Roadmap generation system and method of using

1. A method of determining a roadway map, the method comprising:

receiving an image from above a roadway;

generating a skeletonized map based on the received image, wherein the skeletonized map comprises a plurality of roads;

identifying intersections based on joining of multiple roads of the plurality of roads in the skeletonized map;

partitioning the skeletonized map based on the identified intersections, wherein partitioning the skeletonized map defines a roadway data set and an intersection data set;

analyzing the roadway data set to determine a number of lanes in each roadway of the plurality of roads;

analyzing the intersection data set to determine lane connections extending directly across respective intersections in the identified intersections; and

merging results of the analyzed road data set and the analyzed intersection data set to generate the roadway map, wherein partitioning the skeletonized map comprises:

setting a node at each of the identified intersections;

setting a radius around the node; and

defining the roadway data set as being outside of the radius around the node.

2. The method according to claim 1 , wherein the received image is a satellite image.

3. The method according to claim 1 , wherein analyzing the roadway data set includes analyzing the roadway data set using a trained neural network to perform object detection.

4. The method according to claim 3 , wherein performing object detection comprises identifying lane lines along at least one road of the plurality of roads.

5. The method according to claim 1 , wherein analyzing the roadway data set comprises determining a width of a road of the plurality of roads.

6. The method according to claim 5 , further comprising determining a number of lanes on the road based on the determined width of the road.

7. The method according to claim 1 , wherein setting the radius comprises setting the radius around the node to be a same value for each of the identified intersections.

8. The method according to claim 1 , wherein setting the radius comprises setting the radius around a node associated with a first identified intersection of the identified intersections to be different from the radius around a node associated with a second identified intersection of the identified intersections.

9. A system comprising:

a non-transitory computer readable medium configured to store instructions thereon; and

a processor connected to the non-transitory computer readable medium, wherein the processor is configured to execute the instructions for:

receiving an image from above a roadway;

generating a skeletonized map based on the received image, wherein the skeletonized map comprises a plurality of roads;

identifying intersections based on joining of multiple roads of the plurality of roads in the skeletonized map;

partitioning the skeletonized map based on the identified intersections, wherein partitioning the skeletonized map defines a roadway data set and an intersection data set;

analyzing the roadway data set to determine a number of lanes in each roadway of the plurality of roads;

analyzing the intersection data set to determine lane connections extending directly across respective intersections in the identified intersections; and

merging results of the analyzed road data set and the analyzed intersection data set to generate a roadway map, wherein the processor is configured to execute the instructions for partitioning the skeletonized map by:

setting a node at each of the identified intersections;

setting a radius around the node; and

defining the roadway data set as being outside of the radius around the node.

10. The system according to claim 9 , wherein the received image is a satellite image.

11. The system according to claim 9 , wherein the processor is configured to execute the instructions for analyzing the roadway data set using a trained neural network to perform object detection.

12. The system according to claim 11 , wherein the processor is configured to execute the instructions for using the object detection to identify lane lines along at least one road of the plurality of roads.

13. The system according to claim 9 , wherein the processor is configured to execute the instructions for determining a width of a road of the plurality of roads.

14. The system according to claim 13 , wherein the processor is configured to execute the instructions for determining a number of lanes on the road based on the determined width of the road.

15. The system according to claim 9 , wherein the processor is configured to execute the instructions for setting the radius around the node to be a same value for each of the identified intersections.

16. The system according to claim 9 , wherein the processor is configured to execute the instructions for setting the radius around a node associated with a first identified intersection of the identified intersections to be different from the radius around a node associated with a second identified intersection of the identified intersections.

17. A method of determining a roadway map, the method comprising:

receiving an image from above a roadway;

generating a skeletonized map based on the received image, wherein the skeletonized map comprises a plurality of roads;

identifying nodes based on joining of multiple roads of the plurality of roads in the skeletonized map;

setting a plurality of radii, wherein each of the plurality of radii is around a corresponding node of the identified nodes;

partitioning the skeletonized map to define a roadway data set outside each of the plurality of radii and an intersection data set within each of the plurality of radii;

analyzing the roadway data set to determine a number of lanes in each roadway of the plurality of roads;

analyzing the intersection data set to lane connections; and

merging results of the analyzed road data set and the analyzed intersection data set to generate the roadway map.

18. The method according to claim 17 , further comprising wirelessly transmitting the merged results to an external device.