%0 Conference Paper %1 Li:2016:AGV:2983323.2983797 %A Li, Hengfeng %A Kulik, Lars %A Ramamohanarao, Kotagiri %B Proceedings of the 25th ACM International on Conference on Information and Knowledge Management %C New York, NY, USA %D 2016 %I ACM %K clustering mining spatial %P 1523--1532 %R 10.1145/2983323.2983797 %T Automatic Generation and Validation of Road Maps from GPS Trajectory Data Sets %U http://doi.acm.org/10.1145/2983323.2983797 %X With the popularity of mobile GPS devices such as on-board navigation systems and smart phones, users can contribute their GPS trajectory data for creating geo-volunteered road maps. However, the quality of these road maps cannot be guaranteed due to the lack of expertise among contributing users. Therefore, important challenges are (i) to automatically generate accurate roads from GPS traces and (ii) to validate the correctness of existing road maps. To address these challenges, we propose a novel Spatial-Linear Clustering (SLC) technique to infer road segments from GPS traces. In our algorithm, we propose the use of spatial-linear clusters to appropriately represent the linear nature of GPS points collected from the same road segment. Through inferring road segments our algorithm can detect missing roads and checking the correctness of existing road network. For our evaluation, we conduct extensive experiments that compare our method to the state-of-the-art methods on two real data sets. The experimental results show that the F1 score of our algorithm is on average 10.7% higher than the best state-of-the-art method. %@ 978-1-4503-4073-1

@inproceedings{Li:2016:AGV:2983323.2983797, abstract = {With the popularity of mobile GPS devices such as on-board navigation systems and smart phones, users can contribute their GPS trajectory data for creating geo-volunteered road maps. However, the quality of these road maps cannot be guaranteed due to the lack of expertise among contributing users. Therefore, important challenges are (i) to automatically generate accurate roads from GPS traces and (ii) to validate the correctness of existing road maps. To address these challenges, we propose a novel Spatial-Linear Clustering (SLC) technique to infer road segments from GPS traces. In our algorithm, we propose the use of spatial-linear clusters to appropriately represent the linear nature of GPS points collected from the same road segment. Through inferring road segments our algorithm can detect missing roads and checking the correctness of existing road network. For our evaluation, we conduct extensive experiments that compare our method to the state-of-the-art methods on two real data sets. The experimental results show that the F1 score of our algorithm is on average 10.7% higher than the best state-of-the-art method.}, acmid = {2983797}, added-at = {2016-12-07T15:31:05.000+0100}, address = {New York, NY, USA}, author = {Li, Hengfeng and Kulik, Lars and Ramamohanarao, Kotagiri}, biburl = {https://www.bibsonomy.org/bibtex/28d3bcd3dd89c94d57796db7befaa1040/ntempelmeier}, booktitle = {Proceedings of the 25th ACM International on Conference on Information and Knowledge Management}, description = {Automatic Generation and Validation of Road Maps from GPS Trajectory Data Sets}, doi = {10.1145/2983323.2983797}, interhash = {926b552d0be48566593b7423d13b16de}, intrahash = {8d3bcd3dd89c94d57796db7befaa1040}, isbn = {978-1-4503-4073-1}, keywords = {clustering mining spatial}, location = {Indianapolis, Indiana, USA}, numpages = {10}, pages = {1523--1532}, publisher = {ACM}, series = {CIKM '16}, timestamp = {2016-12-07T15:31:05.000+0100}, title = {Automatic Generation and Validation of Road Maps from GPS Trajectory Data Sets}, url = {http://doi.acm.org/10.1145/2983323.2983797}, year = 2016 }