A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing Imagery

Vessel detection technology based on marine remote sensing imagery is of great importance. However, it often faces challenges, such as small vessel targets, cloud occlusion, insufficient data volume, and severely imbalanced class distribution in datasets. These issues result in conventional models f...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhuhua Hu, Wei Wu, Ziqi Yang, Yaochi Zhao, Lewei Xu, Lingkai Kong, Yunpei Chen, Lihang Chen, Gaosheng Liu
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/14/2471
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849733768539013120
author Zhuhua Hu
Wei Wu
Ziqi Yang
Yaochi Zhao
Lewei Xu
Lingkai Kong
Yunpei Chen
Lihang Chen
Gaosheng Liu
author_facet Zhuhua Hu
Wei Wu
Ziqi Yang
Yaochi Zhao
Lewei Xu
Lingkai Kong
Yunpei Chen
Lihang Chen
Gaosheng Liu
author_sort Zhuhua Hu
collection DOAJ
description Vessel detection technology based on marine remote sensing imagery is of great importance. However, it often faces challenges, such as small vessel targets, cloud occlusion, insufficient data volume, and severely imbalanced class distribution in datasets. These issues result in conventional models failing to meet the accuracy requirements for practical applications. In this paper, we first construct a novel remote sensing vessel image dataset that includes various complex scenarios and enhance the data volume and diversity through data augmentation techniques. Secondly, we address the class imbalance between foreground (small vessels) and background in remote sensing imagery from two perspectives: the sensitivity of IoU metrics to small object localization errors and the innovative design of a cost-sensitive loss function. Specifically, at the dataset level, we select vessel targets appearing in the original dataset as templates and randomly copy–paste several instances onto arbitrary positions. This enriches the diversity of target samples per image and mitigates the impact of data imbalance on the detection task. At the algorithm level, we introduce the Normalized Wasserstein Distance (NWD) to compute the similarity between bounding boxes. This enhances the importance of small target information during training and strengthens the model’s cost-sensitive learning capabilities. Ablation studies reveal that detection performance is optimal when the weight assigned to the NWD metric in the model’s loss function matches the overall proportion of small objects in the dataset. Comparative experiments show that the proposed NWD-YOLO achieves Precision, Recall, and <inline-formula><math display="inline"><semantics><msub><mi>AP</mi><mn>50</mn></msub></semantics></math></inline-formula> scores of 0.967, 0.958, and 0.971, respectively, meeting the accuracy requirements of real-world applications.
format Article
id doaj-art-4480a5d853a64161bb7f0ac3bacee145
institution DOAJ
issn 2072-4292
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-4480a5d853a64161bb7f0ac3bacee1452025-08-20T03:07:58ZengMDPI AGRemote Sensing2072-42922025-07-011714247110.3390/rs17142471A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing ImageryZhuhua Hu0Wei Wu1Ziqi Yang2Yaochi Zhao3Lewei Xu4Lingkai Kong5Yunpei Chen6Lihang Chen7Gaosheng Liu8School of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaSchool of Cyberspace Security, Hainan University, Haikou 570228, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaSchool of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaSchool of Information and Communication Engineering, Hainan University, Haikou 570228, ChinaVessel detection technology based on marine remote sensing imagery is of great importance. However, it often faces challenges, such as small vessel targets, cloud occlusion, insufficient data volume, and severely imbalanced class distribution in datasets. These issues result in conventional models failing to meet the accuracy requirements for practical applications. In this paper, we first construct a novel remote sensing vessel image dataset that includes various complex scenarios and enhance the data volume and diversity through data augmentation techniques. Secondly, we address the class imbalance between foreground (small vessels) and background in remote sensing imagery from two perspectives: the sensitivity of IoU metrics to small object localization errors and the innovative design of a cost-sensitive loss function. Specifically, at the dataset level, we select vessel targets appearing in the original dataset as templates and randomly copy–paste several instances onto arbitrary positions. This enriches the diversity of target samples per image and mitigates the impact of data imbalance on the detection task. At the algorithm level, we introduce the Normalized Wasserstein Distance (NWD) to compute the similarity between bounding boxes. This enhances the importance of small target information during training and strengthens the model’s cost-sensitive learning capabilities. Ablation studies reveal that detection performance is optimal when the weight assigned to the NWD metric in the model’s loss function matches the overall proportion of small objects in the dataset. Comparative experiments show that the proposed NWD-YOLO achieves Precision, Recall, and <inline-formula><math display="inline"><semantics><msub><mi>AP</mi><mn>50</mn></msub></semantics></math></inline-formula> scores of 0.967, 0.958, and 0.971, respectively, meeting the accuracy requirements of real-world applications.https://www.mdpi.com/2072-4292/17/14/2471object detectionYOLOsmall objectsclass imbalancecost-sensitive
spellingShingle Zhuhua Hu
Wei Wu
Ziqi Yang
Yaochi Zhao
Lewei Xu
Lingkai Kong
Yunpei Chen
Lihang Chen
Gaosheng Liu
A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing Imagery
Remote Sensing
object detection
YOLO
small objects
class imbalance
cost-sensitive
title A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing Imagery
title_full A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing Imagery
title_fullStr A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing Imagery
title_full_unstemmed A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing Imagery
title_short A Cost-Sensitive Small Vessel Detection Method for Maritime Remote Sensing Imagery
title_sort cost sensitive small vessel detection method for maritime remote sensing imagery
topic object detection
YOLO
small objects
class imbalance
cost-sensitive
url https://www.mdpi.com/2072-4292/17/14/2471
work_keys_str_mv AT zhuhuahu acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT weiwu acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT ziqiyang acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT yaochizhao acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT leweixu acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT lingkaikong acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT yunpeichen acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT lihangchen acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT gaoshengliu acostsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT zhuhuahu costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT weiwu costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT ziqiyang costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT yaochizhao costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT leweixu costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT lingkaikong costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT yunpeichen costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT lihangchen costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery
AT gaoshengliu costsensitivesmallvesseldetectionmethodformaritimeremotesensingimagery