Systems and methods for monocular based object detection

1. A method for object detection, comprising:

obtaining, by a computing device, an image comprising a plurality of color layers superimposed on each other;

identifying a portion of a road map that is to be projected into the image, based on pose information of a vehicle and a pre-defined map grid portion size, wherein the pose information comprises at least an angle and a pointing direction of the vehicle, and the portion of the road map has a center point aligned with a center point of the vehicle along at least two axis of a coordinate system:

generating at least one first additional layer using information contained in the portion of the road map that was identified, the at least one first additional layer including one of the following types of information: ground height information, ground depth information, drivable geographical area information, map point distance-to-lane center information, lane direction information, and intersection information;

generating a modified image by superimposing the at least one first additional layer on the color layers; and

causing, by the computing device, control of a vehicle's operation based on the object detection made by an object detection algorithm using the modified image as an input.

2. The method according to claim 1 , further comprising obtaining the

pose information for the vehicle and the pre-defined map grid portion size.

3. The method according to claim 1 , wherein the portion of the

road map comprises a segment of the road map that has dimensions equal to dimensions defined by the pre-defined map grid portion size.

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

obtaining road map based values for a plurality of geometric point locations in the portion of the road map; and

using the road map based values to generate the at least one first additional layer.

5. The method according to claim 4 , wherein the at least one first additional layer is generated by:

defining a plurality of tiles in a first coordinate system based on the road map based values;

defining a polygon for each said tile using ground height values of the road map that are associated with respective ones of the road map based values; and

converting coordinates of the polygons from the first coordinate system to a second coordinate system.

6. The method according to claim 4 , wherein the road map based values comprise: values defining a ground surface specified in the road map; values defining a drivable geographical area contained in the road map; ground depth values computed based on a known camera location and ground height information contained in the road map; map point distance-to-lane center values; lane direction values; or intersection values.

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

generating at least one second additional layer using information contained in the road map, the at least one second additional layer including different information than the at least one first additional layer;

wherein the at least one second additional layer is superimposed on the color layers in addition to the at least one first additional layer to generate the modified image.

8. The method according to claim 1 , wherein the modified image comprises a combination of at least two of the following layers in addition to the plurality of color layers: a ground height layer, a ground depth layer, a drivable geographical area layer, a map point distance-to-lane center layer, a lane direction layer, and an intersection layer.

9. The method according to claim 1 , further comprising estimating at least one of a position, an orientation, a spatial extent and a classification for at least one object detected in the modified image.

10. A system, comprising:

a processor;

a non-transitory computer-readable storage medium comprising programming instructions that are configured to cause the processor to implement a method for object detection, wherein the programming instructions comprise instructions to:

obtain an image comprising a plurality of color layers superimposed on each other;

identify a portion of a road map that is to be projected into the image, based on pose information of a vehicle and a pre-defined map grid portion size, wherein the pose information comprises at least an angle and a pointing direction of the vehicle, and the portion of the road map has a center point aligned with a center point of the vehicle along at least two axis of a coordinate system:

generate at least one first additional layer using information contained in the portion of the a road map that was identified, the additional layer including one of the following types of information: ground height information, ground depth information, drivable geographical area information, map point distance-to-lane center information, lane direction information, and intersection information;

generate a modified image by superimposing the at least one first additional layer on the color layers; and

cause control of a vehicle's operation based on the object detection made by an object detection algorithm using the modified image as an input.

11. The system according to claim 10 , wherein the programming instructions further comprise instructions to obtain the pose information for the vehicle and the pre-defined map grid portion size.

12. The system according to claim 10 , wherein the portion of the road map comprises a segment of the road map that has dimensions equal to dimensions defined by the pre-defined map grid portion size.

13. The system according to claim 10 , wherein the programming instructions further comprise instructions to:

obtain road map based values for a plurality of geometric point locations in the portion of the road map; and

use the road map based values to generate the at least one first additional layer.

14. The system according to claim 13 , wherein the at least one first additional layer is generated by:

defining a plurality of tiles in a first coordinate system based on the road map based values;

defining a polygon for each said tile using ground height values of the road map that are associated with respective ones of the road map based values; and

converting coordinates of the polygons from the first coordinate system to a second coordinate system.

15. The system according to claim 13 , wherein the road map based values comprise: values defining a ground surface specified in the road map; values defining a drivable geographical area contained in the road map; ground depth values computed based on a known camera location and ground height information contained in the road map; map point distance-to-lane center values; lane direction values; or intersection values.

16. The system according to claim 10 , wherein the programming instructions further comprise instructions to:

generate at least one second additional layer using information contained in the road map, the at least one second additional layer including different information than the at least one first additional layer;

wherein the at least one second additional layer is superimposed on the color layers in addition to the at least one first additional layer to generate the modified image.

17. The system according to claim 10 , wherein the modified image comprises a combination of at least two of the following layers in addition to the plurality of color layers: a ground height layer, a ground depth layer, a drivable geographical area layer, a map point distance-to-lane center layer, a lane direction layer, and an intersection layer.

18. The system according to claim 10 , wherein the programming instructions further comprise instructions to estimate at least one of position, an orientation, a spatial extent and a classification for at least one object detected in the modified image.

19. A non-transitory computer-readable medium that stores instructions that are configured to, when executed by at least one computing device, cause the at least one computing

device to perform operations comprising:

obtaining an image comprising a plurality of color layers superimposed on each other;

identifying a portion of a road map that is to be projected into the image based on pose information of a vehicle and a pre-defined map grid portion size, wherein the pose information comprises at least an angle and a pointing direction of the vehicle, and the portion of the road map has a center point aligned with a center point of the vehicle along at least two axis of a coordinate system;

generating at least one first additional layer using information contained in the portion of the road map, the at least one first additional layer including one of the following types of information: ground height information, ground depth information, drivable geographical area information, map point distance-to-lane center information, lane direction information, and intersection information;

generating a modified image by superimposing the at least one first additional layer on the color layers; and

causing control of a vehicle's operation based on the object detection made by an object detection algorithm using the modified image as an input.