Addressing unfamiliar ship type recognition in real-scenario vessel monitoring: a multi-angle metric networks framework
Intelligent ship monitoring technology, driven by its exceptional data fitting ability, has emerged as a crucial component within the field of intelligent maritime perception. However, existing deep learning-based ship monitoring studies primarily focus on minimizing the discrepancy between predicte...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Marine Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmars.2024.1516586/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832591593403580416 |
|---|---|
| author | Jiahua Sun Jiawen Li Jiawen Li Jiawen Li Jiawen Li Ronghui Li Ronghui Li Ronghui Li Langtao Wu Liang Cao Liang Cao Liang Cao Liang Cao Molin Sun Molin Sun Molin Sun |
| author_facet | Jiahua Sun Jiawen Li Jiawen Li Jiawen Li Jiawen Li Ronghui Li Ronghui Li Ronghui Li Langtao Wu Liang Cao Liang Cao Liang Cao Liang Cao Molin Sun Molin Sun Molin Sun |
| author_sort | Jiahua Sun |
| collection | DOAJ |
| description | Intelligent ship monitoring technology, driven by its exceptional data fitting ability, has emerged as a crucial component within the field of intelligent maritime perception. However, existing deep learning-based ship monitoring studies primarily focus on minimizing the discrepancy between predicted and true labels during model training. This approach, unfortunately, restricts the model to learning only from labeled ship samples within the training set, limiting its capacity to recognize new and unseen ship categories. To address this challenge and enhance the model’s generalization ability and adaptability, a novel framework is presented, termed MultiAngle Metric Networks. The proposed framework incorporates ResNet as its foundation. By employing a novel multi-scale loss function and a new similarity measure, the framework effectively learns ship patterns by minimizing sample distances within the same category and maximizing distances between samples of different categories. The experimental results indicate that the proposed framework achieves the highest level of ship monitoring accuracy when evaluated on three distinct ship monitoring datasets. Even in the case of unfamiliar ships, where the detection performance of conventional models significantly deteriorates, the framework maintains stable and efficient detection capabilities. These experimental results highlight the framework’s ability to effectively generalize its understanding beyond the training samples and adapt to real-world scenarios. |
| format | Article |
| id | doaj-art-a097799237df4760b34e93b59801802c |
| institution | Kabale University |
| issn | 2296-7745 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Marine Science |
| spelling | doaj-art-a097799237df4760b34e93b59801802c2025-01-22T09:51:36ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452025-01-011110.3389/fmars.2024.15165861516586Addressing unfamiliar ship type recognition in real-scenario vessel monitoring: a multi-angle metric networks frameworkJiahua Sun0Jiawen Li1Jiawen Li2Jiawen Li3Jiawen Li4Ronghui Li5Ronghui Li6Ronghui Li7Langtao Wu8Liang Cao9Liang Cao10Liang Cao11Liang Cao12Molin Sun13Molin Sun14Molin Sun15Naval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang, ChinaNaval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang, ChinaKey Laboratory of Philosophy and Social Science in Hainan Province of Hainan Free Trade Port International Shipping Development and Property Digitization, Hainan Vocational University of Science and Technology, Haikou, ChinaTechnical Research Center for Ship Intelligence and Safety Engineering of Guangdong Province, Zhanjiang, Guangdong, ChinaGuangdong Provincial Key Laboratory of Intelligent Equipment for South China Sea Marine Ranching, Zhanjiang, Guangdong, ChinaNaval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang, ChinaKey Laboratory of Philosophy and Social Science in Hainan Province of Hainan Free Trade Port International Shipping Development and Property Digitization, Hainan Vocational University of Science and Technology, Haikou, ChinaTechnical Research Center for Ship Intelligence and Safety Engineering of Guangdong Province, Zhanjiang, Guangdong, ChinaNaval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang, ChinaNaval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang, ChinaKey Laboratory of Philosophy and Social Science in Hainan Province of Hainan Free Trade Port International Shipping Development and Property Digitization, Hainan Vocational University of Science and Technology, Haikou, ChinaTechnical Research Center for Ship Intelligence and Safety Engineering of Guangdong Province, Zhanjiang, Guangdong, ChinaGuangdong Provincial Key Laboratory of Intelligent Equipment for South China Sea Marine Ranching, Zhanjiang, Guangdong, ChinaNaval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang, ChinaKey Laboratory of Philosophy and Social Science in Hainan Province of Hainan Free Trade Port International Shipping Development and Property Digitization, Hainan Vocational University of Science and