公开(公告)号：US20230334842A1

公开(公告)日：2023-10-19

申请号：US18136252

申请日：2023-04-18

Applicant: Waymo LLC

Inventor： Alex Zihao Zhu ,  Vincent Michael Casser ,  Henrik Kretzschmar ,  Reza Mahjourian ,  Soeren Pirk

IPC: G06V10/82 ,  G06V10/774

CPC classification number: G06V10/82 ,  G06V10/774

Abstract: Methods, systems, and apparatus for processing inputs that include video frames using neural networks. In one aspect, a system comprises one or more computers configured to obtain a set of one or more training images and, for each training image, ground truth instance data that identifies, for each of one or more object instances, a corresponding region of the training image that depicts the object instance. For each training image in the set, the one or more computers process the training image using an instance segmentation neural network to generate an embedding output comprising a respective embedding for each of a plurality of output pixels. The one or more computers then train the instance segmentation neural network to minimize a loss function.

公开(公告)号：US20230281824A1

公开(公告)日：2023-09-07

申请号：US18118705

申请日：2023-03-07

Applicant: Waymo LLC

Inventor： Jieru Mei ,  Hang Yan ,  Liang-Chieh Chen ,  Siyuan Qiao ,  Yukun Zhu ,  Alex Zihao Zhu ,  Xinchen Yan ,  Henrik Kretzschmar

IPC: G06T7/11 ,  G06V20/64 ,  G06V10/82 ,  G06V20/58 ,  G01S17/89

CPC classification number: G06T7/11 ,  G06V20/64 ,  G06V10/82 ,  G06V20/58 ,  G01S17/89 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/30252 ,  G06T2207/10016 ,  G06T2210/12

Abstract: Methods, systems, and apparatus for generating a panoptic segmentation label for a sensor data sample. In one aspect, a system comprises one or more computers configured to obtain a sensor data sample characterizing a scene in an environment. The one or more computers obtain a 3D bounding box annotation at each time point for a point cloud characterizing the scene at the time point. The one or more computers obtain, for each camera image and each time point, annotation data identifying object instances depicted in the camera image, and the one or more computers generate a panoptic segmentation label for the sensor data sample characterizing the scene in the environment.