Generating a road network from location data

• US 9,631,935 B2
• Filed: 06/15/2015
• Issued: 04/25/2017
• Est. Priority Date: 06/27/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Ding, Jian Dong, Duan, Ning, Gao, Peng, Ji, Peng, Zhang, Xin, Zhao, Qian Kun
• Primary Examiner(s): Black, Thomas G
• Assistant Examiner(s): HUYNH, LUAT T
• Application Number:
  US14/738,971
• Publication Number:
  US 20150377636A1
• Time in Patent Office: 680 Days
• Field of Search: 701532, 701400, 701408-410, 701511-512, 701527, 701533
• CPC Class Codes: G01C 21/30 Map- or contour-matching

Abstract

The present disclosure relates to a method and system for generating a road network. An embodiment of the present invention provides a method comprising: identifying a target area to be refined in a road network skeleton; and refining the target area using at least one trajectory associated with the target area to generate the road network. Another embodiment of the present invention provides a corresponding system.

Claims

1. A method for generating a road network, the method comprising:

receiving, from a user, a target area to be refined in a road network skeleton;

creating, by a computer, a virtual link connecting points in the target area;

generating, by the computer, in the target area, a virtual path containing the virtual link;

refining, by the computer, the target area by matching at least one trajectory, stored on a server, associated with the target area to generate the road network and the virtual path; and

notifying the user of the refined target area via a display.

2. The method according to claim 1, further comprising:

generating, by the computer, the road network skeleton by rasterization processing based on location data representing a plurality of locations.

3. The method according to claim 1, wherein receiving the target area further comprises:

dividing, by the computer, the road network skeleton into a plurality of areas; and

identifying, by the computer, the target area in the plurality of areas.

4. The method according to claim 3, wherein identifying the target area in the plurality of areas further comprises:

determining, by the computer, a connectivity of the road network skeleton in the plurality of areas; and

identifying, by the computer, the target area at least in part based on the determined connectivity.

5. The method according to claim 4, wherein receiving the target area at least in part based on the determined connectivity comprises:

determining, by the computer, a distribution of a plurality of locations for generating the road network skeleton among the plurality of areas; and

identifying, by the computer, the target area based on the connectivity and the determined distribution.

6. The method according to claim 1, wherein the at least one trajectory is generated based on at least one of:

a first group of locations that are used for generating the road network skeleton and located in the target area; and

a second group of locations that are obtained after the road network skeleton is generated, and is located in the target area.

7. The method according to claim 1, wherein refining the target area by matching the at least one trajectory and the virtual path comprises:

adding, by the computer, the virtual link contained in the virtual path into the road network in response to the virtual path matching a predetermined number of trajectories in the at least one trajectory.

8. The method according to claim 1, wherein creating the virtual link connecting points in the target area comprises:

selecting, by the computer, an initial node in the target area;

selecting, by the computer, a candidate node in the target area based on the initial node and a predefined constraint; and

creating, by the computer, the virtual link by connecting the initial node and the candidate node.

9. The method according to claim 8, wherein the predefined constraint comprises at least one of a spatial constraint and a time constraint.