公开(公告)号：US20230334895A1

公开(公告)日：2023-10-19

申请号：US18337439

申请日：2023-06-20

申请人： WUHAN UNIVERSITY

发明人： Bo DU ,  Xiaoyang GUO ,  Yutian LIN ,  Chao ZHANG ,  Zheng WANG

IPC分类号： G06V40/10 ,  G06V10/80 ,  G06T7/194 ,  G06V10/82

CPC分类号： G06V40/103 ,  G06T7/194 ,  G06V10/80 ,  G06V10/82 ,  G06T2207/20221

摘要： This invention proposes a pedestrian re-identification method based on virtual samples, comprising following steps: sl) obtaining virtual persons generated by game engine, and generating the virtual samples with person labels by fusing a background of a target dataset and a pose of real persons through a multi-factor variational generation network; s2) rendering the generated virtual samples according to lighting conditions; s3) sampling the rendered virtual samples according to person attributes of target dataset; s4) constructing a training dataset according to virtual samples obtained by sampling to train a pedestrian re-identification model, and verifying identification effect of the trained model. The present invention uses a virtual image generation framework that integrates translation-rendering-sampling to narrow the distribution between virtual images and real images as much as possible to generate virtual samples, and conduct person re-identification model training, which can be effectively and effectively applied to pedestrian datasets in real scenes.