面向骑行地图推断的轨迹数据质量提升方法

doi:10.3969/j.issn.1000-5641.2023.06.002

摘要/Abstract

摘要：

由于定位设备误差、非机动车骑行习惯等因素的影响, 骑行轨迹存在数据异常与定位信息缺失等质量问题, 为骑行地图推断和骑行路径规划等基于轨迹的应用带来了极大挑战. 为解决上述问题, 提出了一个面向骑行地图推断的轨迹数据质量提升框架, 包括网格索引构建、异常轨迹点的消除、徘徊轨迹段的消除、违章轨迹段的消除、漂移轨迹段的校准以及缺失轨迹的恢复等. 在真实非机动车骑行轨迹数据集上进行了对比实验和消融实验, 实验结果验证了所提方案对于提升骑行地图推断的精度优于现有方法.

关键词: 徘徊轨迹, 漂移轨迹, 轨迹恢复

Abstract:

The trajectory optimization of cycling is hindered by the errors of positioning equipment, riding habits of non-motor vehicles, and other factors. It leads to quality problems, such as abnormal data and missing positioning information in the riding trajectory, impacting the application of trajectory-based riding-map inference and riding-path planning. To solve these problems, this paper creates a framework for improving the quality of cycling-trajectory data, based on the construction of a grid index, screening of abnormal trajectory points, elimination of wandering trajectory segments, elimination of illegal trajectory segments, calibration of drift trajectory segments, and recovery of missing trajectory. Comparative and ablation experiments are conducted by using a real non-motor-vehicle cycling-trajectory dataset. The experimental results verify that the proposed method improves the accuracy of cycling-map inference.

Key words: wandering trajectory, drift trajectory, trajectory recovery

中图分类号:

TP311.5

陈杰, 沈文怡, 吴问宇, 毛嘉莉. 面向骑行地图推断的轨迹数据质量提升方法[J]. 华东师范大学学报（自然科学版）, 2023, 2023(6): 14-27.

Jie CHEN, Wenyi SHEN, Wenyu WU, Jiali MAO. Method for improving the quality of trajectory data for riding-map inference[J]. Journal of East China Normal University(Natural Science), 2023, 2023(6): 14-27.

图/表 13

图1

图2

图3

图4

图5

图6

图7

表1

图8

表2

表3

图9

表4

参考文献 18

1	SHAN Z Q, WU H, SUN W W, et al. COBWEB: A robust map update system using GPS trajectories [C]// Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. 2015: 927-937.
2	CHAO P F, HUA W, ZHOU X F.. Trajectories know where map is wrong: An iterative framework for map-trajectory co-optimisation. World Wide Web, 2020, 23, 47- 73.
3	CHAO P F, HUA W, ZHOU X F. An iterative map-trajectory co-optimisation framework based on map-matching and map update [C]// Database Systems for Advanced Applications. 2019: 305-309.
4	ZHAO L S, MAO J L, PU M, et al. Automatic calibration of road intersection topology using trajectories [C]// 2020 IEEE 36th International Conference on Data Engineering. 2020: 1633-1644.
5	QING R T, LIU Y Z, ZHAO Y J, et al. Using feature interaction among GPS data for road intersection detection [C]// Proceedings of the 2nd International Workshop on Human-centric Multimedia Analysis. 2021: 31-37.
6	HE L, NIU X Z, CHEN T, et al. Spatio-temporal trajectory anomaly detection based on common sub-sequence [J]. Applied Intelligence, 2022, 52: 7599-7621.
7	CAO L L, KRUMM J. From GPS traces to a routable road map [C]// Proceedings of the ACM International Symposium on Advances in Geographic Information Systems. 2009: 3-12.
8	CHEN C, LU C W, HUANG Q X, et al. City-scale map creation and updating using GPS collections [C]// Knowledge Discovery and Data Mining. 2016: 1465-1474.
9	SCHROEDL S, WAGGSTAFF K, ROGERS S, et al. Mining GPS traces for map refinement [J]. Data Mining and Knowledge Discovery, 2004, 9: 59-87.
10	HOTEIT S, SECCI S, SOBOLEVSKY S, et al. Estimating human trajectories and hotspots through mobile phone data [J]. Computer Networks, 2014, 64: 296-307.
11	CHEN Z B, SHEN H T, ZHOU X F. Discovering popular routes from trajectories [C]// 2011 IEEE 27th International Conference on Data Engineering. 2011: 900-911.
12	WEI L Y, ZHENG Y, PENG W C. Constructing popular routes from uncertain trajectories[C]// Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2012: 195-203.
13	SU H, ZHENG K, HUANG J M, et al. Calibrating trajectory data for spatio-temporal similarity analysis [J]. The International Journal on Very Large Data Bases, 2015, 24: 93-116.
14	WANG J Y, WU N, LU X X, et al.. Deep trajectory recovery with fine-grained calibration using Kalman Filter. IEEE Transactions on Knowledge and Data Engineering, 2021, 33 (3): 921- 934.
15	CHAO P F, HUA W, MAO R, et al. A survey and quantitative study on map inference algorithms from GPS trajectories [J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(1): 15-28.
16	LI H F, KULIK L, RAMAMOHANARAO K. Automatic generation and validation of road maps from GPS trajectory data sets [C]// Proceedings of the 25th ACM International on Conference on Information and Knowledge Management. 2016: 1523-1532.
17	HUANG Y R, XIAO Z, YU X Y, et al. Road network construction with complex intersections based on sparsely sampled private car trajectory data [J]. ACM Transactions on Knowledge Discovery from Data, 2019, 13(3): 35.
18	LYU H Y, PFOSER D, SHENG Y H. Movement-aware map construction [J]. International Journal of Geographical Information Science, 2021, 35(6): 1065-1093.

