Automatic detection of overhead obstructions

1. A method for detecting an overhead obstruction comprising:

receiving, by a processor, three-dimensional data collected by a depth sensing device traveling along a path segment, wherein the three-dimensional data comprises point cloud data positioned above a ground plane of the path segment;

identifying, by the processor, data points of the point cloud data positioned within a corridor positioned above the ground plane;

projecting, by the processor, the identified data points onto a plane;

detecting, by the processor, the overhead obstruction based on a concentration of point cloud data positioned within a plurality of cells of the plane; and

storing the detected overhead obstruction above the path segment within a map database.

2. The method of claim 1 , wherein the depth sensing device comprises a LIDAR collection device.

3. The method of claim 1 , wherein the identifying of the data points comprises removing collected data points of the point cloud data positioned outside of the corridor.

4. The method of claim 1 , wherein the projecting of the identified data points comprises matching the identified data points with location data associated with the depth sensing device within the plane.

5. The method of claim 1 , wherein the plane is the ground plane of the path segment.

6. The method of claim 1 , wherein the corridor is a volume between a lower plane positioned parallel with the ground plane and an upper plane positioned parallel with both the ground plane and the lower plane.

7. The method of claim 6 , wherein the lower plane is in a range of 2-10 meters above the ground plane and the upper plane is in a range of 10-30 meters above the ground plane.

8. The method of claim 1 , further comprising:

comparing depth data of the identified data points within the corridor to identify a presence of a static structure or non-static structure,

wherein the projecting of the identified data points onto the plane is conducted only for identified static structures.

9. The method of claim 1 , wherein the detecting of the overhead obstruction comprises:

defining each cell of the plurality of cells with either an occupied status or a not-occupied status based on the concentration of the point cloud data with the cell being at least at a predefined threshold level or below the predefined threshold level, respectively;

creating a one-dimensional line segment for the path segment using the defined occupied and not-occupied statuses for each cell; and

identifying the overhead obstruction when a series of consecutive cells of the plurality of cells is defined with the occupied status.

10. The method of claim 9 , wherein the number of the series of consecutive cells equals at least a predetermined longitudinal distance.

11. An apparatus for detecting an overhead obstruction over a path segment, the apparatus comprising:

a processor configured to receive three-dimensional data collected by a depth sensing device traveling along a path segment, wherein the three-dimensional data comprises point cloud data positioned above a ground plane of the path segment, identify data points of the point cloud data positioned within a corridor positioned above the ground plane, project the identified data points onto a plane, and detect the overhead obstruction based on a concentration of point cloud data positioned within a plurality of cells of the plane; and

a map database configured to store the detected overhead obstruction above the path segment within the map database.

12. The apparatus of claim 11 , wherein identification of the data points comprises a removal of collected data points of the point cloud data positioned outside of the corridor.

13. The apparatus of claim 11 , wherein the projection of the identified data points comprises a match of the identified data points with location data associated with the depth sensing device within the plane.

14. The apparatus of claim 11 , wherein the plane is the ground plane of the path segment.

15. The apparatus of claim 11 , wherein the corridor is a volume between a lower plane positioned parallel with the ground plane and an upper plane positioned parallel with both the ground plane and the lower plane.

16. The apparatus of claim 11 , wherein the processor is further configured to compare depth data of the identified data points within the corridor to identify a presence of a static structure or non-static structure, wherein the projection of the identified data points onto the plane is conducted only for identified static structures.

17. The apparatus of claim 11 , wherein the detection of the overhead obstruction is based on a one-dimensional line segment for the path segment using an occupied status or a not-occupied status.

18. A non-transitory computer readable medium including instructions that when executed by a processor are configured to:

receive three-dimensional data collected by a depth sensing device traveling along a path segment, wherein the three-dimensional data comprises point cloud data positioned above a ground plane of the path segment;

identify data points of the point cloud data positioned within a corridor positioned above the ground plane;

project the identified data points onto a plane;

detect an overhead obstruction based on a concentration of point cloud data positioned within a plurality of cells of the plane; and

store the detected overhead obstruction above the path segment within a map database.

19. The non-transitory computer readable medium of claim 18 , wherein the instructions are further configured to:

compare depth data of the identified data points within the corridor to identify a presence of a static structure or non-static structure,

wherein the projection of the identified data points onto the plane is conducted only for identified static structures.

20. The non-transitory computer readable medium of claim 18 , wherein the detection of the overhead obstruction comprises:

define a status for each cell of the plurality of cells with either occupied or not-occupied based on the concentration of the point cloud data with the cell being at least at a predefined threshold level or below the predefined threshold level, respectively;

create a one-dimensional line segment for the path segment using the occupied and not-occupied statuses for each cell; and

identify the overhead obstruction when a series of consecutive cells of the plurality of cells is defined with an occupied status.