发明公开
EP4358042A1 SYSTEM AND METHOD FOR PERFORMING UNIFIED HUMAN MOTION PREDICTION (HMP) FOR 2D AND 3D POSES
审中-实审
基本信息:
- 专利标题： SYSTEM AND METHOD FOR PERFORMING UNIFIED HUMAN MOTION PREDICTION (HMP) FOR 2D AND 3D POSES
- 申请号：EP22217253.8 申请日：2022-12-30
- 公开(公告)号：EP4358042A1 公开(公告)日：2024-04-24
- 发明人： ZHU, Yanjun , BAI, Chen , LU, Cheng
- 申请人： Guangzhou Xiaopeng Autopilot Technology Co., Ltd.
- 申请人地址： CN Guangzhou Guangdong Room 406-46, No.1, Yichuang Street Sino-Singapore Guangzhou Knowledge City Huangpu District
- 专利权人： Guangzhou Xiaopeng Autopilot Technology Co., Ltd.
- 当前专利权人： Guangzhou Xiaopeng Autopilot Technology Co., Ltd.
- 当前专利权人地址： CN Guangzhou Guangdong Room 406-46, No.1, Yichuang Street Sino-Singapore Guangzhou Knowledge City Huangpu District
- 代理机构： Isarpatent
- 优先权： US 202217967970 2022.10.18
- 主分类号： G06V40/20
- IPC分类号： G06V40/20 ; G06V10/82
摘要：
A system and a method for performing unified human motion prediction (HMP) are provided. In operation, the system provides a unified HMP module, which includes an encoder configured to encode a plurality of existing two-dimensional (2D) and three-dimensional (3D) pose sequences into a shared latent space V and a decoder configured to predict a plurality of predicted future 2D and 3D pose sequences based on the encoded shared latent space V, thus forming four pathways of knowledge flow. The system then trains the unified HMP module and the shared latent space V in a weakly supervised manner with input features X with actual future 2D and 3D pose sequences by minimizing a loss between the predicted future 2D and 3D pose sequences and the actual future 2D and 3D pose sequences. Once the training is complete, the unified HMP may be performed using the trained encoded shared latent space V.