正在加载图片...
第2期 陆建,等:道路交通网络安全风险辨识研究进展 409 信及车路之间的智能感知,为车辆之间的碰撞风险[6] Messelodi s, Modena c m, Zanin m,etal. Intelligent 提供实时预警,并有效评估网联汽车和常规汽车混 extended floating car data collection[J]. Expert Systems 合运行环境下的交通运输网络安全风险 th Applications, 2009, 36(3):4213-4227. DOI 1016/ 1. eswa.2008.04.008. 总结可知,目前国内道路交通安全形势依然严[7] Pan X,LuJG,DiS,etal. Cellular-based data-ex 峻,相关的研究进展仍需完善.另外,国内城市道路 tracting method for trip distribution[J]. Transportation 交通网络结构复杂,机非混行、交通违法等一定程 al of the Transportation Re 度上阻碍了道路交通网络安全风险的有效识别和 search board,2006,1945(1):33-39.Dol:10 预警;而目前兴起的自动驾驶技术虽在一定程度缓 1177/0361198106194500105 解了车辆之间的冲突,但对于人车冲突的改善及其 [8 Faouzi N EE, Leung H, Kurian A. Data fusion inin- telligent transportation systems: Progress and challen- 法律层面的保护仍需提高.同时,由于不同模式交 ges-A survey [J]. Information Fusion, 2011, 12(1) 通数据获取较为困难,如何高效获取不同来源的交 通信息,并建立合法的数据共享机制,打破不同部[9] Rehrl K, Brunauer r, Grochenig S. Collecting floating 门之间的数据孤岛,真正实现多源异构交通数据的 car data with smartphones: Results from a field trial in 互联互通仍需要很长的路要走 Austria[ J]. Journal of Location Based Services, 2016 10(1):16-30.DOI:10.1080/17489725.2016. 当然,道路交通网络安全风险辨识领域的相关 1169323 进展远不止本研究所述由于篇幅和作者研究领域[10o] Dozza m, Gonzalez p. Recognising safety critical 的局限性,有关驾驶人不良驾驶行为、道路参与者 events: Can automatic video processing improve natu- 社会心理因素等所带来的风险及其他相关方面尚 ralistic data analyses? [J]. Accident Analysis &Pre- 未涉及但随着研究的深入和研究手段的不断进 vention,2013,60:298-304.DOI:10.1016/j.aap. 013.02.014 步,以上问题会得到有效解决,届时有关道路交通 [11 Ran B, Song L, Zhang J, et al. Using tensor comple- 网络安全风险辨识的相关研究成果必将在未来得 tion method to achieving better coverage of traffic state 到更广泛的应用,并产生深远的影响 estimation from sparse floating car data [J]. PLos One,2016,11(7):c0157420.DOl:10.1371/jour 参考文献( References) nal pone. 0157420 [1] Wang Y B, Coppola P, Tzimitsi A, et al. Real-time [12 Han Y F, Moutarde F. Analysis of large-scale traffic freeway network traffic surveillance: Large-scale field- dynamics in an urban transportation network using non- testing results in southern Italy[ J]. IEEE Transactions negative tensor factorization[J]. International Journal on Intelligent Transportation Systems, 2011, 12(2) of Intelligent Transportation Systems Research, 2016 14(1):36-49.DOI:10.1007/s131770140099-7 548-562.DOl:10.1109/tits.2011.2107901 [2 Kong Q J, Li Z P, Chen Y K, et al. An approach to [13 Leduc G. Road traffic data: Collection methods and urban traffic state estimation by fusing multisource in- applications[ J]. Working Papers on Energy, Trans- port and Climate Change, 2008, 1(55): JRC 47967 formation[ J]. IEEE Transactions on Intelligent Trans- [14 Bachmann C, Abdulhai B, Roorda M J, et al. A com- portation Systems, 2009, 10(3): 499-511. DOI: 10 parative assessment of multi-sensor data fusion tech- 1109/uts.2009.2026308 niques for freeway traffic speed estimation using micro- [3 Ma X L, Tao Z M, Wang Y H, et al. Long short-term imulation modeling[J]. Transportation Research Part memory neural network for traffic speed prediction C: Emerging Technologies, 2013, 26: 33-48. DOI using remote microwave sensor data[J]. Transportation 10.1016/jtre.2012.07.003 Research Part C: Emerging Technologies, 2015, 54 [15 He S L, Zhang J, Cheng Y, et al 187-197.Dol:10.1016/j.urc.2015.03.014. sor data fusion approach integrating data from cell [4 Kwong K, Kavaler R, Rajagopal R, et al. Real-time phone probes and fixed sensors [J]. Joumal of Sen measurement of link vehicle count and travel time in a sors,2016,2016:1-13.DOl:10.1155/2016/ oad network [J]. IEEE Transactions on intelligent 7269382 DOI:10.1109/its.2010.2050881 公路站间旅行时间[J].交通运输系统工程与信息, [5 Cheng H Y, Hsu S H. Intelligent highway traffic sur 2016,16(1):52-57.DOI:10.3969/ J. Issn.100 veillance with self-diagnosis abilities[ J]. IEEE Trans- 6744.2016.01.009 oJD,ⅪuFF, Zhang K, (4):1462-1472.DOl:10.1109/tits.2011.2160171 time prediction based on multi-source data fusion[J] http://journal.seu.edu.cnhttp://journal.seu.edu.cn 信及车路之间的智能感知,为车辆之间的碰撞风险 提供实时预警,并有效评估网联汽车和常规汽车混 合运行环境下的交通运输网络安全风险. 