Infrared (IR) illumination is commonly found in a surveillance camera to improve night-time recording quality. However, the limited available power from Power over Ethernet (PoE) connection in networkenabled cameras restricts the possibilities of increasing image quality by allocating more power to the illumination system.The thesis explored an alternative way to improve the image quality by using strobed IR illumination. Different strobing methods will be discussed in relation to the rolling shutter timing commonly used in CMOS sensors. The method that benefits the evaluation scenario the most was implemented in a prototype which is based on a commercialized fixed-box camera from Axis. The prototype demonstrated how the synchronization of the sensor and the strobing illumination system can be achieved.License plate recognition (LPR) in a dark highway was chosen as the evaluation scenario and an analysis on the car movements was done in a pursue of creating an indoor test. The indoor test provided a controlled environment while the outdoor test exposed the prototype to real-life conditions. The test results show that with strobed IR, the output image experienced brightness improvement and reduction in rolling shutter artifact, compared to constant IR. The theoretical calculation also proved that these improvement does not compromise the average power consumption and eye-safety level of the illumination system. / Infraröd (IR) belysning påträffas ofta i övervakningskameror för att förbättra bildkvalitén vid videoinspelning på natten. Den begränsade tillgängliga effekten från Power over Ethernet-anslutningen (PoE) i nätverksaktiverade kameror sätter dock en övre gräns för hur mycket effekt som kameran tillåts använda till belysningssystemet, och därmed hur pass mycket bildkvalitén kan ökas.I detta examensarbete undersöktes ett alternativt sätt att förbättra bildkvalitén genom att använda blixtrande (eng: ”strobed”) IR-belysning. Olika strobe-metoder undersöktes i relation till rullande slutare, vilket är den slutar-metod som vanligtvis används i CMOS-sensorer. Den metod som gav mest fördelaktiga resultat vid utvärdering implementerades i en prototyp baserad på en kommersiell nätverkskamera av Fixed box-typ från Axis Communications. Denna prototyp visade framgångsrikt ett koncept för hur synkronisering av bildsensorn och belysningssystemet kan uppnås.Registreringsskyltigenkänning (LPR) på en mörk motorväg valdes som utvärderingsscenario och en analys av bilens rörelser gjordes för att skapa en motsvarande testuppställning inomhus. Inomhustesterna gav en kontrollerad miljö medan testerna utomhus utsatte prototypen för verkliga förhållanden. Testresultaten visar att med strobed IR blev bilden från kameran både ljusare och uppvisade mindre artefakter till följd av rullande slutare, jämfört med konstant IR-belysning. Teoretiska beräkningar visade också att dessa förbättringar inte påverkar varken kamerans genomsnittliga effektförbrukning eller ögonsäkerheten för belysningssystemet negativt.

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.

Assunto bastante abordado quando se trata de Sistemas Inteligentes de Transportes (ITS), a identificação veicular - utilizada em grande parte das aplicações de ITS deve ser entendida como um conjunto de recursos de hardware, software e telecomunicações, que interagem para atingir, do ponto de vista funcional, o objetivo de, conseguir extrair e transmitir, digitalmente, a identidade de um veículo. É feita tanto por sistemas que transmitem e recebem uma identidade digital quanto por sistemas que, instalados na infraestrutura da via, são capazes de reconhecer a placa dos veículos circulantes. Quando se trata da identificação automática por meio do reconhecimento da placa veicular, os estudos têm se concentrado sobremaneira nas tecnologias de processamento de imagens, não abordando - em sua maioria - uma visão sistêmica, necessária para compreender de maneira mais abrangente todas as variáveis que podem interferir na eficácia da identificação. Com o objetivo de contribuir para melhor entender e utilizar os sistemas de reconhecimento automático de placas veiculares, este trabalho propõe um modelo sistêmico, em camadas, para representar seus componentes. Associada a esse modelo, propõe uma classificação para os diversos tipos de falhas que podem prejudicar seu desempenho. Uma análise desenvolvida com resultados obtidos em testes realizados em campo com sistemas de identificação de placas voltados à fiscalização de veículos aponta resultados relevantes e limitações para obter correlações entre variáveis, em função dos diversos fatores que podem influenciar os resultados. Algumas entrevistas realizadas apontam os tipos de falhas que ocorrem com mais frequência durante a operação desses sistemas. Finalmente, este trabalho propõe futuros estudos e apresenta um glossário de termos, que poderá ser útil a novos pesquisadores. / The automatic vehicle identification is an important feature of Intelligent Transportation Systems (ITS) and is used in most ITS applications. The identification process is comprised of a group of interacting resources that involves hardware, software and telecommunication to, digitally, extract and transmit the identity of vehicles. At least two technologies may be used in the vehicle identification process: on-board devices transmitting a digital identity or systems installed on the road infrastructure, which identify and read the vehicle license plate. As far as vehicle license plate recognition is concerned, studies have been greatly focused on image processing technologies and have not addressed the problem in a systemic approach, which is very important for understanding all variables that can interfere with the effectiveness of identification. Having this approach in mind and intending to contribute for a better performance, this paper proposes a layer model representation of those systems as well as a failure type classification associated with it. An analysis, based on a significant set of results obtained from field tests of systems with plate recognition capabilities for law enforcement, shows important results as well as limitations to obtain mathematical correlation of variables. Interviews conducted with supply actors of such systems in Brazil point out the most significant sources of failures that occur during operation. Finally, the text presents potential topics for research and organizes a glossary of terms that may be useful to future researchers.

