1.中山大学智能工程学院,广东 深圳 518107
2.广东省智能交通系统重点实验室,广东 深圳 518107
3.广东省交通环境智能监测与治理工程技术研究中心,广东 深圳 518107
4.广东工贸职业技术学院,广东 广州 510510
乔文瑛(1999年生),女;研究方向:智能交通系统;E-mail:qiaowy@mail2.sysu.edu.cn
黄敏(1975年生),女;研究方向:智能交通系统;E-mail:huangm7@mail.sysu.edu.cn
纸质出版日期:2024-01-25,
网络出版日期:2023-10-30,
收稿日期:2023-08-20,
录用日期:2023-09-14
扫 描 看 全 文
乔文瑛,黄敏,张小兰.面向车辆个体出行检测的卡口布设优化模型[J].中山大学学报(自然科学版)(中英文),2024,63(01):137-144.
QIAO Wenying,HUANG Min,ZHANG Xiaolan.Optimization model of bayonet layout for individual vehicle travel detection[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2024,63(01):137-144.
乔文瑛,黄敏,张小兰.面向车辆个体出行检测的卡口布设优化模型[J].中山大学学报(自然科学版)(中英文),2024,63(01):137-144. DOI: 10.13471/j.cnki.acta.snus.2023B053.
QIAO Wenying,HUANG Min,ZHANG Xiaolan.Optimization model of bayonet layout for individual vehicle travel detection[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2024,63(01):137-144. DOI: 10.13471/j.cnki.acta.snus.2023B053.
针对高清卡口检测器可以获取出行者个体级别的细粒度信息但难以实现路网全覆盖的问题,从缺失轨迹重构角度出发,研究了面向车辆个体出行检测的卡口布设优化方法。考虑相邻两次卡口检测序列间的缺失情况,提出缺失轨迹一次重构、二次重构方法。基于一次重构原理,创建流量捕获率、轨迹覆盖率以衡量卡口布设方案对路面交通信息的检测规模;基于二次重构原理,创建缺失轨迹离散度以衡量轨迹重构可靠度。以流量捕获率、轨迹覆盖率作为约束条件,以最大化缺失轨迹离散度作为卡口布设优化目标,构建了面向车辆个体出行检测的卡口布设优化模型,并采用粒子群算法求解。以广州市海珠区某区域路网为例,分全新布设和新增布设两种情况进行算例分析,结果表明:在全新布设场景中,优化后的卡口布设方案相流量捕获率提升了6.20%,轨迹覆盖率提升了2.76%,缺失轨迹离散度提升了139%,在车辆个体出行轨迹检测及重构方面比当前方案获得了更优的效果;在新增布设场景中,依次对新增的1-6个卡口进行优化求解,得到了新增位置和优化结果。
Bayonet detector can obtain fine-grained information at individual traveler level, but it is difficult to achieve full coverage of the road network. Aiming at this problem, from the perspective of missing trajectory reconstruction, the bayonet layout optimization method for individual vehicle travel detection was studied. Considering the missing situation between two adjacent bayonet detection sequences, the methods of first reconstruction and second reconstruction of missing trajectory were proposed. Based on the principle of primary reconstruction, the flow capture rate and track coverage rate were created to measure the monitoring scale of road traffic information by bayonet layout scheme. Based on the principle of secondary reconstruction, the missing trajectory dispersion was created to measure the reliability of trajectory reconstruction. A bayonet layout optimization model for individual vehicle travel detection was constructed by taking traffic capture rate, trajectory coverage as constraints, and maximizing the dispersion of missing tracks as the optimization objective of bayonet layout. Particle swarm optimization algorithm was used to solve the optimization model. Taking a regional road network in Haizhu, Guangzhou as an example, the new layout and the added layout were analyzed respectively. The results showed that: in the new layout scene, the optimized bayonet layout scheme increased the phase flow capture rate by 6.20%, the track coverage rate by 2.76%, and the dispersion of missing track by 139%, which obtained better results than the current scheme in terms of individual vehicle travel track detection and reconstruction. In the added layout scene, the optimization solution of added 1-6 bayonets were carried out successively, and the added positions and optimization results were obtained.
