Orientador: Regina Coeli Ruschel / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Civil / Made available in DSpace on 2018-08-03T15:07:52Z (GMT). No. of bitstreams: 1 Pozzetti_PauloHenrique_M.pdf: 12770381 bytes, checksum: d6fce90f00c39040e03c0b8a9aa801ed (MD5) Previous issue date: 2002 / Resumo: Da concorrência entre os elementos participantes do sistema de circulação surgem os conflitos, que em seus maiores graus de severidade se transformam em acidentes de trânsito. Estes acidentes devem ser analisados sobre diversos pontos de vista para que sua compreensão possa ajudar em medidas corretivas. Este trabalho visa identificar a influência de painéis dinâmicos de propaganda no tempo de percepção e reação do motorista, na visualização do conjunto semafórico, em cruzamentos com altos Índices de acidentes na cidade de São Paulo, através de simulação animada em 2D em ambiente computacional. Através dos dados sobre acidentes, foi selecionado na cidade de São Paulo, o cruzamento da Av. Rebouças com a Av. Brigadeiro Faria Lima para a simulação, definindo um modelo genérico envolvendo: distância de frenagem e distância percorrida durante os tempos de percepção. Para o teste de hipóteses variadas analisou-se a interferência dos parâmetros velocidade, tempo de percepção e campo de visão do grupo focal. O modelo foi elaborado através dos registros fotográficos do local, sendo gerados 36 filmes. Cada filme representava uma combinação diferente das variáveis. Os filmes foram apresentados para grupos de usuários para a identificação da cor do semáforo: o primeiro na Faculdade de Engenharia Civil da UNICAMP e o segundo na CET - Companhia de Engenharia de Tráfego - SP, totalizando 180 participantes. identificação da cor do semáforo: o primeiro na Faculdade de Engenharia Civil da UNICAMP e o segundo na CET - Companhia de Engenharia de Tráfego - SP, totalizando 180 participantes. Ao se analisar os dados obtidos nota-se que as variáveis com maior significância estatística, na visualização do grupo focal, para o modelo desenvolvido, foram as variáveis velocidade, tempo de percepção e a presença do painel. Surpreendentemente a presença do painel atrás do grupo focal contribui para uma correta identificação do semáforo. Observou-se que para velocidades maiores o nível de indefinição na identificação do semáforo é maior. A adoção de tempos de percepção e reação maiores que dois segundos são recomendáveis. Para o modelo desenvolvido não foram relevantes a familiaridade com o local e o ambiente em que os testes foram aplicados. Percebe-se que uma simulação animada em 2D montada em programa para ambientes de navegação para WWW pode incrementar a análise de segurança viária / Abstract: Conflicts emerge from the competition between elements participating in the circulation system, when these achieve severe degree traffic accidents occur. These accidents should be analyzed trom various points view so that its comprehension may indicate corrective measures. This work aims to identify the influence of dynamic publicity panels in the perception-reaction time of drivers in the visualization of light signals of intersections with high accidents rates in the city of São Paulo using an animated 2D simulation in a computer environment. The intersection of Rebouças Avenue and Brigadeiro Faria Lima Avenue was selected as the study site in the simulation. A generic model was defined using the breaking and traversed distance during perception time. The interference of the variables speed, perception time and environment behind the light signal was analyzed in the model. The animation was developed using photographs of the site generating 36 different films. Each film represented a different combination of variables. The films were presented to groups of users for their identification of the color of the light signal: the first group at the Faculdade de Engenharia Civil at UNICAMP and the second group at the Compania de Engenharia de Tráfego (CET) at SP, summing up to 180 participants. Data analyses pointed out that the variables with greatest statistical significance in the focal group for the developed model were speed, perception time and presence of the panel. Surprising1y, the presence of the panel behind the focal group contributes for the correct perception of the light signal. It was also observed that in higher velocities the indefinition in identification of the light signal is greater. There for, it is recommended the use of perception-reaction time higher then 2 seconds. In the developed model the variables familiarity with the site and group of users were not relevant. It can be conc1uded that the 2D animated simulation in computer environment increments the ana1ysis of traffic safety / Mestrado / Transportes / Mestre em Engenharia Civil

This paper presents results from a workshop focusing on human demands of mobility that was conducted during the MFTS conference 2022. It shows, how the international participants, most of them male researchers with a background in engineering, dealt with concepts and findings from mobility research conducted by scholars of social sciences, humanities and cultural studies that focus on human mobility demands including gender and diversity aspects.

