我国城市停车诱导系统及关键技术的研究外文翻译资料

英语原文共 7 页，剩余内容已隐藏，支付完成后下载完整资料

原文

Data fusion in intelligent transportation systems: Progress and challenges – A survey

Nour-Eddin El Faouzi^a,b,c，Henry Leung^d， Ajeesh Kurian^d,*

^aTransport and Traffic Engineering Laboratory, INRETS, LICIT, Bron F-69675, France

^b ENTPE, LICIT, Vaulx-en-Velin F-69518, France

^c University of Lyon, Lyon F-69003, France

^d Department of Electrical and Computer Engineering, University of Calgary, Calgary, Alberta, Canada T2N 1N4

Article info

Article history:

Received 9 June 2010

Accepted 9 June 2010

Available online 18 June 2010

Abstract

In intelligent transportation systems (ITS), transportation infrastructure is complimented with information and communication technologies with the objectives of attaining improved passenger safety,reduced transportation time and fuel consumption and vehicle wear and tear. With the advent of modern communication and computational devices and inexpensive sensors it is possible to collect and process data from a number of sources. Data fusion (DF) is collection of techniques by which information from multiple sources are combined in order to reach a better inference. DF is an inevitable tool for ITS. This paper provides a survey of how DF is used in different areas of ITS.

Keywords: Intelligent transportation systems； Information fusion；Advanced traveler information systems；Global positioning systems；Incident detection

2010 Elsevier B.V. All rights reserved.

1. Introduction

Providing accurate traffic information is becoming a major challenge for the public institutions and private companies leading to the rapid growth of intelligent transportation system (ITS) [1]. At the same time, the emergence of new information technologies and the transformation that has occurred in road traffic management has both increased a need for very accurate road traffic information.In order to provide an accurate and more comprehensive traffic state on a road network, the traffic sensors that are usually used to measure the prevailing traffic conditions are ineffective.Other sources of data (such as cameras, GPS, cell phone tracking, and probe vehicles) are increasingly used to supplement the information provided by those conventional measurement systems. In addition, authorities normally keep track of traffic activities and archive such information. This offline information, together with the measurements from other sensors is often found to be useful in predicting the traffic trend. Multiple sources may provide complementary data, and multi-source data fusion can produce a better understanding of the observed situation by decreasing the uncertainty related to the individual sources. The fusion of multiple sources is perceived, rightly, as a well-adapted answer to the operational needs of traffic management centers and traffic information operators, allowing them to achieve their goal more efficiently. The primary goal of this survey paper is to acquaint the reader with the most significant applications of data fusion (DF) techniques in intelligent transportation systems and to indicate the directions for future research in this area.

The paper is organized into five sections. Section 2 describes basic traffic engineering operations with emphasis on data sources available. DF applications to the traffic engineering area are presented in Section 3. Section 4 describes prospective research analysis with conclusions in Section 5.

2. Data fusion background

Data fusion is applied in diverse fields in civilian and military applications such as surveillance and reconnaissance, wildlife habitat monitoring, and detection of environment hazards [2–5]. Several methodologies have been proposed in the literature for the purpose of multi-sensor fusion and aggregation under heterogeneous data configurations. Due to the different types of sensors that are used and the heterogeneous nature of information that needs to be combined, different data fusion techniques are being developed to suit the applications and data. These techniques were drawn from a wide range of areas including artificial intelligence, pattern recognition, statistical estimation, and other areas. Traffic engineering field has naturally benefited from this abundant literature.For instance, independent of specific application a variety of techniques can be used for ranging from a sample arithmetic mean to a more complex DF approach. More precisely, a three-way split could be suggested:

– Statistical approaches: weighted combination, multivariate statistical analysis and its most up-to-date form data mining engine [6]. Among statistical techniques, the arithmetic mean approach is the simplest which is used for information combination.

This approach is not suitable when the information at hand is not exchangeable or when estimators/classifiers have dissimilar performances [7–9].

– Probabilistic approaches: for instance, Bayesian approach with Bayesian network and state-space models [10], maximum likelihood methods and Kalman filter based DF [11,12], possibility theory [13], evidential reasoning and more specifically evidence theory [14–16] are widely used for the multi-sensor data fusion. This later technique could be viewed as a generalization of Bayesian approach [15–17].

– Artificial intelligence: neural networks and artificial cognition including artificial intelligence, genetic algorithms and neural networks. In many applications, this later approach serves both as a tool to derive classifiers or estimators and as a fusion framework of classifiers/estimators [6,8].

Although applicatio

剩余内容已隐藏，支付完成后下载完整资料

资料编号：[151522]，资料为PDF文档或Word文档，PDF文档可免费转换为Word