城市交通卡口布设粒子群算法(PSO)个体出行检测缺失轨迹离散度
urban trafficbayonet layoutparticle swarm optimization(PSO)individual travel detectiondispersion of missing trajectory
何胜学,孙晶晶,2016.解决路网检测器布局问题的数形结合方法[J].交通运输系统工程与信息,16(5):58-63.
刘畅,2015.浅谈视频监控点如何选点规划[J].大科技,2015(20):199.
刘明,吴育德,1993.基于交通量观测值推求的OD矩阵可靠度分析(1)[J].公路,1993(2):40-44.
逯峰,沙伟春,冯松青,等,2016.基于PGIS时空大数据的治安视频(卡口)空间选址模型研究[J].广东公安科技,24(2):1-6.
沈凌,陆建,冯怡,2021.城市道路监控设备布设方案评价方法研究[C]//面向高质量发展的空间治理:2021中国城市规划年会论文集.成都:中国建筑工业出版社:62-70.
谢一明,2022.城市交通大脑应用现状与业务体系研究[J].中国科技信息,11:136-138.
邢皓,谭世琦,张佐,等,2019.车辆轨迹重构方法综述[J].交通工程,19(4):20-28.
杨帅,于海洋,2016.基于卡口数据的车辆出行轨迹重构方法研究[C]//第十一届中国智能交通年会学术委员会.第十一届中国智能交通年会大会论文集.重庆:电子工业出版社:1355-1362.
杨晓光,刘斌,张晔,2011.城市道路网络OD估计模型及算法研究[J].同济大学学报(自然科学版),39(9):1292-1296.
邹志云,1997.可行合理路径及其在交通分配中的应用[J].武汉城市建设学院学报,1997(3):60-63.
DANCZY A,LIU H X,2011. A mixed-integer linear program for optimizing sensor locations along freeway corridors[J].Transp Res Part B,45(1): 208-217.
DANCZY A,DI X,LIU H X,2016. A probabilistic optimization model for allocating freeway sensors [J].Transp Res Part C,67: 378-398.
FENG H F, BAI F S, XU Y J,2019. Identification of critical roads in urban transportation network based on GPS trajectory data[J].Physica A,535:122337.
HAO F,WILLIAM H K L,HU S,et al,2022. Optimization of multi-type traffic sensor locations for estimation of multi-period origin-destination demands with covariance effects[J].Transp Res Part B,157:102555.
HE Y,MA X,LUO X,et al,2018. Vehicle traffic driven camera placement for better metropolis security surveillance[J].IEEE Intell Syst,33(4):49-61.
HU S R,PEETA S,CHU C H,2009. Identification of vehicle sensor locations for link-based network traffic applications[J].Transp Res Part B,43(8):873-894.
JENELIUS E,KOUTSOPOULO H N,2018. Urban network travel time prediction based on a probabilistic principal component analysis model of probe data [J]. IEEE T Intell Transp,19(2): 436-445.
KIM J,PARK B,LEE J,et al,2011. Determining optimal sensor locations in freeway using genetic algorithm-based optimization [J]. Eng Appl Artif Intel,24(2): 318-324.
SALARI M,KATTAN L,LAM W H K,et al,2019. Optimization of traffic sensor location for complete link flow observability in traffic network considering sensor failure[J].Transp Res Part B,121: 216-251.
XU X D,HONG K L,CHEN A,et al,2016. Robust network sensor location for complete link flow observability under uncertainty [J].Transp Res Part B,88:1-20.
YANG H, LIDA Y, SASAKI T,1991. An analysis of the reliability of an origin-destination trip matrix estimated from traffic counts[J].Transp Res Part B,25(5):351-363.
0
浏览量
3
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构