公开(公告)号：US11987236B2

公开(公告)日：2024-05-21

申请号：US17408911

申请日：2021-08-23

Applicant: NEC Laboratories America, Inc.

Inventor： Pan Ji ,  Buyu Liu ,  Bingbing Zhuang ,  Manmohan Chandraker ,  Xiangyu Chen

IPC: G06K9/00 ,  B60W30/09 ,  B60W30/095 ,  G06F18/21 ,  G06T7/215 ,  G06T7/246 ,  G08G1/16

CPC classification number: B60W30/09 ,  B60W30/0956 ,  G06F18/2193 ,  G06T7/215 ,  G06T7/251 ,  G08G1/166 ,  B60W2554/40 ,  G06T2207/20084 ,  G06T2207/30261

Abstract: A method provided for 3D object localization predicts pairs of 2D bounding boxes. Each pair corresponds to a detected object in each of the two consecutive input monocular images. The method generates, for each detected object, a relative motion estimation specifying a relative motion between the two images. The method constructs an object cost volume by aggregating temporal features from the two images using the pairs of 2D bounding boxes and the relative motion estimation to predict a range of object depth candidates and a confidence score for each object depth candidate and an object depth from the object depth candidates. The method updates the relative motion estimation based on the object cost volume and the object depth to provide a refined object motion and a refined object depth. The method reconstructs a 3D bounding box for each detected object based on the refined object motion and refined object depth.

公开(公告)号：US20220063605A1

公开(公告)日：2022-03-03

申请号：US17408911

申请日：2021-08-23

Applicant: NEC Laboratories America, Inc.

Inventor： Pan Ji ,  Buyu Liu ,  Bingbing Zhuang ,  Manmohan Chandraker ,  Xiangyu Chen

IPC: B60W30/09 ,  G06T7/215 ,  G06K9/62 ,  G06T7/246 ,  G08G1/16 ,  B60W30/095

Abstract: A method provided for 3D object localization predicts pairs of 2D bounding boxes. Each pair corresponds to a detected object in each of the two consecutive input monocular images. The method generates, for each detected object, a relative motion estimation specifying a relative motion between the two images. The method constructs an object cost volume by aggregating temporal features from the two images using the pairs of 2D bounding boxes and the relative motion estimation to predict a range of object depth candidates and a confidence score for each object depth candidate and an object depth from the object depth candidates. The method updates the relative motion estimation based on the object cost volume and the object depth to provide a refined object motion and a refined object depth. The method reconstructs a 3D bounding box for each detected object based on the refined object motion and refined object depth.