Method, apparatus and computer program product for tunnel detection from a point cloud

1. An apparatus comprising at least one processor and at least one non-transitory memory including computer program code instructions, the computer program code instructions configured to, when executed, cause the apparatus to at least:

receive point cloud data representative of an environment from at least one sensor-equipped vehicle traveling on a trajectory along a road segment;

generate, from the point cloud data, one or more two-dimensional images in one or more corresponding planes orthogonal to the trajectory;

determine, for the one or more two-dimensional images, a probability as to whether a respective two-dimensional image is captured within a tunnel along the road segment;

classify a point along the road segment at a position corresponding to a respective one of the one or more two-dimensional images in the one or more corresponding planes orthogonal to the trajectory as a tunnel point in response to the probability as to whether the respective two-dimensional image is captured within a tunnel along the road segment satisfying a predetermined value; and

update a map database of a road network including the road segment with the point along the road segment classified as a tunnel point.

2. The apparatus of claim 1 , wherein causing the apparatus to determine for the one or more two-dimensional images, a probability as to whether the respective two-dimensional image is captured within a tunnel along the road segment comprises causing the apparatus to:

process the respective two-dimensional image as an input to a convolutional neural network; and

generate, from the convolutional neural network, the probability as to whether the respective two-dimensional image is captured within a tunnel along the road segment.

3. The apparatus of claim 1 , wherein the apparatus is further caused to:

classify a point along the road segment at a position corresponding to a respective one of the one or more two-dimensional images as a non-tunnel point in response to the probability as to whether the respective two-dimensional image is captured within a tunnel along the road segment failing to satisfy the predetermined value.

4. The apparatus of claim 3 , wherein the apparatus is further caused to:

identify a first tunnel point following a non-tunnel point in a direction of travel of the trajectory as a tunnel entrance point, wherein the tunnel entrance point represents the entrance of a tunnel along the road segment.

5. The apparatus of claim 4 , wherein the apparatus is further caused to:

identify a first non-tunnel point following a tunnel point in the direction of travel of the trajectory as a tunnel exit point, where the tunnel exit point represents an exit of the tunnel along the road segment.

6. The apparatus of claim 5 , wherein the apparatus is further caused to:

update the map database of the road network to include the tunnel entrance point and the tunnel exit point.

7. The apparatus of claim 1 , wherein causing the apparatus to update a map database of the road network including the road segment with the point along the road segment classified as a tunnel point comprises causing the apparatus to update the map database of the road network with bounds of a tunnel entrance and exit.

8. A computer program product comprising at least one non- transitory computer-readable storage medium having computer-executable program code instructions stored therein, the computer-executable program code instructions comprising program code instructions to:

receive point cloud data representative of an environment from at least one sensor-equipped vehicle traveling on a trajectory along a road segment;

generate, from the point cloud data, one or more two-dimensional images in one or more corresponding planes orthogonal to the trajectory;

determine, for the one or more two-dimensional images, a probability as to whether a respective two-dimensional image is captured within a tunnel along the road segment;

classify a point along the road segment at a position corresponding to a respective one of the one or more two-dimensional images in the one or more corresponding planes orthogonal to the trajectory as a tunnel point in response to the probability as to whether the respective two-dimensional image is captured within a tunnel along the road segment satisfying a predetermined value; and

update a map database of a road network including the road segment with the point along the road segment classified as a tunnel point.

9. The computer program product of claim 8 , wherein the program code instructions to determine for the one or more two-dimensional images, a probability as to whether the respective two-dimensional image is captured within a tunnel along the road segment comprise program code instructions to:

process the respective two-dimensional image as an input to a convolutional neural network; and

generate, from the convolutional neural network, the probability as to whether the respective two-dimensional image is captured within a tunnel along the road segment.

10. The computer program product of claim 8 , further comprising program code instructions to:

classify a point along the road segment at a position corresponding to a respective one of the one or more two-dimensional images as a non-tunnel point in response to the probability as to whether the respective two-dimensional image is captured within a tunnel along the road segment failing to satisfy the predetermined value.

11. The computer program product of claim 10 , further comprising program code instructions to:

identify a first tunnel point following a non-tunnel point in a direction of travel of the trajectory as a tunnel entrance point, wherein the tunnel entrance point represents the entrance of a tunnel along the road segment.

12. The computer program product of claim 11 , further comprising program code instructions to:

identify a first non-tunnel point following a tunnel point in the direction of travel of the trajectory as a tunnel exit point, where the tunnel exit point represents an exit of the tunnel along the road segment.

13. The computer program product of claim 12 , further comprising program code instructions to:

update the map database of the road network to include the tunnel entrance point and the tunnel exit point.

14. The computer program product of claim 8 , wherein the program code instructions to update a map database of the road network including the road segment with the point along the road segment classified as a tunnel point comprise program code instructions to update the map database of the road network with bounds of a tunnel entrance and exit.

15. A method comprising:

receiving point cloud data representative of an environment from at least one sensor-equipped vehicle traveling on a trajectory along a road segment;

generating, from the point cloud data, one or more two-dimensional images in one or more corresponding planes orthogonal to the trajectory;

determining, for the one or more two-dimensional images, a probability as to whether a respective two-dimensional image is captured within a tunnel along the road segment;

classifying a point along the road segment at a position corresponding to a respective one of the one or more two-dimensional images in the one or more corresponding planes orthogonal to the trajectory as a tunnel point in response to the probability as to whether the respective two-dimensional image is captured within a tunnel along the road segment satisfying a predetermined value; and

updating a map database of a road network including the road segment with the point along the road segment classified as a tunnel point.

16. The method of claim 15 , wherein determining for the one or more two-dimensional images, a probability as to whether the respective two-dimensional image is captured within a tunnel along the road segment comprises:

processing the respective two-dimensional image as an input to a convolutional neural network; and

generating, from the convolutional neural network, the probability as to whether the respective two-dimensional image is captured within a tunnel along the road segment.

17. The method of claim 15 , further comprising:

classifying a point along the road segment at a position corresponding to a respective one of the one or more two-dimensional images as a non-tunnel point in response to the probability as to whether the respective two-dimensional image is captured within a tunnel along the road segment failing to satisfy the predetermined value.

18. The method of claim 17 , further comprising:

identifying a first tunnel point following a non-tunnel point in a direction of travel of the trajectory as a tunnel entrance point, wherein the tunnel entrance point represents the entrance of a tunnel along the road segment.

19. The method of claim 18 , further comprising:

identifying a first non-tunnel point following a tunnel point in the direction of travel of the trajectory as a tunnel exit point, where the tunnel exit point represents an exit of the tunnel along the road segment.

20. The method of claim 19 , further comprising:

updating the map database of the road network to include the tunnel entrance point and the tunnel exit point.