Pedestrian road network extraction based on crowdsourcing trajectory data

doi:10.13474/j.cnki.11-2246.2021.0080

Abstract

Abstract: At present, the routes provided by the navigation location service application are mostly based on the data of the vehicle road network, which is difficult to meet the needs of pedestrian navigation. The complete pedestrian network has become an important factor restricting the application of pedestrian navigation. Therefore, this paper proposes a pedestrian network extraction method based on Morse theory. First, the trajectory is preprocessed to remove redundancy and noise in the trajectory data, and the original trajectory is divided reasonably to form a clear trajectory set. Secondly, Morse theory is used to extract the "ridgeline" in the density map of walking track and reconstruct the pedestrian network. The experimental analysis uses the walking GPS track data of Shenzhen university campus to extract the pedestrian network. By qualitative and quantitative comparison of the extracted pedestrian network results with OpenStreetMap (OSM) data, the effectiveness of the method in this paper is verified. At the same time, compared with the current typical road network extraction methods, the proposed method can extract high quality pedestrian network.

Key words: road extraction, walking trajectory, trajectory preprocessing, pedestrian network, Morse theory

CLC Number:

P228

ZHENG Tianjing, HUANG Jincai, ZHOU Baoding, ZHANG Dejin. Pedestrian road network extraction based on crowdsourcing trajectory data[J]. Bulletin of Surveying and Mapping, 2021, 0(3): 69-74.

References

[1] KUNTZSCH C, SESTER M, BRENNER C. Generative models for road network reconstruction[J]. International Journal of Geographical Information Science, 2016, 30(5):1012-1039.
[2] 王振华,胡翔云,单杰.众源GPS浮动车数据中城市道路中心线分级提取的栅格化方法[J].测绘通报,2015(8):22-24.
[3] CAO L, KRUMM J. From GPS traces to a routable road map[C]//Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Seattle, Washington:Association for Computing Machinery, 2009:3-12.
[4] ZHANG L, THIEMANN F, SESTER M. Integration of GPS traces with road map[C]//Proceedings of the 3rd International Workshop on Computational Transportation Science. San Jose, California:Association for Computing Machinery, 2010:17-22.
[5] 杨伟, 艾廷华. 基于众源轨迹数据的道路中心线提取[J]. 地理与地理信息科学, 2016, 32(3):1-7.
[6] WANG J, RUI X, SONG X, 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.
[7] 周宝定, 李清泉, 毛庆洲, 等. 用户行为感知辅助的室内行人定位[J]. 武汉大学学报(信息科学版), 2014, 39(6):719-723.
[8] 李清泉, 周宝定, 马威, 等. GIS辅助的室内定位技术研究进展[J]. 测绘学报, 2019, 48(12):1498-1506.
[9] HOLONE H, MISUND G, HOLMSTEDT H. Users are doing it for themselves:pedestrian navigation with user generated content[C]//Proceedings of the International Conference on Next Generation Mobile Applications, Services and Technologies.[S.l.]:IEEE Computer Society, 2007:91-99.
[10] GAISBAUER C, FRANK A. Wayfinding model for pedestrian navigation[C]//Proceedings of the 11th AGILE International Conference on Geographic Information Science. Barcelona:University of Girona, 2008.
[11] HOLONE H, MISUND G. People helping computers helping people:navigation for people with mobility problems by sharing accessibility annotations[C]//Proceedings of International Conference, on Computers Helping People with Special Needs. Linz:DBLP, 2008.
[12] KASEMSUPPAKORN P, KARIMI H A. Pedestrian network data collection through location-based social networks[C]//Proceedings of the 5th International Conference on Collaborative Computing:Networking, Applications and Worksharing.[S.l.]:IEEE, 2009.
[13] NEIS P, ZIELSTRA D. Recent developments and future trends in volunteered geographic information research:the case of OpenStreetMap[J]. Future Internet, 2014, 6(1):76-106.
[14] NAUMANN S, KOVALYOV M Y. Pedestrian route search based on OpenStreetMap[M]//SIERPINSKI G. Intelligent transport systems and travel behaviour.[S.l.]:Springer. 2017:87-96.
[15] HASHEMI M. A testbed for evaluating network construction algorithms from GPS traces[J]. Computers, Environment and Urban Systems, 2017, 66:96-109.
[16] HASHEMI M. Automatic inference of road and pedestrian networks from spatial-temporal trajectories[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 99:1-17.
[17] WANG S, WANG Y, LI Y. Efficient map reconstruction and augmentation via topological methods[C]//Proceedings of Sigspatial International Conference on Advances in Geographic Information Systems.[S.l.]:ACM, 2015.
[18] 张春亢, 赵学胜, 王洪斌. 采用Morse理论的小尺度地形特征提取方法[J]. 测绘科学技术学报, 2015,32(3):266-270.
[19] 张春亢. 基于Morse理论的三角网格特征提取及简化研究[D].北京:中国矿业大学(北京),2016.
[20] EDELSBRUNNER H, LETSCHER D, ZOMORODIAN A. Topological Persistence and Simplification[J]. Discrete & Computational Geometry, 2002, 28(4):511-533.
[21] AHMED M, WENK C. Constructing street networks from GPS trajectories[C]//Proceedings of the 20th Annual European conference on Algorithms.[S.l.]:Springer, 2012.
[22] KARAGIORGOU S, PFOSER D. On vehicle tracking data-based road network generation[C]//Proceedings of the 20th International Conference on Advances in Geographic Information Systems. Redondo Beach, California:Association for Computing Machinery, 2012:89-98.