skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

An anchor-free detector designed for dense small water object detection

Journal of physics. Conference series, 2023-06, Vol.2513 (1), p.12008 [Peer Reviewed Journal]

Published under licence by IOP Publishing Ltd ;Published under licence by IOP Publishing Ltd. This work is published under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;ISSN: 1742-6588 ;EISSN: 1742-6596 ;DOI: 10.1088/1742-6596/2513/1/012008

Full text available

Citations Cited by
  • Title:
    An anchor-free detector designed for dense small water object detection
  • Author: Wei, Tao ; Li, Zi-Xin ; Wang, Yu-Long
  • Subjects: Algorithms ; Cost function ; Object recognition ; Physics ; Training
  • Is Part Of: Journal of physics. Conference series, 2023-06, Vol.2513 (1), p.12008
  • Description: Abstract The detection of dense small objects on the water surface is one of the hot topics in object detection. In this paper, a one-to-many label assignment strategy based on the OTA algorithm, which is applied to anchor-free detector, is proposed to improve the detection accuracy of dense small objects on water surface. To be specific, one-to-many label assignment means that a ground truth (GT) corresponding to multiple prediction boxes is conducted globally. The cost function used by OTA algorithm is improved to make the distribution of positive and negative samples more reasonable. Meanwhile, an efficient training strategy is designed to accelerate network convergence by adding L1 loss in the last stage of training. The results show that the proposed strategies achieve 87.9% average precision (AP). Compared to the original algorithm, we achieve 3.3% relative improvement for the detection precision of dense small objects.
  • Publisher: Bristol: IOP Publishing
  • Language: English
  • Identifier: ISSN: 1742-6588
    EISSN: 1742-6596
    DOI: 10.1088/1742-6596/2513/1/012008
  • Source: IOP Publishing Free Content
    IOPscience (Open Access)
    GFMER Free Medical Journals
    ProQuest Central
Back to results list
Go to Previous pagePrevious Result  6 NextGo to Next page
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait