UW-YOLO-Bio: A Real-Time Lightweight Detector for Underwater Biological Perception with Global and Regional Context Awareness

Αποθηκεύτηκε σε:
Λεπτομέρειες βιβλιογραφικής εγγραφής
Εκδόθηκε σε:Journal of Marine Science and Engineering vol. 13, no. 11 (2025), p. 2189-2214
Κύριος συγγραφέας: Zhou, Wenhao
Άλλοι συγγραφείς: Zeng Junbao, Li, Shuo, Zhang Yuexing
Έκδοση:
MDPI AG
Θέματα:
Διαθέσιμο Online:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Ετικέτες: Προσθήκη ετικέτας
Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!

MARC

LEADER 00000nab a2200000uu 4500
001 3275540781
003 UK-CbPIL
022 |a 2077-1312 
024 7 |a 10.3390/jmse13112189  |2 doi 
035 |a 3275540781 
045 2 |b d20251101  |b d20251130 
084 |a 231479  |2 nlm 
100 1 |a Zhou, Wenhao  |u Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China; zhouwenhao@sia.cn (W.Z.); shuoli@sia.cn (S.L.); zhangyuexing@sia.cn (Y.Z.) 
245 1 |a UW-YOLO-Bio: A Real-Time Lightweight Detector for Underwater Biological Perception with Global and Regional Context Awareness 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a Accurate biological detection is crucial for autonomous navigation of underwater robots, yet severely challenged by optical degradation and scale variation in marine environments. While image enhancement and domain adaptation methods offer some mitigation, they often operate as disjointed preprocessing steps, potentially introducing artifacts and compromising downstream detection performance. Furthermore, existing architectures struggle to balance accuracy, computational efficiency, and robustness across the extreme scale variability of marine organisms in challenging underwater conditions. To overcome these limitations, we propose UW-YOLO-Bio, a novel framework built upon the YOLOv8 architecture. Our approach integrates three dedicated modules: (1) The Global Context 3D Perception Module (GCPM), which captures long-range dependencies to mitigate occlusion and noise without the quadratic cost of self-attention; (2) The Channel-Aggregation Efficient Downsampling Block (CAEDB), which preserves critical information from low-contrast targets during spatial reduction; (3) The Regional Context Feature Pyramid Network (RCFPN), which optimizes multi-scale fusion with contextual awareness for small marine organisms. Extensive evaluations on DUO, RUOD, and URPC datasets demonstrate state-of-the-art performance, achieving an average improvement in mAP50 of up to 2.0% across benchmarks while simultaneously reducing model parameters by 8.3%. Notably, it maintains a real-time inference speed of 61.8 FPS, rendering it highly suitable for deployment on resource-constrained autonomous underwater vehicles (AUVs). 
653 |a Aggregation 
653 |a Marine environment 
653 |a Benchmarks 
653 |a Accuracy 
653 |a Datasets 
653 |a Collaboration 
653 |a Adaptability 
653 |a Image enhancement 
653 |a Depth perception 
653 |a Navigation 
653 |a Adaptation 
653 |a Underwater robots 
653 |a Modules 
653 |a Occlusion 
653 |a Efficiency 
653 |a Marine organisms 
653 |a Physics 
653 |a Autonomous underwater vehicles 
653 |a Failure analysis 
653 |a Perception 
653 |a Design 
653 |a Underwater vehicles 
653 |a Autonomous navigation 
653 |a Object recognition 
653 |a Real time 
653 |a Environmental 
700 1 |a Zeng Junbao  |u Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China; zhouwenhao@sia.cn (W.Z.); shuoli@sia.cn (S.L.); zhangyuexing@sia.cn (Y.Z.) 
700 1 |a Li, Shuo  |u Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China; zhouwenhao@sia.cn (W.Z.); shuoli@sia.cn (S.L.); zhangyuexing@sia.cn (Y.Z.) 
700 1 |a Zhang Yuexing  |u Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China; zhouwenhao@sia.cn (W.Z.); shuoli@sia.cn (S.L.); zhangyuexing@sia.cn (Y.Z.) 
773 0 |t Journal of Marine Science and Engineering  |g vol. 13, no. 11 (2025), p. 2189-2214 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3275540781/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3275540781/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3275540781/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch