公开(公告)号：US11915484B2

公开(公告)日：2024-02-27

申请号：US17304296

申请日：2021-06-17

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Zhigang Wang ,  Jian Wang ,  Errui Ding ,  Hao Sun

IPC: G06K9/46 ,  G06K9/62 ,  G06V20/52 ,  G06F18/23 ,  G06F18/214 ,  G06F18/21 ,  G06V10/762 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82 ,  G06V20/64 ,  G06V40/10

CPC classification number: G06V20/52 ,  G06F18/214 ,  G06F18/2178 ,  G06F18/23 ,  G06V10/762 ,  G06V10/764 ,  G06V10/7753 ,  G06V10/82 ,  G06V20/64 ,  G06V40/10 ,  G06V2201/07

Abstract: A method, an apparatus, device and a storage medium for generating a target re-recognition model are provided. The method may include: acquiring a set of labeled samples, a set of unlabeled samples and an initialization model obtained through supervised training; performing feature extraction on each sample in the set of the unlabeled samples by using the initialization model; clustering features extracted from the set of the unlabeled samples by using a clustering algorithm; assigning, for each sample in the set of the unlabeled samples, a pseudo label to the sample according to a cluster corresponding to the sample in a feature space; and mixing a set of samples with a pseudo label and the set of the labeled samples as a set of training samples, and performing supervised training on the initialization model to obtain a target re-recognition model.

公开(公告)号：US11379696B2

公开(公告)日：2022-07-05

申请号：US16817419

申请日：2020-03-12

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Zhigang Wang ,  Jian Wang ,  Shilei Wen ,  Errui Ding ,  Hao Sun

IPC: G06K9/62 ,  G06V10/40 ,  G06V40/10

Abstract: The present disclosure provides a pedestrian re-identification method and apparatus, computer device and readable medium. The method comprises: collecting a target image and a to-be-identified image including a pedestrian image; obtaining a feature expression of the target image and a feature expression of the to-be-identified image respectively, based on a pre-trained feature extraction model; wherein the feature extraction model is obtained by training based on a self-attention feature of a base image as well as a co-attention feature of the base image relative to a reference image; identifying whether a pedestrian in the to-be-identified image is the same pedestrian as that in the target image according to the feature expression of the target image and the feature expression of the to-be-identified image. According to the pedestrian re-identification method of the present disclosure, the accuracy of the pedestrian re-identification can be effectively improved when the feature extraction model is used to perform the pedestrian re-identification.