Assunto bastante abordado quando se trata de Sistemas Inteligentes de Transportes (ITS), a identificação veicular - utilizada em grande parte das aplicações de ITS deve ser entendida como um conjunto de recursos de hardware, software e telecomunicações, que interagem para atingir, do ponto de vista funcional, o objetivo de, conseguir extrair e transmitir, digitalmente, a identidade de um veículo. É feita tanto por sistemas que transmitem e recebem uma identidade digital quanto por sistemas que, instalados na infraestrutura da via, são capazes de reconhecer a placa dos veículos circulantes. Quando se trata da identificação automática por meio do reconhecimento da placa veicular, os estudos têm se concentrado sobremaneira nas tecnologias de processamento de imagens, não abordando - em sua maioria - uma visão sistêmica, necessária para compreender de maneira mais abrangente todas as variáveis que podem interferir na eficácia da identificação. Com o objetivo de contribuir para melhor entender e utilizar os sistemas de reconhecimento automático de placas veiculares, este trabalho propõe um modelo sistêmico, em camadas, para representar seus componentes. Associada a esse modelo, propõe uma classificação para os diversos tipos de falhas que podem prejudicar seu desempenho. Uma análise desenvolvida com resultados obtidos em testes realizados em campo com sistemas de identificação de placas voltados à fiscalização de veículos aponta resultados relevantes e limitações para obter correlações entre variáveis, em função dos diversos fatores que podem influenciar os resultados. Algumas entrevistas realizadas apontam os tipos de falhas que ocorrem com mais frequência durante a operação desses sistemas. Finalmente, este trabalho propõe futuros estudos e apresenta um glossário de termos, que poderá ser útil a novos pesquisadores. / The automatic vehicle identification is an important feature of Intelligent Transportation Systems (ITS) and is used in most ITS applications. The identification process is comprised of a group of interacting resources that involves hardware, software and telecommunication to, digitally, extract and transmit the identity of vehicles. At least two technologies may be used in the vehicle identification process: on-board devices transmitting a digital identity or systems installed on the road infrastructure, which identify and read the vehicle license plate. As far as vehicle license plate recognition is concerned, studies have been greatly focused on image processing technologies and have not addressed the problem in a systemic approach, which is very important for understanding all variables that can interfere with the effectiveness of identification. Having this approach in mind and intending to contribute for a better performance, this paper proposes a layer model representation of those systems as well as a failure type classification associated with it. An analysis, based on a significant set of results obtained from field tests of systems with plate recognition capabilities for law enforcement, shows important results as well as limitations to obtain mathematical correlation of variables. Interviews conducted with supply actors of such systems in Brazil point out the most significant sources of failures that occur during operation. Finally, the text presents potential topics for research and organizes a glossary of terms that may be useful to future researchers.

