Personal Information

  • Doctoral Supervisor
  • Master Tutor
  • (Professor)

  • Gender:

    Male

  • Contact Information:

    15827188114

  • Status:

    Employed

  • School/Department:

    测绘遥感信息工程全国重点实验室

  • Date of Birth:

    1976-03-21

  • Alma Mater:

    武汉大学

  • Status:

    Employed

  • School/Department:

    测绘遥感信息工程全国重点实验室

  • Date of Employment:

    2004-07-01

  • Administrative Position:

    副主任

  • Business Address:

    武汉大学星湖实验大楼713

  • Contact Information:

    15827188114

Other Contact Information

  • ZipCode

  • Fax

  • PostalAddress

  • Telephone

  • Email

Paper Publications

Current position: Home > Scientific Research > Paper Publications

Enhancing Object Detection With Fourier Series

  • Time:2025-04-01
  • Hits:

  • DOI number:

    10.1109/tpami.2025.3526990

  • Affiliation of Author(s):

    Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & Re, Wuhan 430079, Peoples R China

  • Journal:

    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE

  • Funded by:

    This work was supported in part by the National Key Research and Development Program of China under

  • Key Words:

    Fourier series,Object detection,Shape,Mathematical models,Transformers,Optimization,Vectors,Predictive models,Image segmentation,Gaussian distribution,closed curve of arbitrary shape,and directional vector

  • Abstract:

    Traditional object detection models often lose the detailed outline information of the object. To address this problem, we propose the Fourier Series Object Detection (FSD). It encodes the object's outline closed curve into two one-dimensional periodic Fourier series. The Fourier Series Model (FSM) is constructed to regress the Fourier series for each object in the image. Thus, during inference, the detailed outline information of each object can be retrieved. We introduce Rolling Optimization Matching for Fourier loss to ensure that the model's learning process is not affected by the sequence

  • Co-author:

    Ming,Jiang, Yong,Hong, Hui,Hu, Yaorong,Cen

  • Indexed by:

    Journal paper

  • Correspondence Author:

    Miaozhong,Xu, Zhenfeng,Shao, Zhongyuan,Lu

  • Document Type:

    Article

  • Volume:

    47

  • Issue:

    4

  • Page Number:

    2581-2596

  • ISSN No.:

    0162-8828

  • Translation or Not:

    no

  • Date of Publication:

    2025-04-01

Copyright @ 2017 Wuhan University

Back
Top