Τα τελευταία χρόνια υπάρχει μεγάλο ενδιαφέρον προς την κατεύθυνση της αναγνώρισης αυτοκινήτου με χρήση διαφορετικών μεθόδων. Η ανάπτυξη ενός κατάλληλου συστήματος υποβοήθησης της οδήγησης είναι εξαιρετικής σημασίας και απαιτεί τη δέουσα προσοχή και έρευνα. Σκοπός της παρούσης διπλωματικής εργασίας είναι η μελέτη, η ανάπτυξη καθώς και η εφαρμογή των πλέον αξιόπιστων μεθόδων αναγνώρισης αυτοκινήτου. Προς αυτήν την κατεύθυνση, μελετώνται λεπτομερώς οι αντίστοιχες μέθοδοι και παρουσιάζονται εκτενώς, τόσο με χρήση πραγματικών (real-time) βίντεο όσο και με την επεξεργασία διαφορετικών συνθηκών. Δίνεται ιδιαίτερη έμφαση στην ανάλυση της οπτικής ροής, η οποία κρίνεται βασική συγκριτικά με τις υπόλοιπες μεθόδους. Τέλος, παρουσιάζονται τα χαρακτηριστικά των πιο αντιπροσωπευτικών μεθόδων και παρατίθενται σχετικές προτάσεις για βελτίωση. / In recent years there has been great interest towards car identification using different methods. The development of an appropriate system of driver assistance is of paramount importance and requires proper attention and investigation. The purpose of this thesis is to study, develop and implement the most reliable methods of car detection. To this direction, the corresponding methods are studied in detail and are presented extensively, using both the actual (real-time) video and the treatment of different conditions. Particular emphasis is given to the analysis of optical flow, which is basic compared to other methods. Finally, the characteristics of the most representative methods are presented along with proposals for improvement.

This thesis presents a general, trainable system for object detection in static images and video sequences. The core system finds a certain class of objects in static images of completely unconstrained, cluttered scenes without using motion, tracking, or handcrafted models and without making any assumptions on the scene structure or the number of objects in the scene. The system uses a set of training data of positive and negative example images as input, transforms the pixel images to a Haar wavelet representation, and uses a support vector machine classifier to learn the difference between in-class and out-of-class patterns. To detect objects in out-of-sample images, we do a brute force search over all the subwindows in the image. This system is applied to face, people, and car detection with excellent results. For our extensions to video sequences, we augment the core static detection system in several ways -- 1) extending the representation to five frames, 2) implementing an approximation to a Kalman filter, and 3) modeling detections in an image as a density and propagating this density through time according to measured features. In addition, we present a real-time version of the system that is currently running in a DaimlerChrysler experimental vehicle. As part of this thesis, we also present a system that, instead of detecting full patterns, uses a component-based approach. We find it to be more robust to occlusions, rotations in depth, and severe lighting conditions for people detection than the full body version. We also experiment with various other representations including pixels and principal components and show results that quantify how the number of features, color, and gray-level affect performance.

This paper describes a general, trainable architecture for object detection that has previously been applied to face and peoplesdetection with a new application to car detection in static images. Our technique is a learning based approach that uses a set of labeled training data from which an implicit model of an object class -- here, cars -- is learned. Instead of pixel representations that may be noisy and therefore not provide a compact representation for learning, our training images are transformed from pixel space to that of Haar wavelets that respond to local, oriented, multiscale intensity differences. These feature vectors are then used to train a support vector machine classifier. The detection of cars in images is an important step in applications such as traffic monitoring, driver assistance systems, and surveillance, among others. We show several examples of car detection on out-of-sample images and show an ROC curve that highlights the performance of our system.

