公开(公告)号：US20210365743A1

公开(公告)日：2021-11-25

申请号：US17253124

申请日：2020-06-23

Applicant: HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY

Inventor： Nong SANG ,  Chuchu HAN ,  Yuanjie SHAO ,  Ruochen ZHENG ,  Changxin GAO

IPC: G06K9/62 ,  G06K9/00 ,  G06K9/46 ,  G06T3/40 ,  G06T7/11 ,  G06T7/73 ,  G06N3/04

Abstract: The invention discloses a person search method based on person re-identification driven localization refinement. On one hand, the region of interest (ROI) conversion module converts an original input image into a small image corresponding to a ROI, and contradiction existing in part of features shared by a person re-identification network and a detection network is avoided; and on the other hand, loss of the person re-identification network can be transmitted back to the detection network in a gradient manner through the ROI conversion module, the supervision of loss of the person re-identification network for the detection bounding box output by the detection network is realized, and the adjusted detection bounding box can effectively remove background interference, contains more useful attribute information and is more suitable for person search, so that the person search accuracy is greatly improved.