Traffic and Road Sign Recognition

This thesis presents a system to recognise and classify road and traffic signs for the purpose of developing an inventory of them which could assist the highway engineers’ tasks of updating and maintaining them. It uses images taken by a camera from a moving vehicle. The system is based on three major stages: colour segmentation, recognition, and classification. Four colour segmentation algorithms are developed and tested. They are a shadow and highlight invariant, a dynamic threshold, a modification of de la Escalera’s algorithm and a Fuzzy colour segmentation algorithm. All algorithms are tested using hundreds of images and the shadow-highlight invariant algorithm is eventually chosen as the best performer. This is because it is immune to shadows and highlights. It is also robust as it was tested in different lighting conditions, weather conditions, and times of the day. Approximately 97% successful segmentation rate was achieved using this algorithm.Recognition of traffic signs is carried out using a fuzzy shape recogniser. Based on four shape measures - the rectangularity, triangularity, ellipticity, and octagonality, fuzzy rules were developed to determine the shape of the sign. Among these shape measures octangonality has been introduced in this research. The final decision of the recogniser is based on the combination of both the colour and shape of the sign. The recogniser was tested in a variety of testing conditions giving an overall performance of approximately 88%.Classification was undertaken using a Support Vector Machine (SVM) classifier. The classification is carried out in two stages: rim’s shape classification followed by the classification of interior of the sign. The classifier was trained and tested using binary images in addition to five different types of moments which are Geometric moments, Zernike moments, Legendre moments, Orthogonal Fourier-Mellin Moments, and Binary Haar features. The performance of the SVM was tested using different features, kernels, SVM types, SVM parameters, and moment’s orders. The average classification rate achieved is about 97%. Binary images show the best testing results followed by Legendre moments. Linear kernel gives the best testing results followed by RBF. C-SVM shows very good performance, but ?-SVM gives better results in some case.

Color detection and segmentation for road and traffic signs

This paper aims to present three new methods for color detection and segmentation of road signs. The images are taken by a digital camera mounted in a car. The RGB images are converted into IHLS color space, and new methods are applied to extract the colors of the road signs under consideration. The methods are tested on hundreds of outdoor images in different light conditions, and they show high robustness. This project is part of the research taking place in Dalarna University / Sweden in the field of the ITS.

The Old Road

The plot consists of the progression which the characters undergo. For the old man, the plot is his movement away from the earthly existence of the farm and into the physical process of the seasons. For the older grandson, it is the movement away from the past, symbolized by the farm, and into the present symbolized by his marriage and coupling with society. For the younger grandson, the movement is from childhood to the maturity which being alone demands in order for him to survive.

The Road from Marja: Wounded in Afghanistan, Capt. Erik Quist '99, USMC, sees another side of combat

Marine Corps Capt. Erik Quist ’99 had fought in two wars. Now he fights again as he recovers from severe wounds suffered in Afghanistan.

"Se meu jipe falasse" : a experiência de consumo dos usuários de veículos off road

Este estudo adota a perspectiva experiencial, trazendo a noção de consumo hedônico e de experiência de consumo para o âmbito do marketing e do comportamento do consumidor. Partese do pressuposto de que entender o consumo exige ir além do processo de decisão de compra e admitir que aquilo que os consumidores fazem e a forma como utilizam os bens adquiridos também influencia seus comportamentos. Mas, acima de tudo, exige a visão do consumidor como um indivíduo emocionalmente envolvido com o consumo, processo pelo qual estímulos sensoriais, a imaginação e aspectos emotivos são procurados e apreciados. A investigação teve por objetivo compreender a experiência dos consumidores em situações de uso e consumo dos produtos através da análise dos elementos que a compõem: o contexto, os estímulos sensoriais, os processos cognitivos, as respostas afetivas, as atividades e o processo de avaliação do produto e da experiência em si. A categoria de produtos escolhida foi a de veículos fora-de-estrada, em função do potencial multiuso e da possibilidade de proporcionar desde simples viagens a grandes aventuras. Para atingir os objetivos propostos foi utilizada a Técnica de Elicitação Fotográfica (PET), que permitiu à pesquisadora se aproximar da experiência real vivenciada pelos consumidores através das imagens visuais que os mesmos foram solicitados a trazer para as entrevistas. Os resultados encontrados apontam não apenas para a riqueza e o profundo entendimento a respeito dos consumidores possibilitado pela análise de suas experiências, mas também o quanto a estimulação visual pode ser uma grande aliada dos pesquisadores quando o objetivo da investigação é entender comportamentos de consumo, a relação das pessoas com seus objetos de desejo, as relações sociais que são possibilitadas através das posses e como as experiências em si (e não apenas as características funcionais dos produto) contribuem para a expressão da identidade, auto-conceito e estilo de vida dos consumidores.

