公开(公告)号：US20240095937A1

公开(公告)日：2024-03-21

申请号：US17933756

申请日：2022-09-20

Applicant: QUALCOMM Incorporated

Inventor： David UNGER ,  Senthil Kumar YOGAMANI ,  Varun RAVI KUMAR

IPC: G06T7/50 ,  G06T7/168

CPC classification number: G06T7/50 ,  G06T7/168 ,  G06T2207/10028 ,  G06T2207/20081

Abstract: Techniques and systems are provided for generating depth information for an image. For instance, a process can include obtaining one or more images of an environment. The process can further include generating a set of features for the one or more images. The process can also include combining the set of features with one or more distance maps to generate combined feature distance information, wherein the one or more distance maps indicate distances based on relative height above a ground level. The process can further include generating depth information of the environment based on the combined feature distance information, and outputting the depth information of the environment.

公开(公告)号：US20240070541A1

公开(公告)日：2024-02-29

申请号：US18365664

申请日：2023-08-04

Applicant: QUALCOMM Incorporated

Inventor： Shubhankar Mangesh BORSE ,  Varun RAVI KUMAR ,  David UNGER ,  Senthil Kumar YOGAMANI ,  Fatih Murat PORIKLI

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: Techniques and systems are provided for training a machine learning (ML) model. A technique can include generating a first set of features for objects in images, predicting image feature labels for the first set of features, comparing the predicted image feature labels to ground truth image feature labels to evaluate a first loss function, perform a perspective transform on the first set of features to generate a birds eye view (BEV) projected image features, combining the BEV projected image features and a first set of flattened features to generate combined image features, generating a segmented BEV map of the environment based on the combined image features, comparing the segmented BEV map to a ground truth segmented BEV map to evaluate a second loss function, and training the ML model for generation of segmented BEV maps based on the evaluated first loss function and the evaluated second loss function.