Les systèmes d'aide à la conduite (ADAS) visent à automatiser/ adapter/ améliorer les systèmes de transport pour une meilleure sécurité et une conduite plus sûre. Plusieurs thématiques de recherche traitent des problématiques autour des ADAS, à savoir la détection des obstacles, la reconnaissance de formes, la compréhension des images, la stéréovision, etc. La présence des réflexions spéculaires limite l'efficacité et la précision de ces algorithmes. Elles masquent les textures de l'image originale et contribuent à la perte de l'information utile. La polarisation de la lumière traduit implicitement l'information attachée à l'objet, telle que la direction de la surface, la nature de la matière, sa rugosité etc. Dans le contexte des ADAS, l'imagerie polarimétrique pourrait être utilisée efficacement pour éliminer les réflexions parasites des images et analyser d'une manière précise les scènes routières. Dans un premier temps, nous proposons dans cette thèse de supprimer les réflexions spéculaires des images via la polarisation en appliquant une minimisation d'énergie globale. L'information polarimétrique fournit une contrainte qui réduit les distorsions couleurs et produit une image diffuse beaucoup plus améliorée. Nous avons ensuite proposé d'utiliser les images de polarisation comme une caractéristique vu que dans les scènes routières, les hautes réflexions proviennent particulièrement de certains objets telles que les voitures. Les attributs polarimétriques sont utilisés pour la compréhension de la scène et la détection des voitures. Les résultats expérimentaux montrent que, une fois correctement fusionnés avec les caractéristiques couleur, les attributs polarimétriques offrent une information complémentaire qui améliore considérablement les résultats de la détection.Nous avons enfin testé l'imagerie de polarisation pour l'estimation de la carte de disparité. Une méthode d'appariement est proposée et validée d'abord sur une base de données couleur. Ensuite, Une règle de fusion est proposée afin d'utiliser l'imagerie polarimétrique comme une contrainte pour le calcul de la carte de disparité. A partir des différents résultats obtenus, nous avons prouvé le potentiel et la faisabilité d'appliquer l'imagerie de polarisation dans différentes applications liées aux systèmes d’aide à la conduite. / Advance Driver Assistance Systems (ADAS) aim to automate/adapt/enhance trans-portation systems for safety and better driving. Various research topics are emerged to focus around the ADAS, including the object detection and recognition, image understanding, disparity map estimation etc. The presence of the specular highlights restricts the accuracy of such algorithms, since it covers the original image texture and leads to the lost of information. Light polarization implicitly encodes the object related information, such as the surface direction, material nature, roughness etc. Under the context of ADAS, we are inspired to further inspect the usage of polarization imaging to remove image highlights and analyze the road scenes.We firstly propose in this thesis to remove the image specularity through polarization by applying a global energy minimization. Polarization information provides a color constraint that reduces the color distortion of the results. The global smoothness assumption further integrates the long range information in the image and produces an improved diffuse image.We secondly propose to use polarization images as a new feature, since for the road scenes, the high reflection appears only upon certain objects such as cars. Polarization features are applied in image understanding and car detection in two different ways. The experimental results show that, once properly fused with rgb-based features, the complementary information provided by the polarization images improve the algorithm accuracy. We finally test the polarization imaging for depth estimation. A post-aggregation stereo matching method is firstly proposed and validated on a color database. A fusion rule is then proposed to use the polarization imaging as a constraint to the disparity map estimation. From these applications, we proved the potential and the feasibility to apply polariza-tion imaging in outdoor tasks for ADAS.

This report presents a method for estimating the presence and duration of preceding and lead vehicle in front of a motorcycle using an object detection algorithm guided by radar data. The video and radar data were collected as part of a large transportation project. The data are recorded by the ego vehicle during a trip while in a naturalistic research study. The goal is to validate objects detected by radar using vision, to identify moving preceding vehicles and the lead vehicle. The proposed approach takes advantage of radar data in locating the vehicles and other targets and then validates the targets as vehicles using Dual-Tree Branch-and-Bound (Kokkinos, 2011) object detection algorithm. Localization, detection and tracking took 0.0385 seconds per frame on average. Precision and recall of lead vehicle detection is 98.61% and 90.53% respectively. The algorithm presents a comprehensive approach to localize target vehicles in video. The radar object coordinates are mapped on the video frame using perspective projection map- ping. Then persistent radar objects are determined by analyzing their trajectory on video frames. When a radar object appears for three consecutive frames, its called a persistent object. A region of interest (ROI) around the persistent radar object is cropped from the frame, and passed to the object detection algorithm to determine if the persistent object is a car. Once a car is detected the validation of the radar object is complete. We track the detected car in the following frames and refresh the detection after every fourteen frames. The car detection algorithm runs whenever a new persistent radar object is introduced. After validating radar objects, at each timestamp, the lead vehicle is determined using radar object's forward and lateral distance. The time from detecting a lead vehicle to the time when the vehicle disappears or another vehicle becomes lead vehicle, is recorded to get the epochs of following driving mode for that lead vehicle. Finally, the detection result is integrated with MATLAB lane detection system to make a complete system for lead vehicle detection and tracking. The video of interest has 240x720 resolution and approximately 15 frames per second. The car detection algorithm takes 0.1960 seconds on average to detect one car in a machine with Windows operating system and 4GB RAM. But as the detection algorithm is not run for each frame it saves time. Since no annotated motorcycle video dataset is publicly available, two videos of 52 seconds and 26 seconds were manually annotated to test the performance of the approach. The current approach works almost at real time. The algorithm has been tested and results have been reported on 1 video. / Master of Science