Introduction: With the beginning of the COVID-19 outbreak and the restrictions put in place to prevent an uncontrolled spread of the virus, the circumstances for daily activities changed. A remarkable shift in the modal split distribution was observed [Ank21]. Moreover, the changes in mobility during the COVID-19 pandemic had multiple impacts on road traffic [Yas21]. By now, several researchers have looked at the impact of COVID-19 as a disruptive event on mobility behaviour. This workshop within the 4th Symposium on Management of Future Motorway and Urban Traffic Systems aimed to discuss insights from these research projects and how they enable experts to transfer this newfound knowledge to future disruptive events such as climate change, rising energy costs and events related to a possible energy transition. Thus, the research question this workshop investigated reads as follows: What can we learn from the pandemic to be able to predict how different future disruptive events can shape the mobility of tomorrow?

This thesis aims at proposing vehicle license plate detection and recognition algorithms, suitable for vehicle re-identification. Simple urban traffic analysis system is also proposed. Multiple stages of this system was developed and tested. Specifically - vehicle detection, license plate detection and recognition. Vehicle detection is based on background substraction method, which results in an average hit rate of ~92%. License plate detection is done by cascade classifiers and achieves an average hit rate of 81.92% and precision rate of 94.42%. License plate recognition based on Template matching results in an average precission rate of 60.55%. Therefore the new license plate recognition method based on license plate scanning using the sliding window principle and neural network recognition was introduced. Neural network achieves a precision rate of 64.47% for five input features. Low precision rate of neural network is caused by small amount of training sample for some specific license plate characters.

A Região Metropolitana de São Paulo (RMSP) sofre de sérios problemas de congestionamento, assim como muitas outras cidades de grande porte. Uma possível solução, proposta por pesquisadores de transportes, economia e ciências ambientais, é a implantação de um sistema de congestion charging, chamada no Brasil de pedágio urbano. Um dos objetivos do presente trabalho foi estabelecer os conceitos relacionados a este assunto e ilustrar as principais questões relacionadas à sua implantação. Espera-se que este trabalho possa auxiliar o desenvolvimento de estudos de avaliação da viabilidade e de impactos de sistemas propostos de congestion charging. Para atingir este objetivo, toca-se em diversos assuntos, como a definição de congestionamento e as formas de medi-lo, a base conceitual e teórica dos sistemas de congestion charging e seus diversos esquemas de diferenciação. São expostas também as medidas de mitigação de congestionamento que já foram implantadas na RMSP, quais foram os estudos já desenvolvidos considerando este tipo de política para a RMSP, e casos em que sistemas de congestion charging já foi implantado. Neste trabalho, desenvolveu-se também um modelo de escolha discreta a partir dos dados da Pesquisa Origem e Destino 2007 do METRÔ, onde pessoas deveriam escolher entre \"Transporte Coletivo\" e \"Transporte Público\". Este modelo foi utilizado para avaliar o potencial de impacto na divisão modal e de arrecadação de um congestion charge aplicado ao centro expandido de São Paulo. Adverte-se, porém, que os resultados obtidos são meramente ilustrativos. Mostra-se, também, que é possível avaliar a capacidade ociosa do sistema de transporte coletivo a partir dos dados disponíveis de bilhetagem e de GPS dos ônibus. Este processo é exemplificado através do cálculo de capacidade de uma única viagem de um único ônibus, dada a dificuldade de automatização deste processo para abranger toda a frota. / The São Paulo Metropolitan Region (SPMR) suffers from severe traffic congestion, as do many other large-scale urban areas around the world. A possible solution to this issue, which has been suggested by transportation, economics and environmental researchers, is the implementation of a congestion charging system. One of the objectives of this project is to establish clear concepts and shed light on the main issues regarding these systems by means of a comprehensive literary review. It is expected that this project may help the development of in-depth studies carried in order to evaluate the viability and impacts of congestion charging proposals. In order to achieve this goal, many subjects are addressed, such as the definition of congestion, how its measured, the theoretical backgrounds that support congestion charging schemes, their different degrees of differentiation, which policies were enacted in order to reduce traffic congestion in São Paulo, what considerations and studies have already been developed for Brazil and São Paulo regarding these systems and where have these systems been successfully installed. Later chapters deal with another goal of this project: estimating how a congestion charging system would affect SPMR. This was achieved through a multinomial logit model, where decision-makers choose between \"Public Transportation\" and \"Private Automobile\". The results presented at this phase are merely indicative of certain tendencies and should not be considered final. This project also attempts to show that given the available Automated Fare Collection (AFC) data and Automated Vehicle Location (AVL) data, it is possible to estimate the current public transportation system\'s unused capacity. The author shows this by calculating the capacity of one bus trip using these data, but also explains the difficulties of expanding this analysis to the whole of SPMR\'s public transportation system.

