Abstract

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.

Abstract

This paper presents a continuous traffic-flow model for the explorative analysis of advanced driver-assistance systems (ADASs). Such systems use technology (sensors and intervehicle communication) to support the task of the driver, who retains full control over the vehicle. Based on a review of different traffic-flow modeling approaches and their suitability for exploring traffic-flow patterns in the presence of ADASs, kinetic traffic-flow models are selected because of their good representation on both the aggregate level (congestion dynamics) and the level of the individual vehicle (vehicular interactions either directly or through intervehicle communication). The human-kinetic modeling approach is presented. It is a multiclass variant of kinetic traffic-flow models that is strongly based on individual driver behavior, i.e., on fully continuous acceleration/deceleration behavior and explicit modeling of the activation level of the driver. The strength of this modeling approach is illustrated by application to a driver-assistance system that uses intervehicle communication. It warns drivers when approaching sharp decelerations in a queue tail. The explorative analysis shows that the system results in safer and smoother transition from free-flowing to congested traffic. It also avoids compression of the queue tail, thus preventing the emergence of stop-and-go congestion patterns.

Abstract

Far-infrared pedestrian detection approaches for advanced driver-assistance systems based on high-dimensional features fail to simultaneously achieve robust and real-time detection. We propose a robust and real-time pedestrian detection system characterized by novel candidate filters, novel pedestrian features and multi-frame approval matching in a coarse-to-fine fashion. Firstly, we design two filters based on the pedestrians’ head and the road to select the candidates after applying a pedestrian segmentation algorithm to reduce false alarms. Secondly, we propose a novel feature encapsulating both the relationship of oriented gradient distribution and the code of oriented gradient to deal with the enormous variance in pedestrians’ size and appearance. Thirdly, we introduce a multi-frame approval matching approach utilizing the spatiotemporal continuity of pedestrians to increase the detection rate. Large-scale experiments indicate that the system works in real time and the accuracy has improved about 9% compared with approaches based on high-dimensional features only. Document type: Article