Η αποφυγή συγκρούσεων με αναγνώριση της θέσης και της σχετικής ταχύτητας προπορευόμενων οχημάτων είναι μια άκρως ενδιαφέρουσα εφαρμογή που βρίσκεται σε πειραματικό στάδιο. Η ύπαρξη πολλαπλών αντικειμένων στο οπτικό πεδίο της κάμερας δημιουργεί προβλήματα στον ακριβή εντοπισμό του προπορευόμενου οχήματος, ενώ η έλλειψη βάσεων δεδομένων με κατηγοριοποιημένα παραδείγματα είναι ένα επιπλέον εμπόδιο για την ανάπτυξη της εφαρμογής αυτής. Στην εργασία αυτή περιγράφονται οι υπάρχουσες εφαρμογές όσον αφορά στο πρόβλημα της μηχανικής όρασης στην αυτοκίνηση, τα προβλήματα που λύνουν αλλά και οι δυσκολίες που συνεχίζουν να υπάρχουν. Αναφέρονται οι αιτίες της έλλειψης βάσεων δεδομένων με κατηγοριοποιημένα παραδείγματα και αναλύεται η ημιαυτόματη μέθοδος (Random Walker) στην οποία καταφεύγουμε για τον λόγο αυτό. Εν συνεχεία θα παρουσιαστούν τα αποτελέσματα της ανάπτυξης σε Matlab που πραγματοποιήθηκε, τα συμπεράσματα που προέκυψαν, αλλά και οι μελλοντικές προκλήσεις. / In this diplom work, the ways followed to deal with the issue of mechanical vision in car driving are described. The reasons why there there are not any specific data sets are decribed and the focus of this work is on the Random Walker algorithm.

Σκοπός της παρούσας εργασίας είναι η μελέτη, η ανάπτυξη καθώς και η μερική εφαρμογή κάποιων μεθόδων για την ανίχνευση θέσης κάποιου οχήματος. Ιδιαίτερη βάση δόθηκε στη μελέτη και την ανάλυση της οπτικής ροής που θεωρείται βασική συγκριτικά με τις υπόλοιπες μεθόδους.Τέλος αναλύεται και μια μέθοδος κατάτμησης εικόνων. / The goal of this thesis is to study, develop and implement some methods of car detection. Particular emphasis is given to the analysis of optical flow, which is considered to be critical compared to other methods. Finally an analysis of a method for image segmentation is being developed.

The process of finding a parking space can be a tedious task that drivers spent too much time on today. With the rising threat from global warming, reducing the time spent driving is vital. The purpose of this thesis is to evaluate the use of LoRaWAN for urban IoT applications by developing a sensor system for parking space monitoring to make this process easier. The main component of the developed prototype of the sensor system consists of a The Things UNO, which is a modified version of the Arduino Leonardo with an integrated RN2483 LoRaWAN transceiver module. Two types of sensors, an ultrasonic distance sensor and a magnetometer, were tested for car detecting abilities in the sensor system. The distance sensor was proven to be the more reliable sensor for detecting cars, but a combination of both a distance sensor and a magnetometer can be used to improve the power usage of the system. LoRaWAN has a high potential to work great in a parking space monitoring system and other urban IoT applications, but its coverage and reliability in different conditions requires more testing. / Att hitta en parkeringsplats kan vara en omständing uppgift, och är något som bilister idag spenderar för mycket tid på. Med den ökade risken från global uppvärmning är det viktigt att försöka reducera körtid. Syftet med den här rapporten är att utvärdera användandet av LoRaWAN för urbana IoT-applikationer genom att utveckla ett sensorsystem för att bevaka parkeringsplatser för att göra det enklare att hitta lediga parkeringsplatser. Huvudkomponenten i den utvecklade prototypen av sensorsystemet är en TheThings UNO, vilket är en modifierad version av en Arduino Leonardo med en inbyggd RN2483 LoRaWAN-modul. Två sorters sensorer, en avståndssensor och en magnetometer, testades i sensorsystemet. Avståndssensorn visade sig vara den mer pålitliga sensorn för att detektera bilar. En kombination av en avståndssensor och en magnetometer kan poteniellt användas tillsammans för att minska strömanvändningen. LoRaWANhar stor potential att fungera i ett parkeringbevakningssystem samt andra urbana IoT-applikationer, men dess täcking och pålitlighet i olika miljöer borde undersökas mer.