Depuis les années 2000, un progrès significatif est enregistré dans les travaux de recherche qui proposent l’apprentissage de détecteurs d’objets sur des grandes bases de données étiquetées manuellement et disponibles publiquement. Cependant, lorsqu’un détecteur générique d’objets est appliqué sur des images issues d’une scène spécifique les performances de détection diminuent considérablement. Cette diminution peut être expliquée par les différences entre les échantillons de test et ceux d’apprentissage au niveau des points de vues prises par la(les) caméra(s), de la résolution, de l’éclairage et du fond des images. De plus, l’évolution de la capacité de stockage des systèmes informatiques, la démocratisation de la "vidéo-surveillance" et le développement d’outils d’analyse automatique des données vidéos encouragent la recherche dans le domaine du trafic routier. Les buts ultimes sont l’évaluation des demandes de gestion du trafic actuelles et futures, le développement des infrastructures routières en se basant sur les besoins réels, l’intervention pour une maintenance à temps et la surveillance des routes en continu. Par ailleurs, l’analyse de trafic est une problématique dans laquelle plusieurs verrous scientifiques restent à lever. Ces derniers sont dus à une grande variété dans la fluidité de trafic, aux différents types d’usagers, ainsi qu’aux multiples conditions météorologiques et lumineuses. Ainsi le développement d’outils automatiques et temps réel pour l’analyse vidéo de trafic routier est devenu indispensable. Ces outils doivent permettre la récupération d’informations riches sur le trafic à partir de la séquence vidéo et doivent être précis et faciles à utiliser. C’est dans ce contexte que s’insèrent nos travaux de thèse qui proposent d’utiliser les connaissances antérieurement acquises et de les combiner avec des informations provenant de la nouvelle scène pour spécialiser un détecteur d’objet aux nouvelles situations de la scène cible. Dans cette thèse, nous proposons de spécialiser automatiquement un classifieur/détecteur générique d’objets à une scène de trafic routier surveillée par une caméra fixe. Nous présentons principalement deux contributions. La première est une formalisation originale de transfert d’apprentissage transductif à base d’un filtre séquentiel de type Monte Carlo pour la spécialisation automatique d’un classifieur. Cette formalisation approxime itérativement la distribution cible inconnue au départ, comme étant un ensemble d’échantillons de la base spécialisée à la scène cible. Les échantillons de cette dernière sont sélectionnés à la fois à partir de la base source et de la scène cible moyennant une pondération qui utilise certaines informations a priori sur la scène. La base spécialisée obtenue permet d’entraîner un classifieur spécialisé à la scène cible sans intervention humaine. La deuxième contribution consiste à proposer deux stratégies d’observation pour l’étape mise à jour du filtre SMC. Ces stratégies sont à la base d’un ensemble d’indices spatio-temporels spécifiques à la scène de vidéo-surveillance. Elles sont utilisées pour la pondération des échantillons cibles. Les différentes expérimentations réalisées ont montré que l’approche de spécialisation proposée est performante et générique. Nous avons pu y intégrer de multiples stratégies d’observation. Elle peut être aussi appliquée à tout type de classifieur. De plus, nous avons implémenté dans le logiciel OD SOFT de Logiroad les possibilités de chargement et d’utilisation d’un détecteur fourni par notre approche. Nous avons montré également les avantages des détecteurs spécialisés en comparant leurs résultats avec celui de la méthode Vu-mètre de Logiroad. / Since 2000, a significant progress has been recorded in research work which has proposed to learn object detectors using large manually labeled and publicly available databases. However, when a generic object detector is applied on images of a specific scene, the detection performances will decrease considerably. This decrease may be explained by the differences between the test samples and the learning ones at viewpoints taken by camera(s), resolution, illumination and background images. In addition, the storage capacity evolution of computer systems, the "video surveillance" democratization and the development of automatic video-data analysis tools have encouraged research into the road-traffic domain. The ultimate aims are the management evaluation of current and future trafic requests, the road infrastructures development based on real necessities, the intervention of maintenance task in time and the continuous road surveillance. Moreover, traffic analysis is a problematicness where several scientific locks should be lifted. These latter are due to a great variety of traffic fluidity, various types of users, as well multiple weather and lighting conditions. Thus, developing automatic and real-time tools to analyse road-traffic videos has become an indispensable task. These tools should allow retrieving rich data concerning the traffic from the video sequence and they must be precise and easy to use. This is the context of our thesis work which proposes to use previous knowledges and to combine it with information extracted from the new scene to specialize an object detector to the new situations of the target scene. In this thesis, we propose to automatically specialize a generic object classifier/detector to a road traffic scene surveilled by a fixed camera. We mainly present two contributions. The first one is an original formalization of Transductive Transfer Learning based on a sequential Monte Carlo filter for automatic classifier specialization. This formalization approximates iteratively the previously unknown target distribution as a set of samples composing the specialized dataset of the target scene. The samples of this dataset are selected from both source dataset and target scene further to a weighting step using some prior information on the scene. The obtained specialized dataset allows training a specialized classifier to the target scene without human intervention. The second contribution consists in proposing two observation strategies to be used in the SMC filter’s update step. These strategies are based on a set of specific spatio-temporal cues of the video surveillance scene. They are used to weight the target samples. The different experiments carried out have shown that the proposed specialization approach is efficient and generic. We have been able to integrate multiple observation strategies. It can also be applied to any classifier / detector. In addition, we have implemented into the Logiroad OD SOFT software the loading and utilizing possibilities of a detector provided by our approach. We have also shown the advantages of the specialized detectors by comparing their results to the result of Logiroad’s Vu-meter method.

