There are many types of road signs, each of which carries a different meaning and function: some signs regulate traffic, others indicate the state of the road or guide and warn drivers and pedestrians. Existent image-based road sign recognition systems work well under ideal conditions, but experience problems when the lighting conditions are poor or the signs are partially occluded. The aim of this research is to propose techniques to recognize road signs in a real outdoor environment, especially to deal with poor lighting and partially occluded road signs. To achieve this, hybrid segmentation and classification algorithms are proposed. In the first part of the thesis, we propose a hybrid dynamic threshold colour segmentation algorithm based on histogram analysis. A dynamic threshold is very important in road sign segmentation, since road sign colours may change throughout the day due to environmental conditions. In the second part, we propose a geometrical shape symmetry detection and reconstruction algorithm to detect and reconstruct the shape of the sign when it is partially occluded. This algorithm is robust to scale changes and rotations. The last part of this thesis deals with feature extraction and classification. We propose a hybrid feature vector based on histograms of oriented gradients, local binary patterns, and the scale-invariant feature transform. This vector is fed into a classifier that combines a Support Vector Machine (SVM) using a Random Forest and a hybrid SVM k-Nearest Neighbours (kNN) classifier. The overall method proposed in this thesis shows a high accuracy rate of 99.4% in ideal conditions, 98.6% in noisy and fading conditions, 98.4% in poor lighting conditions, and 92.5% for partially occluded road signs on the GRAMUAH traffic signs dataset.

Intelligent Transportation System (ITS) is a system that builds a safe, effective and integrated transportation environment based on advanced technologies. Road signs detection and recognition is an important part of ITS, which offer ways to collect the real time traffic data for processing at a central facility.This project is to implement a road sign recognition model based on AI and image analysis technologies, which applies a machine learning method, Support Vector Machines, to recognize road signs. We focus on recognizing seven categories of road sign shapes and five categories of speed limit signs. Two kinds of features, binary image and Zernike moments, are used for representing the data to the SVM for training and test. We compared and analyzed the performances of SVM recognition model using different features and different kernels. Moreover, the performances using different recognition models, SVM and Fuzzy ARTMAP, are observed.

In this thesis, video frames acquired by a camera in a moving car are processed for detection of candidates of triangular, rectangular and circular traffic/road signs based on mainly shape information by performing contour analysis. Color information is utilized as an auxiliary method to improve detection. Then recognition based on template matching is realized on detected traffic/road sign candidates. Detection and recognition results of traffic/road signs in video frames taken in different time intervals of day for these methods are compared. After implementation, results show that the video scene taken in a sunny day in the afternoon gives better results than others. Binary threshold plays a great role in detection with respect to Canny edge detector especially for triangular and rectangular traffic signs. Higher number of binary threshold levels improves detection in general. In addition, the recognition rate for triangular and rectangular traffic/road signs is higher than that of circular sings in general by the methods used in this study.

This thesis is focused on developing a robust algorithm for recognition of road signs including all stages of a machine vision system i.e. image acquisition, pre-processing, colour segmentation, labelling and classifi-cation. Images are acquired by two different imaging systems and noise removal is done by applying Mean filter. Furthermore, different colour segmentation methods are investigated to find out the most high-performance approach and after applying dynamic segmentation based on blue channel in YCbCr colour space, the obtained binary image is transferred to a personal computer through the developed PC software using standard serial port and further processing and classification is run on the PC. Histogram of Oriented Gradients (HOG) is used as the main feature for recognition of road signs and finally the classification task is fulfilled by employing hardware efficient Minimum Distance Classifier (MDC).

No description available.