The aim of this thesis is to create a cloud application for traffic analysis without knowing anything about the system. The only input is address of the web camera pointing at traffic. This application is build on existing solution which is further enhanced. New modules for removing obstacles (such as lamppost covering part of the road) and splitting overlapping cars were added. The whole cloud solution consists of multiple components which communicates by HTTP messages and are controlled by web interface.

This research project took part in the SENA project (Autonomous Embedded Navigation System), which was developed at the Mobile Robotics Lab of the Mechatronics Group at the Engineering School of São Carlos, University of São Paulo (EESC - USP) in collaboration with the São Carlos Institute of Physics. Aiming for an autonomous behavior in the prototype vehicle this dissertation focused on deploying some machine learning algorithms to support its perception. These algorithms enabled the vehicle to execute articial-intelligence tasks, such as prediction and memory retrieval for object classication. Even though in autonomous navigation there are several perception, cognition and actuation tasks, this dissertation focused only on perception, which provides the vehicle control system with information about the environment around it. The most basic information to be provided is the existence of objects (obstacles) around the vehicle. In formation about the sort of object it is also provided, i.e., its classication among cars, pedestrians, stakes, the road, as well as the scale of such an object and its position in front of the vehicle. The environmental data was acquired by using a camera and a Velodyne LiDAR. A ceiling analysis of the object detection pipeline was used to simulate the proposed methodology. As a result, this analysis estimated that processing specic regions in the PDF Compressor Pro xii image (i.e., Regions of Interest, or RoIs), where it is more likely to nd an object, would be the best way of improving our recognition system, a process called image normalization. Consequently, experimental results in a data-fusion approach using laser data and images, in which RoIs were found using the LiDAR data, showed that the fusion approach can provide better object detection and classication compared with the use of either camera or LiDAR alone. Deploying a data-fusion classication using RoI method can be executed at 6 Hz and with 100% precision in pedestrians and 92.3% in cars. The fusion also enabled road estimation even when there were shadows and colored road markers in the image. Vision-based classier supported by LiDAR data provided a good solution for multi-scale object detection and even for the non-uniform illumination problem. / Este projeto de pesquisa fez parte do projeto SENA (Sistema Embarcado de Navegação Autônoma), ele foi realizado no Laboratório de Robótica Móvel do Grupo de Mecatrônica da Escola de Engenharia de São Carlos (EESC), em colaboração com o Instituto de Física de São Carlos (IFSC). A grande motivação do projeto SENA é o desenvolvimento de tecnologias assistidas e autônomas que possam atender às necessidades de diferentes tipos de motoristas (inexperientes, idosos, portadores de limitações, etc.). Vislumbra-se que a aplicação em larga escala desse tipo de tecnologia, em um futuro próximo, certamente reduzirá drasticamente a quantidade de pessoas feridas e mortas em acidentes automobilísticos em estradas e em ambientes urbanos. Nesse contexto, este projeto de pesquisa teve como objetivo proporcionar informações relativas ao ambiente ao redor do veículo, ao sistema de controle e de tomada de decisão embarcado no veículo autônomo. As informações mais básicas fornecidas são as posições dos objetos (obstáculos) ao redor do veículo; além disso, informações como o tipo de objeto (ou seja, sua classificação em carros, pedestres, postes e a própria rua mesma), assim como o tamanho deles. Os dados do ambiente são adquiridos através do emprego de uma câmera e um Velodyne LiDAR. Um estudo do tipo ceiling foi usado para simular a metodologia da detecção dos obstáculos. Estima-se que , após realizar o estudo, que analisar regiões especificas da imagem, chamadas de regiões de interesse, onde é mais provável encontrar um obstáculo, é o melhor jeito de melhorar o sistema de reconhecimento. Observou-se na implementação da fusão dos sensores que encontrar regiões de interesse usando LiDAR, e classificá-las usando visão artificial fornece um melhor resultado na hora de compará-lo com os resultados ao usar apenas câmera ou LiDAR. Obteve-se uma classificação com precisão de 100% para pedestres e 92,3% para carros, rodando em uma frequência de 6 Hz. A fusão dos sensores também forneceu um método para estimar a estrada mesmo quando esta tinha sombra ou faixas de cor. Em geral, a classificação baseada em visão artificial e LiDAR mostrou uma solução para detecção de objetos em várias escalas e mesmo para o problema da iluminação não uniforme do ambiente.