Research on Underwater Sonar Image Object Detection Method based on Improved YOLOv11n

Weina Zhao; Yiwei Qian; Willam Enrique; Mingyu Wang

doi:10.54691/8cydbk77

Authors

Weina Zhao
Yiwei Qian
Willam Enrique
Mingyu Wang

DOI:

https://doi.org/10.54691/8cydbk77

Keywords:

Underwater Sonar Image; Target Detection; YOLOv11n ECA Attention Mechanism; BiFPN; Image Preprocessing.

Abstract

Aiming at the problems of strong noise, low resolution, blurred target edges, severe geometric distortion of underwater sonar images, insufficient accuracy of traditional target detection algorithms, and poor adaptability of the original YOLOv11n model, an underwater sonar image target detection method based on improved YOLOv11n is proposed. The method adopts novel median filtering and single-scale Retinex for image denoising and enhancement, optimizes anchor boxes with K-means++, uses Mixup data augmentation, Focal-EIOU Loss and Soft-NMS, embeds ECA attention mechanism in the backbone network, and replaces the neck network with BiFPN structure. Experimental results show that the proposed method achieves 97.5% precision, 97.8% recall and 98.2% mAP@.5 on the self-built sonar dataset, which are 6.3, 6.2 and 6 percentage points higher than those of the original YOLOv11n respectively. It can effectively adapt to complex underwater environments and meet the high-precision detection requirements of marine exploration, maritime security and other engineering applications.

Downloads

Download data is not yet available.

References

[1] Sang H Q, Lu Q Y, Sun X J, Zhang S, Liu F. A lightweight multi-scale ship detection framework for wave gliders with spatial-channel attention fusion[J]. Measurement, 2026, 258: 119280. https://doi.org/10.1016/j.measurement.2025.119280.

[2] Hu W, Wu Q B, Fang H F, Chen J J, Luo J C, Cai L H. Laser-based automated optical inspection for edge small defect detection in photovoltaic silicon wafers with complex backgrounds[J]. Renewable Energy, 2025, 254: 123658. https://doi.org/10.1016/j.renene.2025.123658.

[3] Gao Z Y, Li Y T, Shao Y P, Tao F Z, Wang Z K, Chen G Y. Enhanced lightweight UAV maritime search and rescue model based on YOLOv11n[J]. iScience, 2026, 29(4): 115366. https://doi.org/10.1016/j.isci.2026.115366.

[4] Zhou J H, Zhang G, Liu Y F, Sun W W, Luo Z M, Li Z Y. Lightweight Multi-Task Perception for USV Navigation with Adaptive Feature Fusion[J]. IFAC-PapersOnLine, 2025, 59(22): 633-638. https://doi.org/10.1016/j.ifacol.2025.11.705.

[5] Chen H Y, Chang Y G, Zeng W M, Wang F, Qu C, Chen C C, Hu X Y, Yang X, Wang L. MaritiNet: An efficient feature fusion network of multi-scenario ship detection for maritime situational awareness[J]. Expert Systems with Applications, 2026, 315: 131662. https://doi.org/10.1016/j.eswa.2026.131662.

[6] Zhai Z L, Li Y, Xu C, Su S Q. Remote Sensing Image Object Detection Network Based on Lightweight Feature Enhancement and Efficient Fusion[J]. Digital Signal Processing, 2026: 106180. https://doi.org/10.1016/j.dsp.2026.106180.

[7] Wang J R, Zhang S A, Cao L Q, Huang J, Xiang Z, Chen J. FBDNet: A faster and better D-FINE for small target defect detection on industrial paper cups[J]. Digital Signal Processing, 2026, 178: 106141. https://doi.org/10.1016/j.dsp.2026.106141.

[8] Shu P, Zhang H, Xiao H P, Luo S J, Wu H. Gear surface defect detection with hierarchical multi-scale feature analysis and dynamic attention enhancement network[J]. Optics & Laser Technology, 2026, 197: 114779. https://doi.org/10.1016/j.optlastec.2026.114779.

[9] Shen Y X, Da M, Jiang L. An infrared small target detection algorithm based on YOLOv11[J]. Digital Signal Processing, 2026, 174: 105968. https://doi.org/10.1016/j.dsp.2026.105968.

[10] Shi K Q, Li Q, Li H C, Xu P, Zhang P, Yang S, Zhu H N. LMFAN: Lightweight multi-scale feature aggregation network with channel pruning and knowledge distillation for ship detection in remote sensing images[J]. Remote Sensing Applications: Society and Environment, 2025, 39: 101692. https://doi.org/10.1016/j.rsase.2025.101692.

