- 专利标题: Optimizations for dynamic object instance detection, segmentation, and structure mapping
-
申请号: US15972035申请日: 2018-05-04
-
公开(公告)号: US10586350B2公开(公告)日: 2020-03-10
- 发明人: Peter Vajda , Peizhao Zhang , Fei Yang , Yanghan Wang
- 申请人: Facebook, Inc.
- 申请人地址: US CA Menlo Park
- 专利权人: Facebook, Inc.
- 当前专利权人: Facebook, Inc.
- 当前专利权人地址: US CA Menlo Park
- 代理机构: Baker Botts L.L.P.
- 主分类号: G06K9/62
- IPC分类号: G06K9/62 ; G06K9/00 ; G06T7/73 ; G06K9/46 ; G06T7/11 ; G06K9/32
摘要:
In one embodiment, a system accesses pose probability models for predetermined parts of a body depicted in an image. Each of the pose probability models is configured for determining a probability of the associated predetermined body part being at a location in the image. The system determines a candidate pose that is defined by a set of coordinates representing candidate locations of the predetermined body parts. The system further determines a first probability score for the candidate pose based on the pose probability models and the set of coordinates of the candidate pose. A pose representation is generated for the candidate pose using a transformation model and the candidate pose. The system determines a second probability score for the pose representation based on a pose-representation probability model. The system selects the candidate pose to represent a pose of the body based on at least the first and second probability scores.
公开/授权文献
信息查询