This doctoral thesis deals primarily with condition assessment of road equipment. The road equipment concept is defined by five main groups, road lighting, fences and barriers, vertical signs, horizontal signs and traffic signals, respectively. Of these groups, road markings, street lighting and barriers of three-lane roads have been studied more in detail. A state-of-the-art, comprising information obtained by comprehensive literature studies on condition assessment of road equipment is presented. Comparably few fundamental studies were found, which, to some degree, can be explained by the lack of suitable physical measurement methods. However, in the case of road marking retroreflectivity, mobile instruments have been developed, and research published in this area is relatively comprehensive. Furthermore, although not based on mobile measurements, several studies on assessments on performance of road sign sheeting have been published. The experimental part of the thesis is divided into four studies, of which two are dealing with mobile measurement of wet road markings and street lighting, respectively. One of the studies concerns condition assessment of road marking performance accomplished in the Nordic countries. Finally, one study comprises risk analysis related to crashes into the barriers on three-lane roads. At road equipment condition assessment, mobile measurement methods are preferable compared to stationary methods. However, many relevant parameters are tricky to measure at speed. One example in this connection is characterization of performance of wet road markings, which has to be based on one or more parameters obtained by measurements on dry surfaces. Results presented in this thesis indicate that retroreflectivity and skid resistance of wet road markings can be predicted based on retroreflectivity and macro-texture of dry road marking. For traffic safety, street lighting is important. The performance of this type of road equipment is in most cases described in terms of luminance of the illuminated road surface. However, luminance measurements are tricky and time-consuming and not useful for condition assessment. On the contrary, measurement of illuminance is easy to carry out and can be performed at speed. One part of the thesis describes how road surface luminance in street lighting can be estimated based on illuminance and reflection properties of the road surface. With the purpose of comparing road marking performance in the Nordic countries, condition assessment using mobile measurement equipment was accomplished in 2002 and 2003. In each of the five Nordic countries, a number of roads were chosen for measuring retroreflectivity. The study showed that the retroreflectivity of edge, centre and lane lines was poor in some countries, but, at least regarding edge lines, this shortcoming could be compensated by use of wide, continuous lines. In other words, the visibility of longitudinal road markings was approximately equal in the different countries. The purpose of the risk analysis performed on three-lane road barriers was to estimate the influence of the time-period between initial crash and repair on the risk of a secondary accident. The result showed that, especially in winter-time, time-reduction means reduced risk of secondary accidents. / QC 20100824

Verkehrsschilder gelten als das gängigste Mittel zur Regulation des Straßenverkehrs und der Kommunikation zu den Straßennutzer*innen. Die Fähigkeit eines Fahrers bzw. einer Fahrerin, ein Verkehrsschild zu verstehen, ist deshalb essentiell für die Verkehrssicherheit. Zahlreiche Studien zeigen allerdings, dass mit einem durchschnittlichen Verständnis zwischen 50 und 70% der Verkehrsschilder z.T. große Verständnisschwierigkeiten bei den Fahrer*innen vorliegen. Die Verwendung von Piktogrammen stellt eine Möglichkeit dar, um vereinfachte, auf das Wesentliche reduzierte standardisierte Informationen zu übermitteln. In Folge der Zunahme des Verkehrsvolumens über die letzten Dekaden haben viele Länder solche symbolischen Schilder eingeführt, um internationale Reisen dort zu erleichtern, wo Sprachdifferenzen Barrieren darstellen könnten. Die vorliegende Arbeit beschäftigt sich deshalb mit der Verbesserung von Beschilderungen im Straßenverkehr für in- und ausländische Fahrer*innen in Bezug auf Verständlichkeit, Korrektheit von Entscheidungen und Reaktionszeiten. Derzeit gibt es eine Fülle an Forschung zu Symbolen auf Warn- und Gebotsschildern, allerdings nicht auf Wegweisern. Ziel dieser Studie war es, einen Forschungsbeitrag zur Nutzung von Piktogrammen im Straßenverkehr und zur Verkehrssicherheit zu leisten. Dazu wurde in einem Reaktionszeitexperiment zum einen die gerichtete Hypothese untersucht, dass Piktogramme schneller und sicherer erkannt werden als verbale Zielangaben. Diese Hypothese konnte nicht bestätigt werden, stattdessen wurde ein gegenteiliger Effekt gefunden. Zum anderen wurde die gerichtete Hypothese untersucht, dass deutsche Muttersprachler*innen sowohl bei symbolischen als auch bei verbalen Zielangaben insgesamt schnellere Reaktionszeiten und mehr korrekte Antworten zeigen; dies konnte bestätigt werden. Unter Einbezug der Kovariaten Alter, Geschlecht und Fahrerfahrung zeigten sich besonders ein signifikanter Effekt des Alters und des Schildes, das die Versuchspersonen präsentiert bekamen; der zuvor noch gefundene Haupteffekt der Art der Zielangabe (symbolisch/ verbal) war dann nicht mehr signifikant. Mögliche Gründe werden abschließend diskutiert. / Road signs can be regarded as the most common means of traffic regulation and communication to road users. The driver’s ability to understand a road sign therefore is essential for traffic safety. However, a large body of research shows that – with a mean comprehension value that varies between 50 and 70% - drivers have difficulties in understanding the meaning of traffic signs. The use of pictorials represents one way of conveying simplified, standardized pieces of information. With the increase in traffic volumes over the last decades, a lot of countries have introduced such symbolic signs to facilitate international travelling where language differences constitute linguistic barriers. Currently, a variety of studies on symbolic warning and mandatory signs, but not on directory signs exists. The present study subsequently deals with the improvement of directory signs in road traffic for national and international drivers regarding comprehensibility, correctness of decisions and reaction times. The aim of this study is to contribute to existing research on the topic of use of pictorials in road traffic and on traffic safety. A reaction time experiment was developed and carried out with 101 participants aged 18 to 87. 63 of the test persons had acquired German as mother language; for 38 of the participants, German was not the native tongue. Each participant was presented with 32 German directory signs that had specially been developed for the experiment. Participants had to indicate the direction they would use to reach a certain predetermined target location that could either be represented verbally or as a symbol. Two hypotheses were tested: the first hypothesis stated that pictorials should be detected faster and more accurately than verbal targets. This could not be confirmed; instead, we found the opposite pattern. The second hypothesis assumed that German native speakers would show faster reaction times and a greater number of correct answers for symbolic as well as for verbal targets compared to non-native German speakers; this hypothesis could be confirmed. Including the covariates age, sex and driving experience, a very significant effect of age as well as of the specific sign that the subjects were presented with could be shown; the previously found main effect of target type (verbal/pictorial) was not significant, anymore. Finally, the present study discusses possible reasons and influencing factors for the observed effects like arrangement and number of targets on a sign as well as the word length of the used targets.

