-Vessels Image.</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2009

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

32nd International Conference Proceeding on Telecommunications and Signal Processing - TSP' 2009

ISBN

978-963-06-7716-5

ISSN

—

e-ISSN

—

Number of pages

5

Pages from-to

—

Publisher name

Asszisztencia Szervezo Kft.

Place of publication

Budapest, Hungary

Event location

Dunakiliti

Event date

Aug 26, 2009

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—