A Região Metropolitana de São Paulo (RMSP) sofre de sérios problemas de congestionamento, assim como muitas outras cidades de grande porte. Uma possível solução, proposta por pesquisadores de transportes, economia e ciências ambientais, é a implantação de um sistema de congestion charging, chamada no Brasil de pedágio urbano. Um dos objetivos do presente trabalho foi estabelecer os conceitos relacionados a este assunto e ilustrar as principais questões relacionadas à sua implantação. Espera-se que este trabalho possa auxiliar o desenvolvimento de estudos de avaliação da viabilidade e de impactos de sistemas propostos de congestion charging. Para atingir este objetivo, toca-se em diversos assuntos, como a definição de congestionamento e as formas de medi-lo, a base conceitual e teórica dos sistemas de congestion charging e seus diversos esquemas de diferenciação. São expostas também as medidas de mitigação de congestionamento que já foram implantadas na RMSP, quais foram os estudos já desenvolvidos considerando este tipo de política para a RMSP, e casos em que sistemas de congestion charging já foi implantado. Neste trabalho, desenvolveu-se também um modelo de escolha discreta a partir dos dados da Pesquisa Origem e Destino 2007 do METRÔ, onde pessoas deveriam escolher entre \"Transporte Coletivo\" e \"Transporte Público\". Este modelo foi utilizado para avaliar o potencial de impacto na divisão modal e de arrecadação de um congestion charge aplicado ao centro expandido de São Paulo. Adverte-se, porém, que os resultados obtidos são meramente ilustrativos. Mostra-se, também, que é possível avaliar a capacidade ociosa do sistema de transporte coletivo a partir dos dados disponíveis de bilhetagem e de GPS dos ônibus. Este processo é exemplificado através do cálculo de capacidade de uma única viagem de um único ônibus, dada a dificuldade de automatização deste processo para abranger toda a frota. / The São Paulo Metropolitan Region (SPMR) suffers from severe traffic congestion, as do many other large-scale urban areas around the world. A possible solution to this issue, which has been suggested by transportation, economics and environmental researchers, is the implementation of a congestion charging system. One of the objectives of this project is to establish clear concepts and shed light on the main issues regarding these systems by means of a comprehensive literary review. It is expected that this project may help the development of in-depth studies carried in order to evaluate the viability and impacts of congestion charging proposals. In order to achieve this goal, many subjects are addressed, such as the definition of congestion, how its measured, the theoretical backgrounds that support congestion charging schemes, their different degrees of differentiation, which policies were enacted in order to reduce traffic congestion in São Paulo, what considerations and studies have already been developed for Brazil and São Paulo regarding these systems and where have these systems been successfully installed. Later chapters deal with another goal of this project: estimating how a congestion charging system would affect SPMR. This was achieved through a multinomial logit model, where decision-makers choose between \"Public Transportation\" and \"Private Automobile\". The results presented at this phase are merely indicative of certain tendencies and should not be considered final. This project also attempts to show that given the available Automated Fare Collection (AFC) data and Automated Vehicle Location (AVL) data, it is possible to estimate the current public transportation system\'s unused capacity. The author shows this by calculating the capacity of one bus trip using these data, but also explains the difficulties of expanding this analysis to the whole of SPMR\'s public transportation system.