Impact of Road Clearings on the Movements of Three Understory Insectivorous Bird Species in the Brazilian Atlantic Forest

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Object-Space Road Extraction in Rural Areas Using Stereoscopic Aerial Images

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Three-Dimensional Semiautomatic Road Extraction From a High-Resolution Aerial Image by Dynamic-Programming Optimization in the Object Space

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Road-killed wild animals: a preservation problem useful for eco-epidemiological studies of pathogens

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Molecular detection of Paracoccidioides brasiliensis in road-killed wild animals

Paracoccidioides brasiliensis infections have been little studied in wild and/or domestic animals, which may represent an important indicator of the presence of the pathogen in nature. Road-killed wild animals have been used for surveillance of vectors of zoonotic pathogens and may offer new opportunities for eco-epidemiological studies of paracoccidiodomycosis (PCM). The presence of P. brasiliensis infection was evaluated by Nested-PCR in tissue samples collected from 19 road-killed animals; 3 Cavia aperea (guinea pig), 5 Cerdocyon thous (crab-eating-fox), 1 Dasypus novemcinctus (nine-banded armadillo), 1 Dasypus septemcinctus (seven-banded armadillo), 2 Didelphis albiventris (white-eared opossum), 1 Eira barbara (tayra), 2 Gallictis vittata (grison), 2 Procyon cancrivorus (raccoon) and 2 Sphiggurus spinosus (porcupine). Specific P. brasiliensis amplicons were detected in (a) several organs of the two armadillos and one guinea pig, (b) the lung and liver of the porcupine, and (c) the lungs of raccoons and grisons. P. brasiliensis infection in wild animals from endemic areas might be more common than initially postulated. Molecular techniques can be used for detecting new hosts and mapping 'hot spot' areas of PCM.

De Sitter Relativity: a New Road to Quantum Gravity?

The Poincar, group generalizes the Galilei group for high-velocity kinematics. The de Sitter group is assumed to go one step further, generalizing Poincar, as the group governing high-energy kinematics. In other words, ordinary special relativity is here replaced by de Sitter relativity. In this theory, the cosmological constant I > is no longer a free parameter, and can be determined in terms of other quantities. When applied to the whole universe, it is able to predict the value of I > and to explain the cosmic coincidence. When applied to the propagation of ultra-high energy photons, it gives a good estimate of the time delay observed in extragalactic gamma-ray flares. It can, for this reason, be considered a new paradigm to approach the quantum gravity problem.

Atmospheric particulate polycyclic aromatic hydrocarbons from road transport in southeast Brazil

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Visual timing and adaptive behavior in a road-crossing simulation study

In this road-crossing simulation study, we assessed both participant's ability to visually judge whether or not they could cross a road, and their adaptive walking behavior. To this end, participants were presented with a road inside the laboratory on which a bike approached with different velocities from different distances. Eight children aged 5-7, ten children aged 10-12, and ten adults were asked both to verbally judge whether they could cross the road, and to actually walk across the road if possible. The results indicated that the verbal judgments were not similar to judgments to actually cross the road. With respect to safety and accuracy of judgments, groups did not differ from each other, although the youngest group tended to be more cautious. All groups appeared to use a strategy to cross the road based both on the distance and the velocity of the approaching bike. Young children waited longer on the curb before crossing the road than older children and adults. All groups adjusted their crossing time to the time-to-arrival of the bike. These findings are discussed in relation to the ecological psychological approach and the putative dissociation between vision for perception (i.e. verbal judgment) and vision for action (i.e. actual crossing). (c) 2004 Elsevier Ltd. All rights reserved.