EasyTracker: automatic transit tracking, mapping, and arrival time prediction using smartphones
Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems
Mining large-scale, sparse GPS traces for map inference: comparison of approaches
Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining
Map inference in the face of noise and disparity
Proceedings of the 20th International Conference on Advances in Geographic Information Systems
CrowdAtlas: self-updating maps for cloud and personal use
Proceeding of the 11th annual international conference on Mobile systems, applications, and services
Segmentation-based road network construction
Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems
| Hi-index | 0.00 |
In order to generate roads digital map of unknown area when the raster map is absent, we proposed a way which employs multi-track GPS (Global Position System) data. Despite inaccuracy of GPS system itself, multi-track data can reduce errors when we assume a symmetric distribution of the error values. Morphological operations to binary image are employed to process the GPS data. Dilation, closing operations are used to merge discrete data points and fill in gaps among GPS tracks, while thinning algorithm and pruning are used to extract skeleton to gets the roads’ position. We also exploit direction rule and distance rule to delete redundant nodes when constructing roads graph so that the data storage of digital map will be reduced. By overlaying our own digital map on the Google Earth map of the same roads, this way of generating digital map with multi-track GPS data is proved to be effective.