Segmentation and classification of point cloud data
AssigneeFord Global Technologies, LLC
InventorsMarcos Paul GERARDO CASTRO, Feng Jin, Jinesh Jain
Life of this patent
Estimating the term…
Abstract
A system can include a computer including a processor and a memory, the memory storing instructions executable by the processor to receive point cloud data. The instructions further include instructions to generate a plurality of feature maps based on the point cloud data, each feature map of the plurality of feature maps corresponding to a parameter of the point cloud data. The instructions further include instructions to aggregate the plurality of feature maps into an aggregated feature map. The instructions further include instructions to generate, via a feedforward neural network, at least one of a segmentation output or a classification output based on the aggregated feature map.
Claims20
A system, comprising a computer including a processor and a memory, the memory storing instructions executable by the processor to:
- receive point cloud data;
- generate a plurality of feature maps based on the point cloud data, each feature map of the plurality of feature maps corresponding to a parameter of the point cloud data;
- aggregate the plurality of feature maps into an aggregated feature map;
- and
- generate, via a feedforward neural network, at least one of a segmentation output or a classification output based on the aggregated feature map.
A method comprising,
- receiving point cloud data;
- generating a plurality of feature maps based on the point cloud data, each feature map of the plurality of feature maps corresponding to a parameter of the point cloud data;
- aggregating the plurality of feature maps into an aggregated feature map;
- and
- generating, via a feedforward neural network, at least one of a segmentation output or a classification output based on the aggregated feature map.
Dependencies are inferred from the claim text.