总结可知,目前国内道路交通安全形势依然严 峻,相关的研究进展仍需完善.另外,国内城市道路 交通网络结构复杂,机非混行、交通违法等一定程 度上阻碍了道路交通网络安全风险的有效识别和 预警;而目前兴起的自动驾驶技术虽在一定程度缓 解了车辆之间的冲突,但对于人车冲突的改善及其 法律层面的保护仍需提高.同时,由于不同模式交 通数据获取较为困难,如何高效获取不同来源的交 通信息,并建立合法的数据共享机制,打破不同部 门之间的数据孤岛,真正实现多源异构交通数据的 互联互通仍需要很长的路要走. 当然,道路交通网络安全风险辨识领域的相关 进展远不止本研究所述.由于篇幅和作者研究领域 的局限性,有关驾驶人不良驾驶行为、道路参与者 社会心理因素等所带来的风险及其他相关方面尚 未涉及.但随着研究的深入和研究手段的不断进 步,以上问题会得到有效解决,届时有关道路交通 网络安全风险辨识的相关研究成果必将在未来得 到更广泛的应用,并产生深远的影响. 参考文献 (References) [1] WangYB,CoppolaP,TzimitsiA,etal.Realtime freewaynetworktrafficsurveillance:Largescalefield testingresultsinsouthernItaly[J].IEEETransactions onIntelligentTransportationSystems,2011,12(2): 548 562.DOI:10.1109/tits.2011.2107901. [2]KongQJ,LiZP,ChenYK,etal.Anapproachto urbantrafficstateestimationbyfusingmultisourcein formation[J].IEEETransactionsonIntelligentTrans portationSystems,2009,10(3):499 511.DOI:10. 1109/tits.2009.2026308. [3]MaXL,TaoZM,WangYH,etal.Longshortterm memory neuralnetwork fortrafficspeed prediction usingremotemicrowavesensordata[J].Transportation ResearchPartC:EmergingTechnologies,2015,54: 187 197.DOI:10.1016/j.trc.2015.03.014. [4]KwongK,KavalerR,RajagopalR,etal.Realtime measurementoflinkvehiclecountandtraveltimeina roadnetwork[J].IEEE TransactionsonIntelligent TransportationSystems,2010,11(4):814 825. DOI:10.1109/tits.2010.2050881. [5] ChengHY,HsuSH.Intelligenthighwaytrafficsur veillancewithselfdiagnosisabilities[J].IEEETrans actionsonIntelligentTransportationSystems,2011,12 (4):1462 1472.DOI:10.1109/tits.2011.2160171. [6]MesselodiS,ModenaCM,ZaninM,etal.Intelligent extendedfloatingcardatacollection[J].ExpertSystems withApplications,2009,36(3):4213 4227.DOI: 10.1016/j.eswa.2008.04.008. [7]PanCX,LuJG,DiS,etal.Cellularbaseddataex tractingmethodfortripdistribution[J].Transportation ResearchRecord:JournaloftheTransportationRe searchBoard,2006,1945(1):33 39.DOI:10. 1177/0361198106194500105. [8]FaouziNEE,LeungH,KurianA.Datafusioninin telligenttransportationsystems:Progressandchallen ges—Asurvey[J].InformationFusion,2011,12(1): 4 10.DOI:10.1016/j.inffus.2010.06.001. [9]RehrlK,BrunauerR,GrchenigS.Collectingfloating cardatawithsmartphones:Resultsfrom afieldtrialin Austria[J].JournalofLocationBasedServices,2016, 10(1):16 30.DOI:10.1080/17489725.2016. 1169323. [10]DozzaM,GonzálezN P.Recognisingsafetycritical events:Canautomaticvideoprocessingimprovenatu ralisticdataanalyses?[J].AccidentAnalysis&Pre vention,2013,60:298 304.DOI:10.1016/j.aap. 2013.02.014. [11]RanB,SongL,ZhangJ,etal.Usingtensorcomple tionmethodtoachievingbettercoverageoftrafficstate estimationfrom sparsefloatingcardata[J].PLoS One,2016,11(7):e0157420.DOI:10.1371/jour nal.pone.0157420. [12]HanYF,MoutardeF.Analysisoflargescaletraffic dynamicsinanurbantransportationnetworkusingnon negativetensorfactorization[J].InternationalJournal ofIntelligentTransportationSystemsResearch,2016, 14(1):36 49.DOI:10.1007/s1317701400997. [13] LeducG.Roadtrafficdata:Collectionmethodsand applications[J].WorkingPapersonEnergy,Trans portandClimateChange,2008,1(55):JRC47967. [14]BachmannC,AbdulhaiB,RoordaM J,etal.Acom parativeassessmentofmultisensordatafusiontech niquesforfreewaytrafficspeedestimationusingmicro simulationmodeling[J].TransportationResearchPart C:EmergingTechnologies,2013,26:33 48.DOI: 10.1016/j.trc.2012.07.003. [15]HeSL,ZhangJ,ChengY,etal.Freewaymultisen sordatafusionapproachintegratingdatafrom cell phoneprobesandfixedsensors[J].JournalofSen sors,2016,2016:1 13. DOI:10.1155/2016/ 7269382. [16]赵建东,徐菲菲,张琨,等.融合多源数据预测高速 公路站间旅行时间[J].交通运输系统工程与信息, 2016,16(1):52 57.DOI:10.3969/j.issn.1009 6744.2016.01.009. ZhaoJD,XuFF,ZhangK,etal.Highwaytravel timepredictionbasedonmultisourcedatafusion[J]. 第 2期 陆建,等:道路交通网络安全风险辨识研究进展 409
<<向上翻页向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有