- 专利标题: Three dimensional bounding box estimation from two dimensional images
-
申请号: US16947251申请日: 2020-07-24
-
公开(公告)号: US11688161B2公开(公告)日: 2023-06-27
- 发明人: Arsalan Mousavian , John Patrick Flynn , Dragomir Dimitrov Anguelov
- 申请人: Zoox, Inc.
- 申请人地址: US CA Foster City
- 专利权人: Zoox, Inc.
- 当前专利权人: Zoox, Inc.
- 当前专利权人地址: US CA Foster City
- 代理机构: Lee & Hayes, P.C.
- 主分类号: G06K9/00
- IPC分类号: G06K9/00 ; G06V10/82 ; G06T11/60 ; G06T7/50 ; G06T7/70 ; G06V10/44 ; G06V10/20 ; G06V20/58
摘要:
A three dimensional bounding box is determined from a two dimensional image. A two dimensional bounding box is calculated based on a detected object within the image. A three dimensional bounding box is parameterized as having a yaw angle, dimensions, and a position. The yaw angle is defined as the angle between a ray passing through a center of the two dimensional bounding box and an orientation of the three dimensional bounding box. The yaw angle and dimensions are determined by passing the portion of the image within the two dimensional bounding box through a trained convolutional neural network. The three dimensional bounding box is then positioned such that the projection of the three dimensional bounding box into the image aligns with the two dimensional bounding box previously detected. Characteristics of the three dimensional bounding box are then communicated to an autonomous system for collision and obstacle avoidance.
信息查询