|Table of Contents|

Study on Road Speed Limit Identification Taking into Account High and Low Speed Information(PDF)

《南京师大学报（自然科学版）》[ISSN:1001-4616/CN:32-1239/N]

Issue:
2024年04期
Page:
31-38
Research Field:
空间数据智能研究
Publishing date:

Info

Title:
Study on Road Speed Limit Identification Taking into Account High and Low Speed Information
Author(s):
Zhang Caili1; Xiang Longgang2; Li Yali3
(1.School of Surveying and Urban Spatial Information,Henan University of Urban Construction,Pingdingshan 467000,China)
(2.State Key Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,Wuhan 430079,China)
(3.School of Transportation and Geomatics Engineering,Shenyang Jianzhu University,Shenyang 110000,China)
Keywords:
vehicle trajectories; road network information; adjacent sections; high and low speed information; road speed limit identification
PACS:
P208
DOI:
10.3969/j.issn.1001-4616.2024.04.004
Abstract:
With the demand of emerging industries for map detail richness and element completeness,it is a general trend to carry out research on the construction of fine navigable road networks. However,road information mining based on trajectory data focuses more on the identification of road network skeletons and less on the identification of road speed limit information. Considering the difference between the trajectory running speed distribution of the low speed and high speed sections,this paper models the high speed and low speed sections separately based on the trajectory data,and carries out the speed limit identification optimization of the trajectory data. Then on this basis,the speed limit identification results based on road network are fused to complete the identification of speed limit information. Experiments are carried out taking the Second Ring Road area of Wuhan City and Chengdu City as examples to verify the effectiveness of the method. Experimental results show that:(1)the separate modeling of high and low speed information significantly improves the speed limit recognition accuracy based on trajectories;(2)the integration of speed limit recognition optimization results based on trajectories with speed limit recognition results based on road network also further improves the speed limit recognition results.

References:

[1]LI J,QIN Q M,HAN J W,et al. Mining trajectory data and geotagged data in social media for road map inference[J]. Transactions in GIS,2015,19(1):1-18.
[2]LILLO-CASTELLANO J M,MORA-JIMÉNEZ I,FIGUERA-POZUELO C,et al. Traffic sign segmentation and classification using statistical learning methods[J]. Neurocomputing,2015,153:286-299.
[3]杨航,张鑫淼,杨冲. 基于卷积神经网络的公路限速牌识别方法[J]. 地理空间信息,2016,14(1):31-33.
[4]王进,任小龙,孙开伟,等. HSV颜色空间下用演化超网络识别道路限速标志的研究[J]. 高技术通讯,2013,23(7):679-684.
[5]刘祥敏. 普通公路限速影响因素与预测模型研究[D]. 济南:山东建筑大学,2020.
[6]宋博. 考虑环境影响的高速公路限速值研究[D]. 西安:长安大学,2018.
[7]GARBER N J,GADIRAJU R. Factors affecting speed variance and its influence on accidents[J]. Transportation research record,1989,1213(1213):64-71.
[8]孙付勇. 基于神经网络的道路通行时间预估方法的设计与实现[D]. 北京:北京交通大学,2019.
[9]唐炉亮,杨雪,任畅,等. 轨迹大数据挖掘与高时空精度道路众包测图[M]. 北京:科学出版社,2019.
[10]张彩丽,向隆刚,李雅丽,等. 基于出租车轨迹的可导航路网构建[J]. 测绘学报,2021,50(12):1650-1662.
[11]廖律超,蒋新华,林铭榛,等. 基于交通轨迹数据挖掘的道路限速信息识别方法[J]. 交通运输工程学报,2015,15(5):118-126.
[12]WINDEN K V,BILJECKI F,STEFAN V D S. Automatic update of road attributes by mining GPS tracks[J]. Transactions in GIS,2016,20(5):664-683.
[13]张彩丽,向隆刚,李雅丽,等. 路段级导航属性信息挖掘[J]. 测绘学报,2024,3(2):367-378.
[14]FERNÁNDEZ-DELGADO M,CERNADAS E,BARRO S,et al. Do we need hundreds of classifiers to solve real world classification problems?[J]. The journal of machine learning research,2014,15(1):3133-3181.
[15]肖湘文,沈校熠,柯长青,等. 基于Sentinel-1A数据的多种机器学习算法识别冰山的比较[J]. 测绘学报,2020,49(4):111-123.
[16]张彩丽,向隆刚,李雅丽,等. 顾及路网与轨迹多模特征的道路等级分类研究[J]. 地球信息科学学报,2022,24(10):1925-1940.
[17]全国交通工程设施(公路)标准化技术委员会.道路交通标志和标线第5部分:限制速度:GB 5768.5—2017[S]. 北京:中国标准出版社,2017.
[18]周志华. 机器学习[M]. 北京:清华大学出版社,2016.
[19]XU Y Y,XIE Z,WU L,et al. Multilane roads extracted from the OpenStreetMap urban road network using random forests[J]. Transactions in GIS,2019,23(2):224-240.

Memo

Memo:
-
Last Update: 2024-12-15