Transparency-characteristic based object classification for automated vehicle

1. An object classification system for an automated vehicle, said system comprising:

a lidar mounted on a host-vehicle, said lidar determines spot-distances indicated by light-beams that were emitted by the lidar and reflected toward the lidar from an area proximate to the host-vehicle;

a controller in communication with the lidar, wherein the controller

determines a lidar-outline of an object in the area based on spot-distances,

determines an object-distance to the object based on spot-distances within the lidar-outline of the object,

determines a backdrop-distance to a backdrop based on spot-distances outside of the lidar-outline of the object,

determines a transparency-characteristic of the object based on instances of spot-distances from within the lidar-outline of the object that correspond to the backdrop-distance, and

operates the host-vehicle to avoid the object when the transparency-characteristic is less than a transparency-threshold.

2. The system of claim 1 , wherein the automated vehicle has a level of automation, and the level of automation for the automated vehicle is providing a warning to a human-operator for the automated vehicle.

3. The system of claim 1 , wherein the lidar is a two-dimensional lidar and the two-dimensional lidar is configured to indicate an azimuth-angle for each of the spots.

4. The system of claim 1 , wherein the controller further:

determines that the transparency-characteristic is over the transparency-threshold; and

in response, operates the host-vehicle to run over or through the object.

5. The system in accordance with claim 1 , wherein the system further includes

a camera mounted on the host-vehicle and in communication with the controller, said camera renders an image based on light detected by a plurality of pixels in the camera, wherein each pixel detects a pixel-color of light from the area, wherein the controller

determines a camera-outline of the object based on the image,

determines a backdrop-color of the backdrop outside of the camera-outline of the object, and

further determines the transparency-characteristic of the object based on instances of pixel-color within the camera-outline that correspond to the backdrop-color.

6. The system of claim 5 , wherein the controller operates the host-vehicle to avoid the object when the second transparency-characteristic is less than the transparency-threshold.

7. The system of claim 5 , wherein the controller operates the host-vehicle to avoid the object when both the transparency-characteristic and the second transparency-characteristic are below the transparency-threshold.

8. A method comprising:

determining, by a lidar mounted on an automated vehicle, respective spot-distances indicated by one or more spots, wherein the one or more spots are locations in an area proximate to the automated vehicle where light-beams emitted by the lidar are reflected toward the lidar;

determining a lidar-outline of an object in the area based on the spot-distances;

determining an object-distance to the object based on the spot-distances within the lidar-outline of the object;

determining a backdrop-distance to a backdrop based on the spot-distances outside of the lidar-outline of the object;

determining a transparency-characteristic of the object based on instances of spot-distances from within the lidar-outline of the object that correspond to the backdrop-distance; and

operating the automated vehicle to avoid the object when the transparency-characteristic is less than a transparency-threshold.

9. The method of claim 8 , further comprising:

determining, by a camera mounted on the automated vehicle, a camera-outline of the object based on the image;

determining a backdrop-color of the backdrop outside of the camera-outline of the object; and

determining a second transparency-characteristic of the object based on instances of pixel-color within the camera-outline that correspond to the backdrop-color.

10. The method of claim 9 , wherein operating the automated vehicle to avoid the object comprises:

determining that the second transparency-characteristic is less than the transparency-threshold; and

in response, operating the automated vehicle to avoid the object.

11. The system of claim 9 , wherein operating the automated vehicle to avoid the object comprises:

determining that both the transparency-characteristic and the second transparency-characteristic are below the transparency-threshold; and

in response, operating the automated vehicle to avoid the object.

12. A non-transitory computer-readable storage medium comprising a plurality of instructions for object classification for an automated vehicle, the plurality of instructions configured to execute on at least one computer processor to enable the computer processor to:

determine, by a lidar mounted on the automated vehicle, respective spot-distances indicated by one or more spots, wherein the one or more spots are locations in an area proximate to the automated vehicle where light-beams emitted by the lidar are reflected toward the lidar;

determine a lidar-outline of an object in the area based on the spot-distances;

determine an object-distance to the object based on the spot-distances within the lidar-outline of the object;

determine a backdrop-distance to a backdrop based on the spot-distances outside of the lidar-outline of the object;

determine a transparency-characteristic of the object based on instances of spot-distances from within the lidar-outline of the object that correspond to the backdrop-distance; and

operate the automated vehicle to avoid the object when the transparency-characteristic is less than a transparency-threshold.

13. An object classification system for an automated vehicle, the system comprising:

a camera mounted on the automated vehicle, the camera renders an image of an area proximate to the automated vehicle, the image based on light detected by a plurality of pixels in the camera, wherein each pixel detects a pixel-color of light from the area; and

a controller in communication with the camera, wherein the controller:

determines a camera-outline of an object based on the image;

determines a backdrop-color of a backdrop outside of the camera-outline of the object;

determines a transparency-characteristic of the object based on instances of pixel-color within the camera-outline that correspond to the backdrop-color; and

operates the automated vehicle to avoid the object when the transparency-characteristic is less than a transparency-threshold.

14. The object classification system of claim 13 , wherein the image rendered by the camera is rendered in black and white.

15. The system of claim 13 , wherein the automated vehicle has a level of automation, and the level of automation for the automated vehicle is providing a warning to a human-operator for the automated vehicle.

16. The system of claim 13 , wherein the controller further:

determines that the transparency-characteristic is over the transparency-threshold; and

in response, operates the automated vehicle to run over or through the object.

17. A method comprising:

rendering, by a camera mounted on an automated vehicle, an image of an area proximate to the automated vehicle, the image based on light detected by a plurality of pixels in the camera, wherein each pixel detects a pixel-color of light from the area;

determining a camera-outline of an object based on the image;

determining a backdrop-color of a backdrop outside of the camera-outline of the object;

determining a transparency-characteristic of the object based on instances of pixel-color within the camera-outline that correspond to the backdrop-color; and

operating the automated vehicle to avoid the object when the transparency-characteristic is less than a transparency-threshold.

18. A non-transitory computer-readable storage medium comprising a plurality of instructions for object classification for an automated vehicle, the plurality of instructions configured to execute on at least one computer processor to enable the computer processor to:

render, by a camera mounted on the automated vehicle, an image of an area proximate to the automated vehicle, the image based on light detected by a plurality of pixels in the camera, wherein each pixel detects a pixel-color of light from the area;

determine a camera-outline of an object based on the image;

determine a backdrop-color of a backdrop outside of the camera-outline of the object;

determine a transparency-characteristic of the object based on instances of pixel-color within the camera-outline that correspond to the backdrop-color; and

operate the automated vehicle to avoid the object when the transparency-characteristic is less than a transparency-threshold.