Next Article in Journal
The Voltage Balance Control Strategy of Static Var Generators DC-Side Capacitors Based on Fuzzy-PI Adaptive Cascaded H-Bridge
Previous Article in Journal
Spatiotemporal Activity Mapping for Enhanced Multi-Object Detection with Reduced Resource Utilization
Previous Article in Special Issue
MFVC: Urban Traffic Scene Video Caption Based on Multimodal Fusion
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Electronics
Volume 12
Issue 1
10.3390/electronics12010038
electronics-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Analysis of Scale Sensitivity of Ship Detection in an Anchor-Free Deep Learning Framework

by
Yongxin Jiang
1,
Li Huang
2,
Zhiyou Zhang
1,
Bu Nie
3 and
Fan Zhang
4,*
1
Department of Navigation, Dalian Naval Academy, Dalian 116018, China
2
School of Computer Science, Wuhan University, Wuhan 430072, China
3
The 722th Institute, China State Shipbuilding Corporation, Wuhan 430010, China
4
School of Navigation, Wuhan University of Technology, Wuhan 430070, China
*
Author to whom correspondence should be addressed.
Electronics 2023, 12(1), 38; https://doi.org/10.3390/electronics12010038
Submission received: 27 October 2022 / Revised: 13 December 2022 / Accepted: 15 December 2022 / Published: 22 December 2022
(This article belongs to the Special Issue Multimodal Signal, Image and Video Analysis and Application)
Browse Figures
Versions Notes

Abstract

Ship detection is an important task in sea surveillance. In the past decade, deep learning-based methods have been proposed for ship detection from images and videos. Convolutional features are observed to be very effective in representing ship objects. However, the scales of convolution often lead to different capacities of feature representation. It is unclear how the scale influences the performance of deep learning methods in ship detection. To this end, this paper studies the scale sensitivity of ship detection in an anchor-free deep learning framework. Specifically, we employ the classical CenterNet as the base and analyze the influence of the size, the depth, and the fusion strategy of convolution features on multi-scale ship target detection. Experiments show that, for small targets, the features obtained from the top-down path fusion can improve the detection performance more significantly than that from the bottom-up path fusion; on the contrary, the bottom-up path fusion achieves better detection performance on larger targets.
Keywords: ship detection; multi-scale features; convolutional neural network; object detection; scale sensitivity ship detection; multi-scale features; convolutional neural network; object detection; scale sensitivity

Share and Cite

MDPI and ACS Style

Jiang, Y.; Huang, L.; Zhang, Z.; Nie, B.; Zhang, F. Analysis of Scale Sensitivity of Ship Detection in an Anchor-Free Deep Learning Framework. Electronics 2023, 12, 38. https://doi.org/10.3390/electronics12010038

AMA Style

Jiang Y, Huang L, Zhang Z, Nie B, Zhang F. Analysis of Scale Sensitivity of Ship Detection in an Anchor-Free Deep Learning Framework. Electronics. 2023; 12(1):38. https://doi.org/10.3390/electronics12010038

Chicago/Turabian Style

Jiang, Yongxin, Li Huang, Zhiyou Zhang, Bu Nie, and Fan Zhang. 2023. "Analysis of Scale Sensitivity of Ship Detection in an Anchor-Free Deep Learning Framework" Electronics 12, no. 1: 38. https://doi.org/10.3390/electronics12010038

APA Style

Jiang, Y., Huang, L., Zhang, Z., Nie, B., & Zhang, F. (2023). Analysis of Scale Sensitivity of Ship Detection in an Anchor-Free Deep Learning Framework. Electronics, 12(1), 38. https://doi.org/10.3390/electronics12010038

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop