Current Issue : April - June Volume : 2019 Issue Number : 2 Articles : 5 Articles
Tire wear is a very complicated phenomenon that is influenced by various\nfactors such as tire material, structure, vehicle and road conditions. In order\nto evaluate tire wear, a method for measuring tire wear using the intensity of\nreflected light was presented [1]. It comprises applying a single layer of reflected\npaint to a tread surface by spraying, and then measuring the intensity\nof light reflected from a matrix of blocks on the unworn tire. In this paper, a\nnumerical technique for predicting the uneven wear of passenger car tire is\npresented. The uneven tire wear produced in wheel alignment condition with\nvehicle speed, camber angle, and toe angle is predicted by the frictional dynamic\nrolling analysis of 3D patterned tire model. The proposed numerical\ntechnique is illustrated through the method of paint testing the wear on the\ntread surface of a tire....
With the development of the economy and the surge in car ownership, the\nsale of used cars has been welcomed by more and more people, and the information\nof the vehicle condition is the focus information of them. The\nframe number is a unique number used in the vehicle, and by identifying it\ncan quickly find out the vehicle models and manufacturers. The traditional\ncharacter recognition method has the problem of complex feature extraction,\nand the convolutional neural network has unique advantages in processing\ntwo-dimensional images. This paper analyzed the key techniques of convolutional\nneural networks compared with traditional neural networks, and proposed\nimproved methods for key technologies, thus increasing the recognition\nof characters and applying them to the recognition of frame number\ncharacters....
This work is meant to report on activities at TU Delft on the design and implementation\nof a path-following system for an autonomous Toyota Prius. The design encompasses: finding\nthe vehicle parameters for the actual vehicle to be used for control design; lateral and longitudinal\ncontrollers for steering and acceleration, respectively. The implementation covers the real-time aspects\nvia LabVIEW from National Instruments and the real-life tests. The deployment of the system was\nenabled by a Spatial Dual Global Positioning System (GPS) system providing more accuracy than the\nregular GPS. The results discussed in this work represent the first autonomous tests on the Toyota\nPrius at TU Delft, and we expect the proposed system to be a benchmark against which to test more\nadvanced solutions. The tests show that the system is able to perform in real-time while satisfying\ncomfort and trajectory tracking requirements: in particular, the tracking error was within 16 cm,\nwhich is compatible with the 13 cm precision of the Spatial Dual GPS, whereas the longitudinal and\nlateral acceleration are within comfort levels as defined by available experimental studies....
Road scene model construction is an important aspect of intelligent transportation system\nresearch. This paper proposes an intelligent framework that can automatically construct road scene\nmodels from image sequences. The road and foreground regions are detected at superpixel level via\na new kind of random walk algorithm. The seeds for different regions are initialized by trapezoids\nthat are propagated from adjacent frames using optical flow information. The superpixel level region\ndetection is implemented by the random walk algorithm, which is then refined by a fast two-cycle\nlevel set method. After this, scene stages can be specified according to a graph model of traffic\nelements. These then form the basis of 3D road scene models. Each technical component of the\nframework was evaluated and the results confirmed the effectiveness of the proposed approach....
Throughout the past decade, vehicular networks have attracted a great deal of interest\nin various fields. The increasing number of vehicles has led to challenges in traffic regulation.\nVehicle-type detection is an important research topic that has found various applications in numerous\nfields. Its main purpose is to extract the different features of vehicles from videos or pictures captured\nby traffic surveillance so as to identify the types of vehicles, and then provide reference information\nfor traffic monitoring and control. In this paper, we propose a step-forward vehicle-detection and\n-classification method using a saliency map and the convolutional neural-network (CNN) technique.\nSpecifically, compressed-sensing (CS) theory is applied to generate the saliency map to label the\nvehicles in an image, and the CNN scheme is then used to classify them. We applied the concept of\nthe saliency map to search the image for target vehicles: this step is based on the use of the saliency\nmap to minimize redundant areas. CS was used to measure the image of interest and obtain its\nsaliency in the measurement domain. Because the data in the measurement domain are much smaller\nthan those in the pixel domain, saliency maps can be generated at a low computation cost and faster\nspeed. Then, based on the saliency map, we identified the target vehicles and classified them into\ndifferent types using the CNN. The experimental results show that our method is able to speed up\nthe window-calibrating stages of CNN-based image classification. Moreover, our proposed method\nhas better overall performance in vehicle-type detection compared with other methods. It has very\nbroad prospects for practical applications in vehicular networks....
Loading....