Made available in DSpace on 2016-08-17T14:52:59Z (GMT). No. of bitstreams: 1 Marcos Barros e Silva.pdf: 1611676 bytes, checksum: 2ac174c844a81425dc12f950d38f1b39 (MD5) Previous issue date: 2005-06-28 / This dissertation is part of TMS project whose objective is the development of a Intelligent Traffic Administration System . TMS has three fundamental functions: (1) Manage the necessary resources to the traffic control; (2) aid in the training of traffic employees; and (3) Accompany the changes of the urban traffic for ends of decision. TMS was conceived to assist the cities that doesn't have systems of traffic control and the others witch has the whole mounted structure with interlinked traffic lights. We show the conception of a system that seeks to assist the needs of traffic administration organs and, at the same time, allow its users to aid in the constant evolution of this management. We will specifically treat an architecture based on agents for our system, the technologies which the system uses and interactions among agents of traffic control. The prototype implemented in this work it allows the automation of the mechanisms of Traffic Administration operation - time of green and red of the traffic lights - turning the changes of semaphored plans the more dynamics as possible. / Esta dissertação é parte do Projeto TMS cujo objetivo é o desenvolvimento de um Sistema inteligente de Gerenciamento de Trânsito. O TMS tem três funções fundamentais : (1) Gerenciar os recursos necessários ao controle do tráfego ; (2) Ajudar no treinamento dos funcionários das companhias de trânsito ; e (3) Acompanhar as mudanças do tráfego urbano para fins de tomada de decisão. O TMS foi concebido para atender desde as cidades que não tem sistemas de controle de tráfego até aquelas que tem todo a estrutura montada com semáforos interligados, etc. Apresenta-se aqui a concepção do sistema que visa atender às necessidades dos órgãos de gerenciamento de trânsito e que, ao mesmo tempo, permita que os seus usuários pudessem auxiliar na constante evolução do mesmo. Trataremos especificamente da arquitetura baseada em agentes proposta para o sistema, as tecnologias que o fundamentam e apreendemos as interações entre agentes de controle de trânsito. O protótipo implementado neste trabalho permite a automação dos mecanismos de funcionamento de Gerenciamento de Trânsito tempo de verde e vermelho dos semáforos - tornando as mudanças de planos semafóricos as mais dinâmicas possíveis.

Multimodality is a main requirement for future Urban Traffic Control (UTC). For cities and traffic engineers to implement multimodal UTC, a holistic, multimodal assessment of UTC measures is needed. This paper proposes a Multimodal Performance Index (MPI), which considers the delays and number of stops of different transport modes that are weighted to each other. To determine suitable mode-specific weights, a case study for the German city Ingolstadt is conducted using the microscopic simulation tool SUMO. In the case study, different UTC measures (bus priority, coordination for cyclists, coordination for private vehicle traffic) are implemented to a varying extent and evaluated according to different weight settings. The MPI calculation is done both network-wide and intersection-specific. The results indicate that a weighting according to the occupancy level of modes, as mainly proposed in the literature so far, is not sufficient. This applies particularly to cycling, which should be weighted according to its positive environmental impact instead of its occupancy. Besides, the modespecific weights have to correspond to the traffic-related impact of the mode-specific UTC measures. For Ingolstadt, the results are promising for a weighting according to the current modal split and a weighting with incentives for sustainable modes.

Improving road safety and optimizing the traffic flow – these are major challenges at urban intersections. In particular, strengthening the needs of vulnerable road users (VRUs) such as pedestrians, cyclists and e-scooter drivers is becoming increasingly important, combined with support for automated and connected driving. In the LTSA project, a new system is being developed and implemented exactly for this purpose. The LTSA is an intelligent infrastructure system that records the movements of all road users in the vicinity of an intersection using a combination of several locally installed sensors e.g. video, radar, lidar. AI-based software processes the detected data, interprets the movement patterns of road users and continuously analyzes the current traffic situation (digital twin). Potentially dangerous situations are identified, e.g. right turning vehicles and simultaneously crossing VRUs, and warning messages can be sent to connected road users via vehicle-to-infrastructure communication (V2X). Automated vehicles can thus adapt their driving maneuvers. In addition, the collected data is applied to improve traffic light control depending on the current traffic situation, especially for VRUs. This abstract describes the LTSA system and its implementation in the German city of Potsdam. The current project state is presented and an outlook on next steps is given.