公开(公告)号：US11373067B2

公开(公告)日：2022-06-28

申请号：US16526073

申请日：2019-07-30

申请人： NEC Laboratories America, Inc.

发明人： Samuel Schulter ,  Ziyan Wang ,  Buyu Liu ,  Manmohan Chandraker

IPC分类号： G06K9/62 ,  B60R11/04 ,  G05D1/02 ,  G06N3/02 ,  G06V20/56 ,  H04N5/32 ,  B60W50/14 ,  B60W60/00 ,  G06N3/04 ,  G06N3/08 ,  G06V10/82 ,  H04N5/232

摘要： A method for implementing parametric models for scene representation to improve autonomous task performance includes generating an initial map of a scene based on at least one image corresponding to a perspective view of the scene, the initial map including a non-parametric top-view representation of the scene, implementing a parametric model to obtain a scene element representation based on the initial map, the scene element representation providing a description of one or more scene elements of the scene and corresponding to an estimated semantic layout of the scene, identifying one or more predicted locations of the one or more scene elements by performing three-dimensional localization based on the at least one image, and obtaining an overlay for performing an autonomous task by placing the one or more scene elements with the one or more respective predicted locations onto the scene element representation.

公开(公告)号：US20200050900A1

公开(公告)日：2020-02-13

申请号：US16526073

申请日：2019-07-30

申请人： NEC Laboratories America, Inc.

发明人： Samuel Schulter ,  Ziyan Wang ,  Buyu Liu ,  Manmohan Chandraker

IPC分类号： G06K9/62 ,  G05D1/02 ,  G06K9/00 ,  B60R11/04 ,  H04N5/232 ,  G06N3/02

摘要： A method for implementing parametric models for scene representation to improve autonomous task performance includes generating an initial map of a scene based on at least one image corresponding to a perspective view of the scene, the initial map including a non-parametric top-view representation of the scene, implementing a parametric model to obtain a scene element representation based on the initial map, the scene element representation providing a description of one or more scene elements of the scene and corresponding to an estimated semantic layout of the scene, identifying one or more predicted locations of the one or more scene elements by performing three-dimensional localization based on the at least one image, and obtaining an overlay for performing an autonomous task by placing the one or more scene elements with the one or more respective predicted locations onto the scene element representation.