Knowledge-Transfer-Based Bidirectional Vessel Monitoring System for Remote and Nearshore Images
Vessel monitoring technology involves the application of remote sensing technologies to detect and identify vessels in various environments, which is critical for monitoring vessel traffic, identifying potential threats, and facilitating maritime safety and security to achieve real-time maritime awa...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/11/5/1068 |
| _version_ | 1797599510555262976 |
|---|---|
| author | Jiawen Li Yun Yang Xin Li Jiahua Sun Ronghui Li |
| author_facet | Jiawen Li Yun Yang Xin Li Jiahua Sun Ronghui Li |
| author_sort | Jiawen Li |
| collection | DOAJ |
| description | Vessel monitoring technology involves the application of remote sensing technologies to detect and identify vessels in various environments, which is critical for monitoring vessel traffic, identifying potential threats, and facilitating maritime safety and security to achieve real-time maritime awareness in military and civilian domains. However, most existing vessel monitoring models tend to focus on a single remote sensing information source, leading to limited detection functionality and underutilization of available information. In light of these limitations, this paper proposes a comprehensive ship monitoring system that integrates remote satellite devices and nearshore detection equipment. The system employs ResNet, a deep learning model, along with data augmentation and transfer learning techniques to enable bidirectional detection of satellite cloud images and nearshore outboard profile images, thereby alleviating prevailing issues such as low detection accuracy, homogeneous functionality, and poor image recognition applicability. Empirical findings based on two real-world vessel monitoring datasets demonstrate that the proposed system consistently performs best in both nearshore identification and remote detection. Additionally, extensive supplementary experiments were conducted to evaluate the effectiveness of different modules and discuss the constraints of current deep learning-based vessel monitoring models. |
| first_indexed | 2024-03-11T03:35:30Z |
| format | Article |
| id | doaj.art-6d87d41ddcbb4d38a0f79d2bbc981c84 |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-11T03:35:30Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-6d87d41ddcbb4d38a0f79d2bbc981c842023-11-18T02:00:55ZengMDPI AGJournal of Marine Science and Engineering2077-13122023-05-01115106810.3390/jmse11051068Knowledge-Transfer-Based Bidirectional Vessel Monitoring System for Remote and Nearshore ImagesJiawen Li0Yun Yang1Xin Li2Jiahua Sun3Ronghui Li4Naval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang 524005, ChinaNaval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang 524005, ChinaNaval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang 524005, ChinaNaval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang 524005, ChinaNaval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang 524005, ChinaVessel monitoring technology involves the application of remote sensing technologies to detect and identify vessels in various environments, which is critical for monitoring vessel traffic, identifying potential threats, and facilitating maritime safety and security to achieve real-time maritime awareness in military and civilian domains. However, most existing vessel monitoring models tend to focus on a single remote sensing information source, leading to limited detection functionality and underutilization of available information. In light of these limitations, this paper proposes a comprehensive ship monitoring system that integrates remote satellite devices and nearshore detection equipment. The system employs ResNet, a deep learning model, along with data augmentation and transfer learning techniques to enable bidirectional detection of satellite cloud images and nearshore outboard profile images, thereby alleviating prevailing issues such as low detection accuracy, homogeneous functionality, and poor image recognition applicability. Empirical findings based on two real-world vessel monitoring datasets demonstrate that the proposed system consistently performs best in both nearshore identification and remote detection. Additionally, extensive supplementary experiments were conducted to evaluate the effectiveness of different modules and discuss the constraints of current deep learning-based vessel monitoring models.https://www.mdpi.com/2077-1312/11/5/1068ship classificationsynthetic-aperture radar (SAR)deep learningtransfer learningvessel monitoring system |
| spellingShingle | Jiawen Li Yun Yang Xin Li Jiahua Sun Ronghui Li Knowledge-Transfer-Based Bidirectional Vessel Monitoring System for Remote and Nearshore Images Journal of Marine Science and Engineering ship classification synthetic-aperture radar (SAR) deep learning transfer learning vessel monitoring system |
| title | Knowledge-Transfer-Based Bidirectional Vessel Monitoring System for Remote and Nearshore Images |
| title_full | Knowledge-Transfer-Based Bidirectional Vessel Monitoring System for Remote and Nearshore Images |
| title_fullStr | Knowledge-Transfer-Based Bidirectional Vessel Monitoring System for Remote and Nearshore Images |
| title_full_unstemmed | Knowledge-Transfer-Based Bidirectional Vessel Monitoring System for Remote and Nearshore Images |
| title_short | Knowledge-Transfer-Based Bidirectional Vessel Monitoring System for Remote and Nearshore Images |
| title_sort | knowledge transfer based bidirectional vessel monitoring system for remote and nearshore images |
| topic | ship classification synthetic-aperture radar (SAR) deep learning transfer learning vessel monitoring system |
| url | https://www.mdpi.com/2077-1312/11/5/1068 |
| work_keys_str_mv | AT jiawenli knowledgetransferbasedbidirectionalvesselmonitoringsystemforremoteandnearshoreimages AT yunyang knowledgetransferbasedbidirectionalvesselmonitoringsystemforremoteandnearshoreimages AT xinli knowledgetransferbasedbidirectionalvesselmonitoringsystemforremoteandnearshoreimages AT jiahuasun knowledgetransferbasedbidirectionalvesselmonitoringsystemforremoteandnearshoreimages AT ronghuili knowledgetransferbasedbidirectionalvesselmonitoringsystemforremoteandnearshoreimages |