公开(公告)号：US20220156483A1

公开(公告)日：2022-05-19

申请号：US17527653

申请日：2021-11-16

Applicant: Waymo LLC

Inventor： Pei Sun ,  Weiyue Wang ,  Yuning Chai ,  Xiao Zhang ,  Dragomir Anguelov

IPC: G06K9/00 ,  G06T7/194

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for performing object detection. The system obtains a respective range image corresponding to each point cloud in a set of point clouds captured by one or more sensors. The system processes each range image using a segmentation neural network to generate range image features and a segmentation output. The system generates a feature representation of the set of point clouds from only the feature representations of the foreground points. The system processes the feature representation of the set of point clouds using a prediction neural network to generate a prediction characterizing the set of point clouds.

公开(公告)号：US12125298B2

公开(公告)日：2024-10-22

申请号：US17527653

申请日：2021-11-16

Applicant: Waymo LLC

Inventor： Pei Sun ,  Weiyue Wang ,  Yuning Chai ,  Xiao Zhang ,  Dragomir Anguelov

IPC: G06V20/64 ,  G06T7/194

CPC classification number: G06V20/64 ,  G06T7/194 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for performing object detection. The system obtains a respective range image corresponding to each point cloud in a set of point clouds captured by one or more sensors. The system processes each range image using a segmentation neural network to generate range image features and a segmentation output. The system generates a feature representation of the set of point clouds from only the feature representations of the foreground points. The system processes the feature representation of the set of point clouds using a prediction neural network to generate a prediction characterizing the set of point clouds.

公开(公告)号：US20220156585A1

公开(公告)日：2022-05-19

申请号：US17526731

申请日：2021-11-15

Applicant: Waymo LLC

Inventor： Zhaoqi Leng ,  Shuyang Cheng ,  Weiyue Wang ,  Xiao Zhang ,  Dragomir Anguelov

IPC: G06N3/08 ,  G06K9/62

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for performing training of a neural network that is configured to process a network input comprising a point cloud to generate a network output for a point cloud processing task. The system obtains a set of labeled training examples and a set of unlabeled point clouds, generates a respective pseudo-label for each unlabeled point cloud, generates a plurality of pseudo-elements based on the respective pseudo-label for the unlabeled point cloud, generates augmented training data by augmenting the labeled training examples using the pseudo-elements generated for the unlabeled point clouds, and performing training of the neural network on the augmented training data.

公开(公告)号：US11941875B2

公开(公告)日：2024-03-26

申请号：US17443674

申请日：2021-07-27

Applicant: Waymo LLC

Inventor： Yuning Chai ,  Pei Sun ,  Jiquan Ngiam ,  Weiyue Wang ,  Vijay Vasudevan ,  Benjamin James Caine ,  Xiao Zhang ,  Dragomir Anguelov

IPC: G06V20/00 ,  G01S7/48 ,  G01S17/89 ,  G06F18/21 ,  G06F18/213 ,  G06F18/25 ,  G06N3/08 ,  G06T7/70 ,  G06V10/94 ,  H04N23/10

CPC classification number: G06V20/00 ,  G01S7/4802 ,  G01S17/89 ,  G06F18/213 ,  G06F18/217 ,  G06F18/253 ,  G06N3/08 ,  G06T3/4046 ,  G06T7/70 ,  G06V10/95 ,  H04N23/10 ,  G06T2207/20084

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for processing a perspective view range image generated from sensor measurements of an environment. The perspective view range image includes a plurality of pixels arranged in a two-dimensional grid and including, for each pixel, (i) features of one or more sensor measurements at a location in the environment corresponding to the pixel and (ii) geometry information comprising range features characterizing a range of the location in the environment corresponding to the pixel relative to the one or more sensors. The system processes the perspective view range image using a first neural network to generate an output feature representation. The first neural network comprises a first perspective point-set aggregation layer comprising a geometry-dependent kernel.