Technology, Haikou, ChinaTechnical Research Center for Ship Intelligence and Safety Engineering of Guangdong Province, Zhanjiang, Guangdong, ChinaIntelligent ship monitoring technology, driven by its exceptional data fitting ability, has emerged as a crucial component within the field of intelligent maritime perception. However, existing deep learning-based ship monitoring studies primarily focus on minimizing the discrepancy between predicted and true labels during model training. This approach, unfortunately, restricts the model to learning only from labeled ship samples within the training set, limiting its capacity to recognize new and unseen ship categories. To address this challenge and enhance the model’s generalization ability and adaptability, a novel framework is presented, termed MultiAngle Metric Networks. The proposed framework incorporates ResNet as its foundation. By employing a novel multi-scale loss function and a new similarity measure, the framework effectively learns ship patterns by minimizing sample distances within the same category and maximizing distances between samples of different categories. The experimental results indicate that the proposed framework achieves the highest level of ship monitoring accuracy when evaluated on three distinct ship monitoring datasets. Even in the case of unfamiliar ships, where the detection performance of conventional models significantly deteriorates, the framework maintains stable and efficient detection capabilities. These experimental results highlight the framework’s ability to effectively generalize its understanding beyond the training samples and adapt to real-world scenarios.https://www.frontiersin.org/articles/10.3389/fmars.2024.1516586/fullship classificationdeep learningfew-shot learningmaritime managementvessel monitoring |
| spellingShingle | Jiahua Sun Jiawen Li Jiawen Li Jiawen Li Jiawen Li Ronghui Li Ronghui Li Ronghui Li Langtao Wu Liang Cao Liang Cao Liang Cao Liang Cao Molin Sun Molin Sun Molin Sun Addressing unfamiliar ship type recognition in real-scenario vessel monitoring: a multi-angle metric networks framework Frontiers in Marine Science ship classification deep learning few-shot learning maritime management vessel monitoring |
| title | Addressing unfamiliar ship type recognition in real-scenario vessel monitoring: a multi-angle metric networks framework |
| title_full | Addressing unfamiliar ship type recognition in real-scenario vessel monitoring: a multi-angle metric networks framework |
| title_fullStr | Addressing unfamiliar ship type recognition in real-scenario vessel monitoring: a multi-angle metric networks framework |
| title_full_unstemmed | Addressing unfamiliar ship type recognition in real-scenario vessel monitoring: a multi-angle metric networks framework |
| title_short | Addressing unfamiliar ship type recognition in real-scenario vessel monitoring: a multi-angle metric networks framework |
| title_sort | addressing unfamiliar ship type recognition in real scenario vessel monitoring a multi angle metric networks framework |
| topic | ship classification deep learning few-shot learning maritime management vessel monitoring |
| url | https://www.frontiersin.org/articles/10.3389/fmars.2024.1516586/full |
| work_keys_str_mv | AT jiahuasun addressingunfamiliarshiptyperecognitioninrealscenariovesselmonitoringamultianglemetricnetworksframework AT jiawenli addressingunfamiliarshiptyperecognitioninrealscenariovesselmonitoringamultianglemetricnetworksframework AT jiawenli addressingunfamiliarshiptyperecognitioninrealscenariovesselmonitoringamultianglemetricnetworksframework AT jiawenli addressingunfamiliarshiptyperecognitioninrealscenariovesselmonitoringamultianglemetricnetworksframework AT jiawenli addressingunfamiliarshiptyperecognitioninrealscenariovesselmonitoringamultianglemetricnetworksframework AT ronghuili addressingunfamiliarshiptyperecognitioninrealscenariovesselmonitoringamultianglemetricnetworksframework AT ronghuili addressingunfamiliarshiptyperecognitioninrealscenariovesselmonitoringamultianglemetricnetworksframework AT ronghuili addressingunfamiliarshiptyperecognitioninrealscenariovesselmonitoringamultianglemetricnetworksframework AT langtaowu addressingunfamiliarshiptyperecognitioninrealscenariovesselmonitoringamultianglemetricnetworksframework AT liangcao addressingunfamiliarshiptyperecognitioninrealscenariovesselmonitoringamultianglemetricnetworksframework AT liangcao addressingunfamiliarshiptyperecognitioninrealscenariovesselmonitoringamultianglemetricnetworksframework AT liangcao addressingunfamiliarshiptyperecognitioninrealscenariovesselmonitoringamultianglemetricnetworksframework AT liangcao addressingunfamiliarshiptyperecognitioninrealscenariovesselmonitoringamultianglemetricnetworksframework AT molinsun addressingunfamiliarshiptyperecognitioninrealscenariovesselmonitoringamultianglemetricnetworksframework AT molinsun addressingunfamiliarshiptyperecognitioninrealscenariovesselmonitoringamultianglemetricnetworksframework AT molinsun addressingunfamiliarshiptyperecognitioninrealscenariovesselmonitoringamultianglemetricnetworksframework |