Name
Abstract | ||
|---|---|---|
Extracting road network information including lane boundaries, lane centerlines, junctions and their relationship from AIS data plays an important role in location based services, urban computing and intelligent transportation systems, etc. However, AIS data are large scale, high noisy, the density and quality are very uneven in different areas, extracting a whole, continuous and smooth maritime road network with rich information from such data is a challenging problem. To address these issues, this paper proposes an adaptive maritime road network extraction approach that can extract both lane boundaries and centerlines for a large sea area from AIS data. Based on a road network definition including nodes, segments and segment curves, the approach designs parallel grid merging and filtering algorithms to determine if a grided area is inside lane or not. Lane boundaries are smoothed through jagged edge filtering and Simple Moving Average algorithms before centerline extraction. We evaluate our method based on real world AIS data in various area across the world's seas. Experimental results show the advantage of our method beyond the close related work. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/ACCESS.2019.2935794 | IEEE ACCESS |
Keywords | DocType | Volume |
AIS data,road network,spatio-temporal data mining,trajectory data mining,trajectory computing,visual analysis | Journal | 7 |
ISSN | Citations | PageRank |
2169-3536 | 2 | 0.39 |
References | Authors | |
0 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Guiling Wang | 1 | 832 | 52.06 |
| Jinlong Meng | 2 | 2 | 0.39 |
| Yanbo Han | 3 | 500 | 59.74 |