YOLO-LPSS: A Lightweight and Precise Detection Model for Small Sea Ships

The accurate detection of small ships based on images or vision is critical for many scenarios, like maritime surveillance, port security, and navigation safety. However, achieving accurate detection for small ships is a challenge for cost-efficiency models; while the models could meet this requirem...

Full description

Saved in:
Bibliographic Details
Main Authors: Liran Shen, Tianchun Gao, Qingbo Yin
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Journal of Marine Science and Engineering
Subjects:
Online Access:https://www.mdpi.com/2077-1312/13/5/925
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849711816877277184
author Liran Shen
Tianchun Gao
Qingbo Yin
author_facet Liran Shen
Tianchun Gao
Qingbo Yin
author_sort Liran Shen
collection DOAJ
description The accurate detection of small ships based on images or vision is critical for many scenarios, like maritime surveillance, port security, and navigation safety. However, achieving accurate detection for small ships is a challenge for cost-efficiency models; while the models could meet this requirement, they have unacceptable computation costs for real-time surveillance. We propose YOLO-LPSS, a novel model designed to significantly improve small ship detection accuracy with low computation cost. The characteristics of YOLO-LPSS are as follows: (1) Strengthening the backbone’s ability to extract and emphasize features relevant to small ship objects, particularly in semantic-rich layers. (2) A sophisticated, learnable method for up-sampling processes is employed, taking into account both deep image information and semantic information. (3) Introducing a post-processing mechanism in the final output of the resampling process to restore the missing local region features in the high-resolution feature map and capture the global-dependence features. The experimental results show that YOLO-LPSS outperforms the known YOLOv8 nano baseline and other works, and the number of parameters increases by only 0.33 M compared to the original YOLOv8n while achieving 0.796 and 0.831 AP<sup>50:95</sup> in classes consisting mainly of small ship targets (the bounding box of the target area is less than 5% of the image resolution), which is 3–5% higher than the vanilla model and recent SOTA models.
format Article
id doaj-art-315e787d07694fdfa001f51d7dc0f56f
institution DOAJ
issn 2077-1312
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Journal of Marine Science and Engineering
spelling doaj-art-315e787d07694fdfa001f51d7dc0f56f2025-08-20T03:14:31ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-05-0113592510.3390/jmse13050925YOLO-LPSS: A Lightweight and Precise Detection Model for Small Sea ShipsLiran Shen0Tianchun Gao1Qingbo Yin2College of Marine Electrical Engineering, Dalian Maritime University, Dalian 116023, ChinaCollege of Marine Electrical Engineering, Dalian Maritime University, Dalian 116023, ChinaCollege of Information Science and Technology, Dalian Maritime University, Dalian 116023, ChinaThe accurate detection of small ships based on images or vision is critical for many scenarios, like maritime surveillance, port security, and navigation safety. However, achieving accurate detection for small ships is a challenge for cost-efficiency models; while the models could meet this requirement, they have unacceptable computation costs for real-time surveillance. We propose YOLO-LPSS, a novel model designed to significantly improve small ship detection accuracy with low computation cost. The characteristics of YOLO-LPSS are as follows: (1) Strengthening the backbone’s ability to extract and emphasize features relevant to small ship objects, particularly in semantic-rich layers. (2) A sophisticated, learnable method for up-sampling processes is employed, taking into account both deep image information and semantic information. (3) Introducing a post-processing mechanism in the final output of the resampling process to restore the missing local region features in the high-resolution feature map and capture the global-dependence features. The experimental results show that YOLO-LPSS outperforms the known YOLOv8 nano baseline and other works, and the number of parameters increases by only 0.33 M compared to the original YOLOv8n while achieving 0.796 and 0.831 AP<sup>50:95</sup> in classes consisting mainly of small ship targets (the bounding box of the target area is less than 5% of the image resolution), which is 3–5% higher than the vanilla model and recent SOTA models.https://www.mdpi.com/2077-1312/13/5/925small ship detectiondeep learningdynamic up-samplelightweight model
spellingShingle Liran Shen
Tianchun Gao
Qingbo Yin
YOLO-LPSS: A Lightweight and Precise Detection Model for Small Sea Ships
Journal of Marine Science and Engineering
small ship detection
deep learning
dynamic up-sample
lightweight model
title YOLO-LPSS: A Lightweight and Precise Detection Model for Small Sea Ships
title_full YOLO-LPSS: A Lightweight and Precise Detection Model for Small Sea Ships
title_fullStr YOLO-LPSS: A Lightweight and Precise Detection Model for Small Sea Ships
title_full_unstemmed YOLO-LPSS: A Lightweight and Precise Detection Model for Small Sea Ships
title_short YOLO-LPSS: A Lightweight and Precise Detection Model for Small Sea Ships
title_sort yolo lpss a lightweight and precise detection model for small sea ships
topic small ship detection
deep learning
dynamic up-sample
lightweight model
url https://www.mdpi.com/2077-1312/13/5/925
work_keys_str_mv AT liranshen yololpssalightweightandprecisedetectionmodelforsmallseaships
AT tianchungao yololpssalightweightandprecisedetectionmodelforsmallseaships
AT qingboyin yololpssalightweightandprecisedetectionmodelforsmallseaships