Information acquisition method of three-dimensional intersection spatial structure based on vehicle GPS trajectory
-
摘要: 为了识别立体交叉口中不同的行驶规则, 利用随机森林特征选择方法分析了车辆轨迹数据特征, 按照重要性评分对特征进行聚类; 利用戴维森堡丁指数衡量聚类结果, 获得交叉口最优聚类结果下的各个行驶规则的聚类簇, 并构建聚类簇范围约束的狄洛尼三角网; 利用骨架线提取与公共序列合并方法, 提取立体交叉口的几何结构与拓扑连通关系, 获取城市立体交叉口空间结构信息; 以武汉市2016年出租车轨迹为数据源, 选取了武汉市城区立体交叉口进行空间结构信息获取试验。研究结果表明: 立体交叉口中车载GPS轨迹特征重要性评分的前4项依次是终点角度、起点角度、起终点角度差、中间角度平均值, 其中利用终点角度与起点角度特征组合的聚类结果是最优的; 立体交叉口空间结构信息获取方法在直行、左转、右转方向下识别准确率分别为85.7%、85.4%、87.5%, 综合准确率为86.2%, 直行、左转、右转方向下信息召回率分别为91.5%、87.2%、85.9%, 综合召回率为88.2%, 因此, 较高的准确率与召回率说明本文提出的方法可以准确识别立体交叉口空间结构信息, 并提取立体交叉口中各个行驶规则的几何与拓扑连通关系。Abstract: In order to identify different driving rules at the three-dimensional intersections, the features of vehicle trajectory data were analyzed by using random forest feature selection algorithm, and features were clustered according to the importance scores. The clustered results were measured by Davies-Bouldin index to obtain each driving rule cluster under the optimal clustering result, and Delaunay triangle network was constructed based on the cluster range. The skeleton line extraction and common sequence combination method were used to obtain the geometric structure and topological connectivity relationship of three-dimensional intersection. Finally, the spatial structure information of three-dimensional intersection was obtained. Taking the taxi trajectory data of Wuhan in 2016 as data source, the spatial structure information acquisition experiment of three-dimensional intersection in Wuhan was conduct. Analysis result shows that the top four items of vehicle GPS trajectory feature importance scores are the angle of ending point, the angle of starting point, the difference of starting and ending point angles, and the mean angle of middle points. The clustering result using the characteristics combination of terminal angle and starting angle is optimal. The recognition precision rates of the spatial structure information acquisition method in the directions of straight, left and right turning are 85.7%, 85.4%, and 87.5%, respectively, and the comprehensive precision rate is 86.2%. The information recall rates in the directions of straight, left and right turning are 91.5%, 87.2%, and 85.9%, respectively, and the comprehensive recall rate is 88.2%. The higher precision rates and recall rates indicate that the proposed method can accurately identify the spatial structure information and extract the geometric and topological connectivity relationship of driving rules at three-dimensional intersection.
-
图 11 特征组合A聚类结果的DBI曲线
Figure 11. DBI curves of clustering results under feature combination A
图 12 立体交叉口中不同行驶规则类簇
Figure 12. Clusters of different driving rules at three-dimensional intersections
图 14 立体交叉口信息提取结果
Figure 14. Information extraction results at three-dimensional intersections
表 1 特征组合
Table 1. Feature combinations
特征组合 起点角度 终点角度 起终点角度差 中间轨迹点平均角度 A √ √ × × B √ √ × √ C √ √ √ √ D √ √ √ × E × × √ √ 
下载: 导出CSV
表 2 行驶方向识别准确率与召回率
Table 2. Precision rates and recall rates in driving directions
行驶方向 正确识别个数 错误识别个数 漏识别个数 准确率/% 召回率/% 直行 54 9 5 85.7 91.5 左转 41 7 6 85.4 87.2 右转 49 7 8 87.5 85.9
下载: 导出CSV
-
[1] KONG Hui, AUDIBERT J Y, PONCE J. General road detection from a single image[J]. IEEE Transactions on Image Processing, 2010, 19(8): 2211-2220. doi: 10.1109/TIP.2010.2045715 [2] 李晓峰, 张树清, 韩富伟, 等. 基于多重信息融合的高分辨率遥感影像道路信息提取[J]. 测绘学报, 2008, 37(2): 178-184. doi: 10.3321/j.issn:1001-1595.2008.02.009LI Xiao-feng, ZHANG Shu-qing, HAN Fu-wei, et al. Road extraction from high-resolution remote sensing images based on multiple information fusion[J]. Acta Geodaetica et Cartographica Sinica, 2008, 37(2): 178-184. (in Chinese). doi: 10.3321/j.issn:1001-1595.2008.02.009 [3] 刘如意, 宋建锋, 权义宁, 等. 一种自动的高分辨率遥感影像道路提取方法[J]. 西安电子科技大学学报, 2017, 44(1): 100-105. https://www.cnki.com.cn/Article/CJFDTOTAL-XDKD201701018.htmLIU Ru-yi, SONG Jian-feng, QUAN Yi-ning, et al. Automatic road extraction method for high-resolution remote sensing images[J]. Journal of Xidian University, 2017, 44(1): 100-105. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-XDKD201701018.htm [4] 谢明鸿, 宋纳. 一种高分辨率遥感影像道路提取方法[J]. 四川大学学报(自然科学版), 2017, 54(1): 81-88. https://www.cnki.com.cn/Article/CJFDTOTAL-SCDX201701014.htmXIE Ming-hong, SONG Na. A method for road extraction from high resolution remote sensing image[J]. Journal of Sichuan University (Natural Science Edition), 2017, 54(1): 81-88. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-SCDX201701014.htm [5] AYCARD O, BAIG Q, BOTA S, et al. Intersection safety using lidar and stereo vision sensors[C]//IEEE. 2011 IEEE Intelligent Vehicles Symposium. New York: IEEE, 2011: 863-869. [6] LINDNER P, RICHTER E, WANIELIK G, et al. Multi-channel lidar processing for lane detection and estimation[C]//IEEE. 2009 12th International IEEE Conference on Intelligent Transportation Systems. New York: IEEE, 2009: 202-207. [7] MAAREF M, KHALIFE J, KASSAS Z M. Lane-level localization and mapping in GNSS-challenged environments by fusing LiDAR data and cellular pseudoranges[J]. IEEE Transactions on Intelligent Vehicles, 2018, 4(1): 73-89. [8] 贺勇, 路昊, 王春香, 等. 基于多传感器的车道级高精细地图制作方法[J]. 长安大学学报(自然科学版), 2015, 35(增): 274-278. https://www.cnki.com.cn/Article/CJFDTOTAL-XAGL2015S1058.htmHE Yong, LU Hao, WANG Chun-xiang, et al. Generation of precise lane-level maps based on multi-sensors[J]. Journal of Chang'an University (Natural Science Edition), 2015, 35(S): 274-278. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-XAGL2015S1058.htm [9] UDUWARAGODA E R I A C M, PERERA A S, DIAS S A D. Generating lane level road data from vehicle trajectories using kernel density estimation[C]//IEEE. 16th International IEEE Conference on Intelligent Transportation Systems: Intelligent Transportation Systems for All Modes. New York: IEEE, 2013: 384-391. [10] 唐炉亮, 牛乐, 杨雪, 等. 利用轨迹大数据进行城市道路交叉口识别及结构提取[J]. 测绘学报, 2017, 46(6): 770-779. https://www.cnki.com.cn/Article/CJFDTOTAL-CHXB201706015.htmTANG Lu-liang, NIU Le, YANG Xue, et al. Urban intersection recognition and construction based on big trace data[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(6): 770-779. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-CHXB201706015.htm [11] BAR HILLEL A, LERNER R, LEVI D, et al. Recent progress in road and lane detection: a survey[J]. Machine Vision and Applications, 2014, 25(3): 727-745. doi: 10.1007/s00138-011-0404-2 [12] 蔡红玥, 姚国清. 高分辨率遥感图像道路交叉口自动提取[J]. 国土资源遥感, 2016, 28(1): 63-71. https://www.cnki.com.cn/Article/CJFDTOTAL-GTYG201601011.htmCAI Hong-yue, YAO Guo-qing. Auto-extraction of road intersection from high resolution remote sensing image[J]. Remote Sensing for Land and Resource, 2016, 28(1): 63-71. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-GTYG201601011.htm [13] 曹闻, 李润生. 利用可变形部件模型检测遥感影像道路交叉口[J]. 武汉大学学报·信息科学版, 2018, 43(3): 413-419. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201803013.htmCAO Wen, LI Run-sheng. Road intersections detection using deformable part models on remote sensing image[J]. Geomatics and Information Science of Wuhan University, 2018, 43(3): 413-419. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201803013.htm [14] ZHU Quan-wen, CHEN Long, LI Qing-quan, et al. 3D LiDAR point cloud based intersection recognition for autonomous driving[C]//IEEE. 2012 IEEE Intelligent Vehicles Symposium. New York: IEEE, 2012: 456-461. [15] 陈卓, 马洪超. 基于机载LiDAR数据的大型立交桥自动提取与建模方法[J]. 测绘学报, 2012, 41(2): 252-258. https://www.cnki.com.cn/Article/CJFDTOTAL-CHXB201202018.htmCHEN Zhuo, MA Hong-chao. Automatic extracting and modeling approach of city cloverleaf from airborne LiDAR Data[J]. Acta Geodaetica et Cartographica Sinica, 2012, 41(2): 252-258. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-CHXB201202018.htm [16] FATHI A, KRUMM J. Detecting road intersections from GPS traces[C]∥Springer. International Conference on Geographic Information Science. Berlin: Springer, 2010: 56-69. [17] XIE Xing-zhe, LIAO Wen-zhi, AGHAJAN H, et al. Detecting road intersections from GPS traces using longest common subsequence algorithm[J]. International Journal of Geo-Information, 2017, 6(1): 1-15. [18] WANG Jing, WANG Chao-liang, SONG Xian-feng, et al. Automatic intersection and traffic rule detection by mining motor-vehicle GPS trajectories[J]. Computers, Environment and Urban Systems, 2017, 64: 19-29. doi: 10.1016/j.compenvurbsys.2016.12.006 [19] YANG Xue, TANG Lu-liang, NIU Le, et al. Generating lane-based intersection maps from crowdsourcing big trace data[J]. Transportation Research Part C: Emerging Technologies, 2018, 89: 168-187. doi: 10.1016/j.trc.2018.02.007 [20] WANG Jing, RUI Xiao-ping, SONG Xian-feng, et al. A novel approach for generating routable road maps from vehicle GPS traces[J]. International Journal of Geographical Information Science, 2015, 29(1): 69-91. doi: 10.1080/13658816.2014.944527 [21] 姚登举, 杨静, 詹晓娟. 基于随机森林的特征选择算法[J]. 吉林大学学报(工学版), 2014, 44(1): 137-141. https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY201401024.htmYAO Deng-ju, YANG Jing, ZHAN Xiao-juan. Feature selection algorithm based on random forest[J]. Journal of Jilin University (Engineering and Technology Edition), 2014, 44(1): 137-141. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY201401024.htm [22] 丁姝郁. 一种基于DBI-PD聚类算法的异常检测机制[J]. 电脑开发与应用, 2015(2): 24-26, 30. doi: 10.3969/j.issn.1003-5850.2015.02.008DING Shu-yu. An anomaly detection scheme based on DBI-PD clustering algorithm[J]. Computer Development and Applications, 2015(2): 24-26, 30. (in Chinese). doi: 10.3969/j.issn.1003-5850.2015.02.008 [23] 陈涛, 艾廷华. 多边形骨架线与形心自动搜寻算法研究[J]. 武汉大学学报: 信息科学版, 2004, 29(5): 443-446, 455. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH200405014.htmCHEN Tao, AI Ting-hua. Automatic extraction of skeleton and center of area feature[J]. Geomatics and Information Science of Wuhan University, 2004, 29(5): 443-446, 455. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH200405014.htm [24] 唐炉亮, 杨雪, 靳晨, 等. 基于约束高斯混合模型的车道信息获取[J]. 武汉大学学报(信息科学版), 2017, 42(3): 341-347. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201703010.htmTANG Lu-liang, YANG Xue, JIN Chen, et al. Traffic lane number extraction based on the constrained Gaussian mixture model[J]. Geomatics and Information Science of Wuhan University, 2017, 42(3): 341-347. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201703010.htm [25] GROSS F, JORDAN J, WENINGER F, et al. Route and stopping intent prediction at intersections from car fleet data[J]. IEEE Transactions on Intelligent Vehicles, 2016, 1(2): 177-186. doi: 10.1109/TIV.2016.2617625 [26] 付鑫, 杨宇, 孙皓. 出租汽车出行轨迹网络结构复杂性与空间分异特征[J]. 交通运输工程学报, 2017, 17(2): 106-116. http://transport.chd.edu.cn/article/id/201702012FU Xin, YANG Yu, SUN Hao. Structural complexity and spatial differentiation characteristics of taxi trip trajectory network[J]. Journal of Traffic and Transportation Engineering, 2017, 17(2): 106-116. (in Chinese). http://transport.chd.edu.cn/article/id/201702012 [27] HUANG Jin-cai, DENG Min, ZHANG Yun-fei, et al. Complex road intersection modelling based on low-frequency GPS track data[C]//ISPRS. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Amsterdam: ISPRS, 2017: 23-28. [28] FLÖTTERÖD G, ROHDE J. Operational macroscopic modeling of complex urban road intersections[J]. Transportation Research Part B: Methodological, 2011, 45(6): 903-922. [29] 袁冠, 夏士雄, 张磊, 等. 基于结构相似度的轨迹聚类算法[J]. 通信学报, 2011, 32(9): 103-110. https://www.cnki.com.cn/Article/CJFDTOTAL-TXXB201109016.htmYUAN Guan, XIA Shi-xiong, ZHANG Lei, et al. Trajectory clustering algorithm based on structural similarity[J]. Journal on Communications, 2011, 32(9): 103-110. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-TXXB201109016.htm [30] 石陆魁, 张延茹, 张欣. 基于时空模式的轨迹数据聚类算法[J]. 计算机应用, 2017, 37(3): 854-859, 895. https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201703044.htmSHI Lu-kui, ZHANG Yan-ru, ZHANG Xin. Trajectory data clustering algorithm based on spatio-temporal pattern[J]. Journal of Computer Applications, 2017, 37(3): 854-859, 895. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JSJY201703044.htm -
点击查看大图
图(14) / 表(2)
计量
- 文章访问数: 1047
- HTML全文浏览量: 99
- PDF下载量: 704
- 被引次数: 0