Verkehrsschilder gelten als das gängigste Mittel zur Regulation des Straßenverkehrs und der Kommunikation zu den Straßennutzer*innen. Die Fähigkeit eines Fahrers bzw. einer Fahrerin, ein Verkehrsschild zu verstehen, ist deshalb essentiell für die Verkehrssicherheit. Zahlreiche Studien zeigen allerdings, dass mit einem durchschnittlichen Verständnis zwischen 50 und 70% der Verkehrsschilder z.T. große Verständnisschwierigkeiten bei den Fahrer*innen vorliegen. Die Verwendung von Piktogrammen stellt eine Möglichkeit dar, um vereinfachte, auf das Wesentliche reduzierte standardisierte Informationen zu übermitteln. In Folge der Zunahme des Verkehrsvolumens über die letzten Dekaden haben viele Länder solche symbolischen Schilder eingeführt, um internationale Reisen dort zu erleichtern, wo Sprachdifferenzen Barrieren darstellen könnten. Die vorliegende Arbeit beschäftigt sich deshalb mit der Verbesserung von Beschilderungen im Straßenverkehr für in- und ausländische Fahrer*innen in Bezug auf Verständlichkeit, Korrektheit von Entscheidungen und Reaktionszeiten. Derzeit gibt es eine Fülle an Forschung zu Symbolen auf Warn- und Gebotsschildern, allerdings nicht auf Wegweisern. Ziel dieser Studie war es, einen Forschungsbeitrag zur Nutzung von Piktogrammen im Straßenverkehr und zur Verkehrssicherheit zu leisten. Dazu wurde in einem Reaktionszeitexperiment zum einen die gerichtete Hypothese untersucht, dass Piktogramme schneller und sicherer erkannt werden als verbale Zielangaben. Diese Hypothese konnte nicht bestätigt werden, stattdessen wurde ein gegenteiliger Effekt gefunden. Zum anderen wurde die gerichtete Hypothese untersucht, dass deutsche Muttersprachler*innen sowohl bei symbolischen als auch bei verbalen Zielangaben insgesamt schnellere Reaktionszeiten und mehr korrekte Antworten zeigen; dies konnte bestätigt werden. Unter Einbezug der Kovariaten Alter, Geschlecht und Fahrerfahrung zeigten sich besonders ein signifikanter Effekt des Alters und des Schildes, das die Versuchspersonen präsentiert bekamen; der zuvor noch gefundene Haupteffekt der Art der Zielangabe (symbolisch/ verbal) war dann nicht mehr signifikant. Mögliche Gründe werden abschließend diskutiert.:Danksagung Zusammenfassung 1. Hinführung und Ziele 2. Theorie 2.1 Überblick über bisherige Literatur 2.2 Überlegungen zum Studiendesign 3. Hypothesen 3.1 Reaktionszeitunterschiede zwischen symbolischen und verbalen Zielangaben 3.2 Reaktionszeitunterschiede zwischen deutschen Muttersprachler*innen und Nicht-Muttersprachler*innen 4. Methoden 4.1 Stichprobe 4.2 Ablauf und Materialien 4.3 Design 4.4 Statistische Analyse 5. Ergebnisse 5.1 Deskriptive Analyse der abhängigen Variablen 5.2 Überprüfung auf Normalverteilung 5.3 Deskriptive Analyse der Daten der Nachbefragung 5.4 Überprüfung der Hypothesen 6. Diskussion 6.1 Vergleich verbaler und symbolisches Zielangaben 6.2 Vergleich deutscher und nicht-deutscher Muttersprachler*innen 6.3 Weitere Ergebnisse und Überlegungen 7. Literaturverzeichnis Anhang Abbildungsverzeichnis Tabellenverzeichnis / Road signs can be regarded as the most common means of traffic regulation and communication to road users. The driver’s ability to understand a road sign therefore is essential for traffic safety. However, a large body of research shows that – with a mean comprehension value that varies between 50 and 70% - drivers have difficulties in understanding the meaning of traffic signs. The use of pictorials represents one way of conveying simplified, standardized pieces of