Multi-modal segmentation network for enhanced semantic labeling in mapping

Patent metadata

Field	Value
Publication number	US-12131562-B2
Application number	US-202218079498-A
Country	US
Kind code	B2
Filing date	Dec 12, 2022
Priority date	Dec 16, 2021
Publication date	Oct 29, 2024
Grant date	Oct 29, 2024

Abstract

Provided are methods for enhanced semantic labeling in mapping with a semantic labeling system, which can include receiving, from a LiDAR sensor of a vehicle, LiDAR point cloud information including at least one raw point feature for a point, receiving, from a camera of the vehicle, image data associated with an image captured using the camera, generating at least one rich point feature for the point based on the image data, predicting, using a LiDAR segmentation neural network and based on the at least one raw point feature and the at least one rich point feature, a point-level semantic label for the point, and providing the point-level semantic label to a mapping engine to generate a map based on the point-level semantic label Systems and computer program products are also provided.

First claim

What is claimed is:

1. A vehicle comprising:
at least one processor communicatively coupled to a camera and a LiDAR sensor; and
at least one memory storing instructions thereon that, when executed by the at least one processor, result in operations comprising:
generating at least one rich point feature for a point based on image data, the at least one rich point feature including a vector corresponding to a prediction score, the prediction score generated based on an application of a pixel-wise segmentation label to an enhanced pixel, wherein the vector includes vector values comprising the prediction score for the pixel-wise segmentation label applied to the enhanced pixel, the prediction score indicating a likelihood that the pixel-wise segmentation label corresponds to the point;
predicting a point-level semantic label for the point; and
providing the point-level semantic label to a mapping engine to generate a map.

2. The vehicle of claim 1 , wherein the vehicle further comprises:
the camera configured to capture an image of an object proximate to the vehicle; and
the LiDAR sensor configured to detect light reflected from the object proximate to the vehicle and generate LiDAR point cloud information based on the light, the LiDAR point cloud information comprising at least one raw point feature for the point.

3. The vehicle of claim 2 ,
wherein the enhanced pixel is generated by projecting LiDAR point cloud information onto a pixel of the image data; and
the at least one raw point feature comprises an additional vector having additional vector values corresponding to at least one of spatial information associated with the point, intensity information associated with the point, and depth information associated with the point.

4. The vehicle of claim 2 , wherein the predicting of the point-level semantic label for the point is based on a LiDAR segmentation neural network and based on the at least one raw point feature.

5. The vehicle of claim 4 , wherein the instructions cause the at least one rich point feature to be generated based on a first neural network; and wherein the LiDAR segmentation neural network is different from the first neural network.

6. The vehicle of claim 1 , wherein the pixel-wise segmentation label is predicted by providing the image data to an image segmentation neural network to cause the image segmentation neural network to generate the pixel-wise segmentation label.

7. The vehicle of claim 1 , wherein the prediction score represents a likelihood that the pixel-wise segmentation label corresponds to the point.

8. The vehicle of claim 7 , wherein the prediction score comprises a plurality of prediction scores; wherein the pixel-wise segmentation label comprises a plurality of pixel-wise segmentation labels; and wherein each prediction score of the plurality of prediction scores represents a particular likelihood that an associated pixel-wise segmentation label of the plurality of pixel-wise segmentation labels corresponds to the point.

9. The vehicle of claim 1 , wherein the at least one rich point feature is generated based on applying at least one post-processing technique to reduce re-projection error from the camera.

10. The vehicle of claim 1 , wherein the instructions that cause the at least one processor to generate the map cause the at least one processor to at one least of:
remove an object from a previous map, detect a landmark, compare semantic consistency between the map and the previous map, and annotate the map.

11. The vehicle of claim 1 , wherein the map comprises a LiDAR point cloud of LiDAR point cloud information.

12. The vehicle of claim 11 , wherein the map further comprises at least one point-level semantic label that is associated with at least one point of the LiDAR point cloud, the at least one point-level semantic label comprising the point-level semantic label that is predicted.

13. The vehicle of claim 1 , wherein the operations further comprise:
receiving, by an image segmentation neural network and from the camera, the image data; and
predicting, based on the image data, the pixel-wise segmentation label.

14. The vehicle of claim 13 , wherein the operations further comprise:
projecting LiDAR point cloud information onto a pixel of the image data to generate the enhanced pixel; and
applying the pixel-wise segmentation label from the image segmentation neural network to the enhanced pixel.

15. The vehicle of claim 14 , wherein the operations further comprise: applying, to the enhanced pixel, at least one post-processing technique configured to reduce a re-projection error from the camera.

16. The vehicle of claim 14 , wherein the operations further comprise:
transmitting, to a LiDAR segmentation neural network, an additional vector having additional vector values corresponding to the enhanced pixel and the pixel-wise segmentation label.

17. A system, comprising:
at least one processor communicatively coupled to a camera and a LiDAR sensor; and
at least one memory storing instructions thereon that, when executed by the at least one processor, result in operations comprising:
generating at least one rich point feature for a point based on image data, the at least one rich point feature including a vector corresponding to a prediction score, the prediction score generated based on an application of a pixel-wise segmentation label to an enhanced pixel, wherein the vector includes vector values comprising the prediction score for the pixel-wise segmentation label applied to the enhanced pixel, the prediction score indicating a likelihood that the pixel-wise segmentation label corresponds to the point;
predicting a point-level semantic label for the point; and
providing the point-level semantic label to a mapping engine to generate a map.

18. The system of claim 17 , wherein the system further comprises:
the camera configured to capture an image of an object proximate to a vehicle; and
the LiDAR sensor configured to detect light reflected from the object proximate to the vehicle and generate LiDAR point cloud information based on the light, the LiDAR point cloud information comprising at least one raw point feature for the point.

19. The system of claim 18 , wherein
the enhanced pixel is generated by projecting LiDAR point cloud information onto a pixel of the image data; and
the at least one raw point feature comprises an additional vector having additional vector values corresponding to at least one of spatial information associated with the point, intensity information associated with the point, and depth information associated with the point.

20. The system of claim 18 , wherein the predicting of the point-level semantic label for the point is based on a LiDAR segmentation neural network and based on the at least one raw point feature.

21. The system of claim 20 , wherein the instructions cause the at least one rich point feature to be generated based on a first neural network; and wherein the LiDAR segmentation neural network is different from the first neural network.

22. The system of claim 17 , wherein the pixel-wise segmentation label is predicted by providing the image data to an image segmentation neural network to cause the image segmentation neural network to generate the pixel-wise segmentation label.

23. The system of claim 17 , wherein the prediction score represents a likelihood that the pixel-wise segmentation label corresponds to the point.

Assignees

• Motional Ad Llc

Inventors

• Widjaja Sergi Adipraja
• Sharma Dhananjai
• Liong Venice Erin B

Classifications

• G06T2207/30252

  Vehicle exterior; Vicinity of vehicle · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title

• G06T2207/10024

  Color image · CPC title