The theme of this thesi’s deals with the detection and recognition of car license plate from pictures made of screening machine situated on a crassing or inside a car. The thesis si divided into two basic parts. First deals with searching for presence of licence plate in the picture. If the marque was found, we continue the second part of the program which identificates the found license plate. The first part of program aspires to find the licence plate by the edge detectors. The second part classifies characters by the method based on an analytical description.

<p>Disertacija prikazuje novi algoritam za detekciju i izdvajanje registarskih tablica iz slike vozila koristeći fazi 2D Gaborov filtar. Parametri filtra: orijentacija i talasna dužina su fazifikovani u cilju optimizacije odziva Gaborovog filtra i postizanja dodatne selektivnosti filtra. Prethodno navedeni parametri dominiraju u rezultatu filtriranja. Bellova i trougaona funkcija pripadnosti pokazale su se kao najbolji izbor pri fazifikaciji parametara filtra. Algoritam je evaluiran nad vi&scaron;e baza slika i postignuti su zadovoljavajući rezultati. Komponente od interesa su efikasno izdvojene i postignuta značajna otpornost na &scaron;um i degradaciju na slici.</p> / <p>The thesis presents a new algorithm for detection and extraction of license plates from a vehicle image using a fuzzy two-dimensional Gabor filter. The filter parameters, orientation and wavelengths are fuzzified to optimize the Gabor filter&rsquo;s response and achieve a greater selectivity. It was concluded that Bell&rsquo;s function and triangular membership function are the most efficient methods for fuzzification. Algorithm was evaluated on several databases and has provided satisfactory results. The components of interest were efficiently extracted, and the procedure was found to be very noise-resistant.</p>

В работе актуализируется проблема поиска свободного парковочного места на крупных парковках. Разработанная система видео-мониторинга парковочного пространства, являющаяся частью программного комплекса «Умная парковка», включает в себя два модуля: модуль распознавания номеров для идентификации приезжающих автомобилей, модуль распознавания графических меток для мониторинга парковочных мест. Работы по тестированию проводилась на макете автомобильной парковки с использованием радиоуправляемых моделей. / The problem of finding a free parking space in large parking lots is being updated. The developed video monitoring system for the parking space, which is part of the Smart Parking program, includes two modules. The module of number recognition serves for identification of visiting cars. The module of recognition of graphic marks serves for monitoring of parking places. Testing was carried out on a minimized parking model.

A 15.5-mile portion of the I-85 high-occupancy vehicle (HOV) lane in the metropolitan area of Atlanta, GA was converted to a high-occupancy toll (HOT) lane as part of a federal demonstration project designed to provide a reliable travel option through this congested corridor. Results from the I-85 demonstration project provided insight into the results that may follow the Georgia Department of Transportation's planned implementation of a $16 billion HOT lane network along metropolitan Atlanta's other major roadways [2]. To evaluate the impacts of the conversion, it was necessary to measure changes in corridor travel speed, reliability, vehicle throughput, passenger throughput, lane weaving, and user demographics. To measure such performance, a monitoring project, led by the Georgia Institute of Technology collected various forms of data through on-site field deployments, GDOT video, and cooperation from the State Road and Toll Authority (SRTA). Changes in the HOT lane's speed, reliability or other performance measure can affect the demographic and vehicle characteristics of those who utilize the corridor. The purpose of this particular study was to analyze the changes to the vehicle characteristics by comparing vehicle occupancy, vehicle classifications, and vehicle registration data to their counterparts from before the HOV-to-HOT conversion. As part of the monitoring project, the Georgia Tech research team organized a two-year deployment effort to collect data along the corridor during morning and afternoon peak hours. One year of data collection occurred before the conversion date to establish a control and a basis from which to compare any changes. The second year of data collection occurred after the conversion to track those changes and observe the progress of the lane's performance. While on-site, researchers collected data elements including visually-observed vehicle occupancy, license plate numbers, and vehicle classification [25]. The research team obtained vehicle records by submitting the license plate tag entries to a registration database [26]. In previous work, vehicle occupancy data were collected independently of license plate records used to establish the commuter shed. For the analyses reported in this thesis, license plate data and occupancy data were collected concurrently, providing a link between occupancy records of specific vehicles and relevant demographic characteristics based upon census data. The vehicle records also provided characteristics of the users' vehicles (light-duty vehicle vs. sport utility vehicle, model year, etc.) that the researchers aggregated to identify general trends in fleet characteristics. The analysis reported in this thesis focuses on identifying changes in vehicle characteristics that resulted from the HOV-to-HOT conversion. The data collected from post-conversion are compared to pre-conversion data, revealing changes in vehicle characteristics and occupancy distributions that most likely resulted from the implementation of the HOT lane. Plausible reasons affecting the vehicle characteristics alterations will be identified and further demographic research will enhance the data currently available to better pinpoint the cause and effect relationship between implementation and the current status of the I-85 corridor. Preliminary data collection outliers were identified by using vehicle occupancy data. However, future analysis will reveal the degree of their impact on the project as a whole. Matched occupancy and license plate data revealed vehicle characteristics for HOT lane users as well as indications that the tested data collectors are predominantly synchronized when concurrently collecting data, resulting in an argument to uphold the validity of the data collection methods. Chapter two provides reasons for why HOT lanes were sought out to replace I-85's HOV lanes. Chapter two will also provide many details regarding how the HOT lanes function and it will describe the role the Georgia Institute of Technology played in the assessment the HOV-to-HOT conversion. Chapter three includes the methodologies used to complete this document while chapter four provides results and analysis for the one year period before the conversion and the one year period after the conversion.