[11] Gong Y F, Jin J C, Liu D Q, Ren P. A real-time lightweight object detection algorithm based on improved you only look once version 8 for unmanned surface vehicle[J]. Engineering Applications of Artificial Intelligence, 2025, 152: 110798. https://doi.org/10.1016/j.engappai.2025.110798.

[12] Zhang X H, Yuan D Q, Hu Y H, et al. A semantic-aware tiny object detection network against missed detection[J]. Pattern Recognition, 2026, 172: 112624. https://doi.org/10.1016/j.patcog.2025.112624.

[13] Chen Z K, Yang D G, Song T T, et al. Enhanced multi-scale attentional remote sensing detector[J]. Digital Signal Processing, 2026, 174: 105948. https://doi.org/10.1016/j.dsp.2026.105948.

[14] Ruan C L, Hong L, Gao J J. A high-precision object detection algorithm for complex maritime environments[J]. Applied Ocean Research, 2026, 169: 104994. https://doi.org/10.1016/j.apor.2026.104994.

[15] Wu C M, Lei J, Li Z Q, Ren M L. General ship detection based on mixed distillation and dynamic task-aligned detection head[J]. Ocean Engineering, 2025, 323: 120616. https://doi.org/10.1016/j.oceaneng.2025.120616.

[16] Wei L, Zhang Y J, Ding B Q, Li W W, Lu H R. A lightweight visual detection method for maritime autonomous surface ships in port area navigation[J]. Digital Signal Processing, 2025, 167: 105422. https://doi.org/10.1016/j.dsp.2025.105422.

[17] Wang Y J, Li Z B, Wang T M, Hu Y X, Bai Z Y, Ding G G, Geng X F. FRCL-SARNet : A lightweight SAR ship detection network based on feature refinement and dual cross level fusion[J]. Digital Signal Processing, 2026, 175: 106005. https://doi.org/10.1016/j.dsp.2026.106005.

[18] Teixeira E H, Mafra S B, De Figueiredo F A P. InaTechShips: A validation study of a novel ship dataset through deep learning-based classification and detection models for maritime applications[J]. Ocean Engineering, 2025, 326: 120823. https://doi.org/10.1016/j.oceaneng.2025.120823.

[19] Zhang W S, Zhang X L, Xu X W, Wei S J, Shi J, Wang Y Q, Zeng T J. MHFNet: Multimodal hybrid fusion framework for misaligned SAR-Optical ship detection[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2026, 231: 151-166. https://doi.org/10.1016/j.isprsjprs.2025.10.027.

[20] Yang Z H, Xu T, Ye Q, Zhao L, Bai Y, Paik J K. FoggySea: Bridging synthetic realism and low-contrast robustness for maritime object detection[J]. Ocean Engineering, 2026, 354: 124893. https://doi.org/10.1016/j.oceaneng.2026.124893.

[21] Sun J, Liu Z Q, Xie M J, Wang Y F, Yuan R, Wu J N, Duan S K, Wang L D. DP-CIADet: Detail perception and critical information aggregation compact detection network for aerial optical remote sensing images[J]. Optics & Laser Technology, 2026, 193: 113519. https://doi.org/10.1016/j.optlastec.2025.113519.

[22] Gao G, Li C Y, Zhang X, Yao B X, Chen Z. Mamba-CNN hybrid Multi-scale ship detection Network driven by a Dual-perception feature of Doppler and Scattering[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2026, 232: 656-674. https://doi.org/10.1016/j.isprsjprs.2026.01.004.

[23] Bi Z B, Yang H, Fu Y S, Zheng W H. Enhanced YOLO-security deep learning model for ship detection in maritime security[J]. Results in Engineering, 2026, 29: 108815. https://doi.org/10.1016/j.rineng.2025.108815.

[24] Wu R B, Cui Y N, Hu Z J, Ren J, Zhang Y, Li B. Heterogeneous multi-scale enhanced YOLOv8 for real-time maritime obstacle detection on unmanned surface vessels[J]. Expert Systems with Applications, 2026, 321: 132244. https://doi.org/10.1016/j.eswa.2026.132244.

[25] Zhang E Z, Guo Y C, Li S B. Water surface object detection in river channels based on feature cross-layer fusion and reconstruction[J]. Digital Signal Processing, 2026, 168: 105618. https://doi.org/10.1016/j.dsp.2025.105618.