Extracting feature geometries for localization of a device
Systems, apparatuses, and methods are provided for developing a fingerprint database and extracting feature geometries for determining the geographic location of an end-user device. A device collects, or a processor receives, a depth map of a location in a path network. A physical structure is identified within the depth map. The depth map is divided, at the physical structure, into a horizontal plane at an elevation from the road level. A two-dimensional feature geometry is extracted from the horizontal plane of the depth map using a linear regression algorithm, a curvilinear regression algorithm, or a machine learning algorithm.
1. A method comprising:
receiving a depth map of a location in a path network;
identifying, using a processor, a physical structure within the depth map;
dividing the depth map, at the physical structure, into a plurality of horizontal planes at different elevations from a road level;
performing an analysis of a first horizontal plane at a first elevation for a predetermined two-dimensional feature geometry;
selecting a second horizontal plane at a second elevation when the analysis of the first horizontal plane does not identify the predetermined two-dimensional feature geometry;
extracting the predetermined two-dimensional feature geometry from the second horizontal plane using a linear regression algorithm, curvilinear regression algorithm, or a machine learning algorithm; and
georeferencing points of the extracted feature geometry to a geographic location.
2. The method of claim 1 ,
wherein each point is matched with location reference information selected from the group consisting of: latitude, longitude, elevation from the road level, altitude, and combinations thereof.
3. The method of claim 2 , further comprising:
encoding the georeferenced points of the extracted feature geometry in a fingerprint database.
4. The method of claim 1 , wherein the two-dimensional feature geometry is a line or a set of connected lines, and the extracting uses the linear regression algorithm.
5. The method of claim 4 , wherein the georeferencing includes:
georeferencing points of the line or the set of connected lines to the geographic location, wherein each point is matched with location reference information for latitude, longitude, elevation from the road level, and altitude.
6. The method of claim 1 , wherein the two-dimensional feature geometry is an arc, and the extracting uses the curvilinear regression algorithm.
7. The method of claim 6 , wherein the georeferencing includes:
georeferencing a radius of the arc and points along the arc to the geographic location, wherein each point is matched with location reference information for latitude, longitude, elevation from the road level, and altitude.
8. The method of claim 1 , wherein the two-dimensional feature geometry is a spline, and the extracting uses the curvilinear regression algorithm.
9. The method of claim 8 , wherein the georeferencing includes:
georeferencing knots of the spline and points along the spline to the geographic location, wherein each point is matched with location reference information for latitude, longitude, elevation from the road level, and altitude.
10. A method comprising:
collecting, by an end-user device, a depth map at a location in a path network;
identifying, using a processor of the end-user device, a physical structure within the depth map;
dividing the depth map, at the physical structure, into a first horizontal plane at a first elevation from a road level and a second horizontal plane at a second elevation from the road level;
performing an analysis of the first horizontal plane; and
extracting, in response to the first horizontal plane lacking a predetermined two-dimensional feature geometry, a two-dimensional feature geometry from the second horizontal plane using a linear regression algorithm, a curvilinear regression algorithm, or a machine learning algorithm, wherein a geographic position is determined from the two-dimensional feature geometry.
11. The method of claim 10 , further comprising:
transmitting the extracted feature geometry to an external processor; and
receiving, from the external processor, a geographic location of the end-user device through a comparison of the feature geometry and a database of feature geometries for the path network.
12. An apparatus comprising:
at least one processor; and
at least one memory including computer program code for one or more programs;
the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to at least perform:
receive a depth map of a location in a path network;
identify a physical structure within the depth map;
divide the depth map, at the physical structure, into a first horizontal plane at a first elevation from a road level and a second horizontal plane at a second elevation from the road level;
extract, in response to the first horizontal plane lacking a predetermined two-dimensional feature geometry, a two-dimensional feature geometry from the second horizontal plane using a linear regression algorithm, a curvilinear regression algorithm, or a machine learning algorithm; and
provide a geographic position based on the two-dimensional feature geometry.
13. The apparatus of claim 12 , wherein the at least one memory and the computer program code are configured to cause the apparatus to further perform:
georeference points of the extracted feature geometry to a geographic location, wherein each point is matched with location reference information selected from the group consisting of: latitude, longitude, elevation from the road level, altitude, and combinations thereof.
14. The apparatus of claim 13 , wherein the at least one memory and the computer program code are configured to cause the apparatus to further perform:
encode the georeferenced points of the extracted feature geometry in a fingerprint database.
15. The apparatus of claim 12 , wherein the two-dimensional feature geometry is a line or a set of connected lines, and the extracting uses the linear regression algorithm.
16. The apparatus of claim 15 , wherein the at least one memory and the computer program code are configured to cause the apparatus to further perform:
georeference points of the line or the set of connected lines to a geographic location, wherein each point is matched with location reference information for latitude, longitude, elevation from the road level, and altitude.
17. The apparatus of claim 12 , wherein the two-dimensional feature geometry is an arc, and the extracting uses the curvilinear regression algorithm.
18. The apparatus of claim 17 , wherein the at least one memory and the computer program code are configured to cause the apparatus to further perform:
georeference a radius of the arc and points along the arc to a geographic location, wherein each point is matched with location reference information for latitude, longitude, elevation from the road level, and altitude.
19. The apparatus of claim 12 , wherein the two-dimensional feature geometry is a spline, and the extracting uses the curvilinear regression algorithm.
20. The apparatus of claim 19 , wherein the at least one memory and the computer program code are configured to cause the apparatus to further perform:
georeference knots of the spline and points along the spline to a geographic location, wherein each point is matched with location reference information for latitude, longitude, elevation from the road level, and altitude.