ABSTRACT
Map construction from vehicle trajectories has been an active challenge topic due to the progress of positioning technologies and high cost of map constructions since last decades. In our work, we focus on road network generation from a massive GPS data collected from a large number of vehicles, particularly the detection of intersections which provide the connectivity information of road network. Among several methods to detect intersections, image processing, observing the distribution of GPS points, and finding the behavioral characteristics of trajectories have been widely studied. However, actual roads are in three-dimensional space and there are overpass or underpass roads that can be falsely detected as intersections. In order to solve this problem, we extend our previous algorithm, Virtual Run [16] to the Bidirectional Virtual Run algorithm to detect the split point among roads. Moreover, by reversing the Virtual Run algorithm, this new algorithm can find the joining point of roads. For the evaluation, we used about 2000 actual vehicle trajectories gathered up with taxies in three metropolitan cities - Seoul, Pusan, and Sungnam in Korea.
- M. Aanjaneya, F. Chazal, D. Chen, M. Glisse, L. Guibas, and D. Morozov. Metric graph reconstruction from noisy data. Int. J. of Computational Geometry & Applications, 22(04):305--325, 2012.Google ScholarCross Ref
- G. Agamennoni, J. I. Nieto, and E. M. Nebot. Robust inference of principal road paths for intelligent transportation systems. IEEE Trans. on Intelligent Transportation Systems, 12(1):298--308, 2011. Google ScholarDigital Library
- M. Ahmed, S. Karagiorgou, D. Pfoser, and C. Wenk. A comparison and evaluation of map construction algorithms using vehicle tracking data. Geoinformatica, 19(3):601--632, 2015. Google ScholarDigital Library
- M. Ahmed and C. Wenk. Constructing street networks from gps trajectories. In European Symposium on Algorithms, pages 60--71, 2012. Google ScholarDigital Library
- J. Biagioni and J. Eriksson. Map inference in the face of noise and disparity. In Proc. of the 20th Int. Conf. on Advances in Geographic Information Systems, pages 79--88. Google ScholarDigital Library
- L. Cao and J. Krumm. From gps traces to a routable road map. In Proc. of the 17th ACM SIGSPATIAL Int. Conf. on Advances in Geographic Information Systems, pages 3--12, 2009. Google ScholarDigital Library
- D. Chen, L. J. Guibas, J. Hershberger, and J. Sun. Road network reconstruction for organizing paths. In Proc. of the 21th annual ACM-SIAM SODA, pages 1309--1320, 2010. Google ScholarDigital Library
- H.-G. Cho, W. Evans, N. Saeedi, and C. su Shin. Covering points with convex sets of minimum size. In Proc. of WALCOM 2016, pages 116--178, 2016.Google ScholarCross Ref
- S. Edelkamp and S. Schrödl. Route planning and map inference with global positioning traces. In Computer Science in Perspective, pages 128--151. 2003. Google ScholarDigital Library
- A. Fathi and J. Krumm. Detecting road intersections from gps traces. In Proc. of the 6th Int. Conf. on Geographic Information Science, pages 56--69, 2010. Google ScholarDigital Library
- J. Hu, A. Razdan, J. C. Femiani, M. Cui, and P. Wonka. Road network extraction and intersection detection from aerial images by tracking road footprints. IEEE Transactions on Geoscience and Remote Sensing, 45(12):4144--4157, 2007.Google ScholarCross Ref
- S. Karagiorgou and D. Pfoser. On vehicle tracking data-based road network generation. In Proc. of the 20th Int. Conf. on advances in geographic information systems, pages 89--98, 2012. Google ScholarDigital Library
- X. Liu, J. Biagioni, J. Eriksson, Y. Wang, G. Forman, and Y. Zhu. Mining large-scale, sparse gps traces for map inference: comparison of approaches. In Proc. of the 18th ACM SIGKDD, pages 669--677, 2012. Google ScholarDigital Library
- B. Park, S.-H. Kim, T. Kim, J. Park, and H.-G. Cho. Virtual running of gps vehicles for trajectory analysis. In Proc. of the 10th Int. Conf. on Ubiquitous Information Management and Communication, number 79, pages 1--8, 2016. Google ScholarDigital Library
- B. Park, J. Park, T. Kim, and H.-G. Cho. Detecting road intersections using partially similar trajectories of moving objects. J. of KIISE, 43(4):404--410, 2016.Google ScholarCross Ref
- J. Park, T. Kim, B. Park, and H.-G. Cho. Virtual running of vehicle trajectories for automatic map generation. In Proc. of the 31st Ann. ACM SAC, pages 572--579, 2016. Google ScholarDigital Library
- W. Shi, S. Shen, and Y. Liu. Automatic generation of road network map from massive gps, vehicle trajectories. In 2009 12th Int. IEEE Conf. on Intelligent Transportation Systems, pages 1--6, 2009.Google ScholarCross Ref
- J. Wu, Y. Zhu, T. Ku, and L. Wang. Detecting road intersections from coarse-gained gps traces based on clustering. J. of Computers, 8(11):2959--2965, 2013.Google ScholarCross Ref
Index Terms
- Virtual running model for locating road intersections using GPS trajectory data
Recommendations
Detecting road intersections from GPS traces
GIScience'10: Proceedings of the 6th international conference on Geographic information scienceAs an alternative to expensive road surveys, we are working toward a method to infer the road network from GPS data logged from regular vehicles. One of the most important components of this problem is to find road intersections. We introduce an ...
Evaluating eco-driving advice using GPS/CANBus data
SIGSPATIAL'13: Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information SystemsVehicles in the US use approximately 1.4 billion liters of fuel a day. This number can be reduced by driving more fuel efficiently. Several sources provide fuel saving eco-driving advice, but the advices are often quite abstract. This paper uses a large ...
Road Map Generation and Feature Extraction from GPS Trajectories Data
IWCTS'19: Proceedings of the 12th ACM SIGSPATIAL International Workshop on Computational Transportation ScienceRoad maps are important in our personal lives and are widely used in many different applications. Therefore, an up-to-date road map is essential. The huge amount of GPS data collected from moving objects provides an opportunity to generate an up-to-date ...
Comments