类别	$n_{\rm{P}} $	$n_{\rm{R}} $	$F_1 $
CITT	0.092	0.478	0.155
CITT + proposed	0.134	0.486	0.212
Huang19	0.161	0.363	0.223
Huang19 + proposed	0.316	0.374	0.343

类别	$n_{\rm{P}} $	$n_{\rm{R}} $	$F_1 $
无数据质量提升	0.161	0.363	0.223
不包含数据质量提升	0.316	0.374	0.343
不包含异常轨迹点消除	0.276	0.374	0.318
不包含仅徘徊轨迹段消除	0.252	0.365	0.298
不包含违章轨迹段消除	0.279	0.374	0.320
不包含漂移轨迹段校准	0.308	0.373	0.337
仅缺失轨迹段恢复	0.310	0.372	0.338

类别	$ {C}_{{\rm{MP}}} $	$ {A}_{{\rm{L}}} $	$ {A}_{{\rm{N}}} $
SLC	0.538	0.122	0.387
SLC + proposed	0.837	0.184	0.6
Cao09	0.217	0.210	0.161
Cao09 + proposed	0.308	0.336	0.231

类别	$ {C}_{{\rm{MP}}} $	$ {A}_{{\rm{L}}} $	$ {A}_{{\rm{N}}} $
无数据质量提升	0.217	0.210	0.161
数据质量提升	0.308	0.336	0.231
不包含异常轨迹点消除	0.294	0.321	0.218
不包含徘徊轨迹段消除	0.273	0.289	0.202
不包含违章轨迹段消除	0.282	0.299	0.214
不包含漂移轨迹段校准	0.301	0.325	0.226
不包含缺失轨迹段恢复	0.299	0.321	0.225

[1]	郁毅明, 洪语晨, 王晔, 董启文. 化工材料配方的实验数据治理模块设计[J]. 华东师范大学学报（自然科学版）, 2022, 2022(5): 1-13.
[2]	孙晴, 梁冠宇, 武延军, 武斌, 田春岐, 王伟. 数据驱动的开源软件供应链可维护性风险分析方法[J]. 华东师范大学学报（自然科学版）, 2022, 2022(5): 90-99.
[3]	龚鑫, 徐立华, 窦亮, 赵瑞祥. 金融科技软件自动化测试用例的冗余评价和削减方法[J]. 华东师范大学学报（自然科学版）, 2022, 2022(4): 43-55.
[4]	纪宇, 何一璇, 吴国群, 吴敏. 基于Prony-like方法的第一类贝塞尔函数逼近[J]. 华东师范大学学报(自然科学版), 2019, 2019(6): 42-60.
[5]	张涛, 张小磊, 李宇明, 张春熙, 张蓉. Woodpecker+:基于数据特征的自定义负载性能评测[J]. 华东师范大学学报(自然科学版), 2019, 2019(5): 190-202.
[6]	张衡, 陈良育. Levenshtein算法优化及在题库判重中的应用[J]. 华东师范大学学报(自然科学版), 2018, 2018(5): 154-163.
[7]	李捷荧, 李宇明, 张小磊, 张蓉. Woodpecker:支持细粒度冲突模拟的数据库测试框架[J]. 华东师范大学学报(自然科学版), 2018, 2018(2): 77-88.
[8]	杨乐, 柳银萍, 李志斌. Emathema：在线的方程自动求解平台[J]. 华东师范大学学报(自然科学版), 2017, (3): 20-28.
[9]	赵大鹏,梁磊,田秀霞,王晓玲. LBS的隐私保护：模型与进展[J]. 华东师范大学学报(自然科学版), 2015, 2015(5): 28-45.
[10]	韩文文;王玲;陈优广 . 基于亚像素文本图像的分割算法 [J]. 华东师范大学学报(自然科学版), 2007, 2007(3): 100-106.
[11]	顾星晔;王琦;过仲阳;吴健平. 地理数据多边形动态显示的方法研究(简报)[J]. 华东师范大学学报(自然科学版), 2007, 2007(2): 122-125.
[12]	王远飞;陆涛;宓伟杰;朱海燕;邵德民;鲁小琴;冯泾贤. 基于GIS技术的热带气旋信息系统设计与实现(简报)[J]. 华东师范大学学报(自然科学版), 2006, 2006(4): 137-140.
[13]	王远飞;周枫;刘志强;宓伟杰;陆涛;丁金宏. 浦东新区人口普查地理信息系统的设计与实现[J]. 华东师范大学学报(自然科学版), 2006, 2006(2): 27-32.
[14]	张圣希;张薇;李国强;顾国庆. 利用顶点链编码探测表格的斜率[J]. 华东师范大学学报(自然科学版), 2004, 2004(3): 54-58.