OptWake-YOLO: a lightweight and efficient ship wake detection model based on optical remote sensing images
IntroductionShip wakes exhibit more distinctive characteristics than vessels themselves, making wake detection more feasible than direct ship detection. However, challenges persist due to sea surface interference, meteorological conditions, and coastal structures, while practical applications demand...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-08-01
|
| Series: | Frontiers in Marine Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmars.2025.1624323/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850052112029843456 |
|---|---|
| author | Runxi Qiu Nan Bi Chaoyue Yin |
| author_facet | Runxi Qiu Nan Bi Chaoyue Yin |
| author_sort | Runxi Qiu |
| collection | DOAJ |
| description | IntroductionShip wakes exhibit more distinctive characteristics than vessels themselves, making wake detection more feasible than direct ship detection. However, challenges persist due to sea surface interference, meteorological conditions, and coastal structures, while practical applications demand lightweight models with fast detection speeds.MethodsWe propose OptWake-YOLO, a lightweight ship wake detection model with three key innovations: A RepConv-based RCEA module in the Backbone combining efficient layer aggregation with reparameterization to enhance feature extraction. An Adaptive Dynamic Feature Fusion Network (ADFFN) in the Neck integrating channel attention with Dynamic Upsampling (Dysample). A Shared Lightweight Object Detection Head (SLODH) using parameter sharing and Group Normalization.ResultsExperiments on the SWIM dataset show OptWake-YOLO improves mAP50 by 1.5% (to 93.2%) and mAP50-95 by 2.9% (to 66.5%) compared to YOLOv11n, while reducing parameters by 40.7% (to 1.6M) and computation by 25.8% (to 4.9 GFLOPs), maintaining 303 FPS speed.DiscussionThe model demonstrates superior performance in complex maritime conditions through: RCEA's multi-branch feature extraction. ADFFN's adaptive multi-scale fusion. SLODH's efficient detection architecture. Ablation studies confirm each component's contribution to balancing accuracy and efficiency for real-time wake detection. |
| format | Article |
| id | doaj-art-523b19f87c344b69a4eadbc5c4e1deaf |
| institution | DOAJ |
| issn | 2296-7745 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Marine Science |
| spelling | doaj-art-523b19f87c344b69a4eadbc5c4e1deaf2025-08-20T02:52:56ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452025-08-011210.3389/fmars.2025.16243231624323OptWake-YOLO: a lightweight and efficient ship wake detection model based on optical remote sensing imagesRunxi QiuNan BiChaoyue YinIntroductionShip wakes exhibit more distinctive characteristics than vessels themselves, making wake detection more feasible than direct ship detection. However, challenges persist due to sea surface interference, meteorological conditions, and coastal structures, while practical applications demand lightweight models with fast detection speeds.MethodsWe propose OptWake-YOLO, a lightweight ship wake detection model with three key innovations: A RepConv-based RCEA module in the Backbone combining efficient layer aggregation with reparameterization to enhance feature extraction. An Adaptive Dynamic Feature Fusion Network (ADFFN) in the Neck integrating channel attention with Dynamic Upsampling (Dysample). A Shared Lightweight Object Detection Head (SLODH) using parameter sharing and Group Normalization.ResultsExperiments on the SWIM dataset show OptWake-YOLO improves mAP50 by 1.5% (to 93.2%) and mAP50-95 by 2.9% (to 66.5%) compared to YOLOv11n, while reducing parameters by 40.7% (to 1.6M) and computation by 25.8% (to 4.9 GFLOPs), maintaining 303 FPS speed.DiscussionThe model demonstrates superior performance in complex maritime conditions through: RCEA's multi-branch feature extraction. ADFFN's adaptive multi-scale fusion. SLODH's efficient detection architecture. Ablation studies confirm each component's contribution to balancing accuracy and efficiency for real-time wake detection.https://www.frontiersin.org/articles/10.3389/fmars.2025.1624323/fullship wake detectionYOLOv11nRepConvlightweight detectorDySample |
| spellingShingle | Runxi Qiu Nan Bi Chaoyue Yin OptWake-YOLO: a lightweight and efficient ship wake detection model based on optical remote sensing images Frontiers in Marine Science ship wake detection YOLOv11n RepConv lightweight detector DySample |
| title | OptWake-YOLO: a lightweight and efficient ship wake detection model based on optical remote sensing images |
| title_full | OptWake-YOLO: a lightweight and efficient ship wake detection model based on optical remote sensing images |
| title_fullStr | OptWake-YOLO: a lightweight and efficient ship wake detection model based on optical remote sensing images |
| title_full_unstemmed | OptWake-YOLO: a lightweight and efficient ship wake detection model based on optical remote sensing images |
| title_short | OptWake-YOLO: a lightweight and efficient ship wake detection model based on optical remote sensing images |
| title_sort | optwake yolo a lightweight and efficient ship wake detection model based on optical remote sensing images |
| topic | ship wake detection YOLOv11n RepConv lightweight detector DySample |
| url | https://www.frontiersin.org/articles/10.3389/fmars.2025.1624323/full |
| work_keys_str_mv | AT runxiqiu optwakeyoloalightweightandefficientshipwakedetectionmodelbasedonopticalremotesensingimages AT nanbi optwakeyoloalightweightandefficientshipwakedetectionmodelbasedonopticalremotesensingimages AT chaoyueyin optwakeyoloalightweightandefficientshipwakedetectionmodelbasedonopticalremotesensingimages |