VIOS-Net: A Multi-Task Fusion System for Maritime Surveillance Through Visible and Infrared Imaging DOI Creative Commons
Jie Zhan, Jiawen Li, Lihua Wu

et al.

Journal of Marine Science and Engineering, Journal Year: 2025, Volume and Issue: 13(5), P. 913 - 913

Published: May 6, 2025

Automatic ship monitoring models leveraging image recognition have become integral to regulatory applications within maritime management, with multi-source co-monitoring serving as the primary method for achieving comprehensive, round-the-clock surveillance. Despite their widespread use, existing predominantly train each data source independently or simultaneously multiple sources without fully optimizing integration of similar information. This approach, while capable all-weather detection, results in underutilization features from related and unnecessary repetition model training, leading excessive time consumption. To address these inefficiencies, this paper introduces a novel multi-task learning framework designed enhance utilization diverse information sources, thereby reducing training time, lowering costs, improving accuracy. The proposed model, VIOS-Net, integrates advantages both visible infrared meet challenges all-weather, all-day under complex environmental conditions. VIOS-Net employs Shared Bottom network architecture, utilizing shared specific feature extraction modules at model’s lower upper layers, respectively, optimize system’s capabilities maximize efficiency. experimental demonstrate that achieves an accuracy 96.20% across spectral datasets, significantly outperforming baseline ResNet-34 which attained accuracies only 4.86% 9.04% data, respectively. Moreover, reduces number parameters by 48.82% compared baseline, optimal performance multi-spectral monitoring. Extensive ablation studies further validate effectiveness individual framework.

Language: Английский

A Novel Ship Fuel Sulfur Content Estimation Method Using Improved Gaussian Plume Model and Genetic Algorithms DOI Creative Commons
Chao Wang, Hao Wu,

Wang Nini

et al.

Journal of Marine Science and Engineering, Journal Year: 2025, Volume and Issue: 13(4), P. 690 - 690

Published: March 29, 2025

Maritime transportation plays a vital role in global economic development but is also significant contributor to air pollution, especially through emissions of SO2, NOx, and CO2. Identifying non-compliance with fuel sulfur content regulations crucial for mitigating these environmental impacts, yet current methods face challenges, particularly the absence reliable CO2 concentration data. This study proposes novel inverse calculation framework estimate ship without relying on measurements. An improved Gaussian plume line source model was tailored dispersion characteristics emissions, influencing factors evaluated under varying wind field conditions. The emission intensity inversion formulated as an unconstrained multi-dimensional optimization problem, solved using genetic algorithms. By incorporating consumption data derived from basic information, fuels effectively estimated. Experimental evaluations 30 days monitoring revealed that method successfully identified 2743 ships, overall detection rate 82.72%. Among them, 131 ships were flagged suspected high-sulfur fuel, 111 confirmed be non-compliant via sampling laboratory testing, achieving accuracy 84.73%. These results demonstrate proposed approach offers efficient solution real-time enforcement diverse atmospheric conditions, contributing management maritime transport emissions.

Language: Английский

Citations

0
Unmanned Aerial Vehicles and Low-Cost Sensors for Air Quality Monitoring: A Comprehensive Review of Applications Across Diverse Emission Sources DOI

Vishal Choudhary,

Manuj Sharma,

Suresh Jain

et al.

Sustainable Cities and Society, Journal Year: 2025, Volume and Issue: unknown, P. 106409 - 106409

Published: April 1, 2025

Language: Английский

Citations

0
VIOS-Net: A Multi-Task Fusion System for Maritime Surveillance Through Visible and Infrared Imaging DOI Creative Commons
Jie Zhan, Jiawen Li, Lihua Wu

et al.

Journal of Marine Science and Engineering, Journal Year: 2025, Volume and Issue: 13(5), P. 913 - 913

Published: May 6, 2025

Automatic ship monitoring models leveraging image recognition have become integral to regulatory applications within maritime management, with multi-source co-monitoring serving as the primary method for achieving comprehensive, round-the-clock surveillance. Despite their widespread use, existing predominantly train each data source independently or simultaneously multiple sources without fully optimizing integration of similar information. This approach, while capable all-weather detection, results in underutilization features from related and unnecessary repetition model training, leading excessive time consumption. To address these inefficiencies, this paper introduces a novel multi-task learning framework designed enhance utilization diverse information sources, thereby reducing training time, lowering costs, improving accuracy. The proposed model, VIOS-Net, integrates advantages both visible infrared meet challenges all-weather, all-day under complex environmental conditions. VIOS-Net employs Shared Bottom network architecture, utilizing shared specific feature extraction modules at model’s lower upper layers, respectively, optimize system’s capabilities maximize efficiency. experimental demonstrate that achieves an accuracy 96.20% across spectral datasets, significantly outperforming baseline ResNet-34 which attained accuracies only 4.86% 9.04% data, respectively. Moreover, reduces number parameters by 48.82% compared baseline, optimal performance multi-spectral monitoring. Extensive ablation studies further validate effectiveness individual framework.

Language: Английский

Citations

0