The thesis deals with analysis and design of system for automatic localization and recognition of the license plate. The input images are from different sources, and contain large scenic and weather variations. The aim was to create a system able to find the licence plate on the image and recognize its alphanumeric figure. In this work, there is a focus on analysis and implementation of localization and optical character recognition methods. One own and four other localization methods are compared. There are also compared three classifiers for optical character recognition. Localization and OCR methods are tested on real data and evaluated in accordance with the calculated evaluation parameters. The work also contains sensitivity analysis of the proposed system.

Konceptet automatiserad igenkänning och avläsning av registreringsskyltarhar utvecklats mycket de senaste åren och användningen av Artificiellaneurala nätverk har introducerats i liten skala med lovande resultat. Viundersökte möjligheten att använda detta i ett automatiserat system förgarageportar och implementerade en prototyp för testning. Den traditionellaprocessen för att läsa av en skylt kräver flera steg, i vissa fall upp till fem.Dessa steg ger alla en felmarginal som aggregerat kan leda till över 30% riskför ett misslyckat resultat. I denna uppsats adresseras detta problem och medhjälp av att använda oss utav Artificiella neurala nätverk utvecklades enkortare process med endast två steg för att läsa en skylt, (1) lokaliseraregistreringsskylten (2) läsa karaktärerna på registreringsskylten. Dettaminskar antalet steg till hälften av den traditionella processen samt minskarrisken för fel med 13%. Vi gjorde en Litteraturstudie för att identifiera detlämpligaste neurala nätverket för uppgiften att lokalisera registreringsskyltarmed vår miljös begränsningar samt möjligheter i åtanke. Detta ledde tillanvändandet av Faster R-CNN, en algoritm som använder ett antal artificiellaneurala nätverk. Vi har använt metoden Design och Creation för att skapa enproof of concept prototyp som använder vårt föreslagna tillvägagångssätt föratt bevisa att det är möjligt att implementera detta i en verklig miljö. / The concept of automated recognition and reading of license plates haveevolved a lot the last years and the use of Artificial neural networks have beenintroduced in a small scale with promising results. We looked into thepossibility of using this in an automated garage port system and weimplemented a prototype for testing. The traditional process for reading alicense plate requires multiple steps, sometimes up to five. These steps all givea margin of error which aggregated sometimes leads to over 30% risk forfailure. In this paper we addressed this issue and with the help of a Artificialneural network. We developed a process with only two steps for the entireprocess of reading a license plate, (1) localize license plate (2) read thecharacters on the plate. This reduced the number of steps to half of theprevious number and also reduced the risk for errors with 13%. We performeda Literature Review to find the best suited algorithm for the task oflocalization of the license plate in our specific environment. We found FasterR-CNN, a algorithm which uses multiple artificial neural networks. We usedthe method Design and Creation to implement a proof of concept prototypeusing our approach which proved that this is possible to do in a realenvironment.