information. With the increase in traffic volumes over the last decades, a lot of countries have introduced such symbolic signs to facilitate international travelling where language differences constitute linguistic barriers. Currently, a variety of studies on symbolic warning and mandatory signs, but not on directory signs exists. The present study subsequently deals with the improvement of directory signs in road traffic for national and international drivers regarding comprehensibility, correctness of decisions and reaction times. The aim of this study is to contribute to existing research on the topic of use of pictorials in road traffic and on traffic safety. A reaction time experiment was developed and carried out with 101 participants aged 18 to 87. 63 of the test persons had acquired German as mother language; for 38 of the participants, German was not the native tongue. Each participant was presented with 32 German directory signs that had specially been developed for the experiment. Participants had to indicate the direction they would use to reach a certain predetermined target location that could either be represented verbally or as a symbol. Two hypotheses were tested: the first hypothesis stated that pictorials should be detected faster and more accurately than verbal targets. This could not be confirmed; instead, we found the opposite pattern. The second hypothesis assumed that German native speakers would show faster reaction times and a greater number of correct answers for symbolic as well as for verbal targets compared to non-native German speakers; this hypothesis could be confirmed. Including the covariates age, sex and driving experience, a very significant effect of age as well as of the specific sign that the subjects were presented with could be shown; the previously found main effect of target type (verbal/pictorial) was not significant, anymore. Finally, the present study discusses possible reasons and influencing factors for the observed effects like arrangement and number of targets on a sign as well as the word length of the used targets.:Danksagung Zusammenfassung 1. Hinführung und Ziele 2. Theorie 2.1 Überblick über bisherige Literatur 2.2 Überlegungen zum Studiendesign 3. Hypothesen 3.1 Reaktionszeitunterschiede zwischen symbolischen und verbalen Zielangaben 3.2 Reaktionszeitunterschiede zwischen deutschen Muttersprachler*innen und Nicht-Muttersprachler*innen 4. Methoden 4.1 Stichprobe 4.2 Ablauf und Materialien 4.3 Design 4.4 Statistische Analyse 5. Ergebnisse 5.1 Deskriptive Analyse der abhängigen Variablen 5.2 Überprüfung auf Normalverteilung 5.3 Deskriptive Analyse der Daten der Nachbefragung 5.4 Überprüfung der Hypothesen 6. Diskussion 6.1 Vergleich verbaler und symbolisches Zielangaben 6.2 Vergleich deutscher und nicht-deutscher Muttersprachler*innen 6.3 Weitere Ergebnisse und Überlegungen 7. Literaturverzeichnis Anhang Abbildungsverzeichnis Tabellenverzeichnis

In my master thesis I deal with a design reconstruction of the current public transport terminus of Nemocnice - Bohunice. Terminus layout includes transfering the tramway line from Osová stop to the hub, the new tramway stop is a setting-back track. There is preserved the utilization of hub by existing city and regional lines of buses and troley buses and newly established regional bus lines (401,402,403,404) and also the entrance to the Bohunice hospital parking in the design. This design provides a safe flow of passengers and pedestrians and their safe road crossing.