公开(公告)号：US20200219316A1

公开(公告)日：2020-07-09

申请号：US16733234

申请日：2020-01-02

Applicant: QUALCOMM Incorporated

Inventor： Young-Ki BAIK ,  Hyun-Mook CHO ,  Duck Hoon KIM ,  Jeong-Kyun LEE ,  ChaeSeong LIM ,  Hee-Seok LEE

IPC: G06T17/10 ,  G06T7/73 ,  G05D1/02

Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.

公开(公告)号：US20200218913A1

公开(公告)日：2020-07-09

申请号：US16733222

申请日：2020-01-02

Applicant: QUALCOMM Incorporated

Inventor： Jayakrishnan UNNIKRISHNAN ,  Avdhut JOSHI ,  Shivam AGARWAL ,  Amir SALIMI ,  Sree Sesha Aravind VADREVU ,  Gautam SACHDEVA ,  Yoga Y NADARAAJAN ,  Ravi Teja SUKHAVASI ,  Aolin XU ,  Xinzhou WU ,  Young-Ki BAIK ,  Duck Hoon KIM ,  Hyun-Mook CHO

IPC: G06K9/00 ,  G06T7/277 ,  G06T7/246 ,  G01S13/931 ,  B60R11/04

Abstract: Disclosed are techniques for determining a motion state of a target object. In an aspect, an on-board computer of an ego vehicle detects the target object in one or more images, determines one or more first attributes of the target object based on measurements of the one or more images, determines one or more second attributes of the target object based on measurements of a map of a roadway on which the target object is travelling, and determines the motion state of the target object based on the one or more first attributes and the one or more second attributes of the target object.

公开(公告)号：US20230112799A1

公开(公告)日：2023-04-13

申请号：US18047538

申请日：2022-10-18

Applicant: QUALCOMM Incorporated

Inventor： Young-Ki BAIK ,  Hyun-Mook CHO ,  Duck Hoon KIM ,  Jeong-Kyun LEE ,  Chaeseong LIM ,  Hee-Seok LEE

IPC: G06T17/10 ,  G06T7/73 ,  G05D1/02 ,  G06T7/70

Abstract: Disclosed are techniques for estimating a 3D bounding box (3DBB) from a 2D bounding box (2DBB). Conventional techniques to estimate 3DBB from 2DBB rely upon classifying target vehicles within the 2DBB. When the target vehicle is misclassified, the projected bounding box from the estimated 3DBB is inaccurate. To address such issues, it is proposed to estimate the 3DBB without relying upon classifying the target vehicle.