文献类型：期刊文献

英文题名：LFN-YOLO: precision underwater small object detection via a lightweight reparameterized approach

作者：Liu, Mingxin[1,2];Wu, Yujie[3];Li, Ruixin[3];Lin, Cong[1,2]

机构：[1]Guangdong Ocean Univ, Sch Elect & Informat Engn, Zhanjiang, Peoples R China;[2]Guangdong Prov Key Lab Intelligent Equipment South, Zhanjiang, Peoples R China;[3]Guangdong Ocean Univ, Coll Naval Architecture & Shipping, Zhanjiang, Peoples R China

年份：2025

卷号：11

外文期刊名：FRONTIERS IN MARINE SCIENCE

收录：SCI-EXPANDED(收录号：WOS:001413637200001)、、WOS

基金：The author(s) declare financial support was received for the research, authorship, and/or publication of this article. This work was partly supported by the National Natural Science Foundation of China (62171143), Guangdong Provincial University Innovation Team (2023KCXTD016), special projects in key fields of ordinary universities in Guangdong, Province (2021ZDZX1060), the Stable Supporting Fund of Acoustic Science and Technology Laboratory (JCKYS2024604SSJS00301), the Undergraduate Innovation Team Project of Guangdong Ocean University under Grant CXTD2024011, the Open Fund of Guangdong Provincial Key Laboratory of Intelligent Equipment for South China Sea Marine Ranching (Grant NO. 2023B1212030003).

语种：英文

外文关键词：underwater object detection; lightweight detector; small object; marine resources; multi-scale feature fusion

外文摘要：Underwater object detection plays a significant role in fisheries resource assessment and ecological environment protection. However, traditional underwater object detection methods struggle to achieve accurate detection in complex underwater environments with limited computational resources. This paper proposes a lightweight underwater object detection network called LightFusionNet-YOLO (LFN-YOLO). First, we introduce the reparameterization technique RepGhost to reduce the number of parameters while enhancing training and inference efficiency. This approach effectively minimizes precision loss even with a lightweight backbone network. Then, we replaced the standard depthwise convolution in the feature extraction network with SPD-Conv, which includes an additional pooling layer to mitigate detail loss. This modification effectively enhances the detection performance for small objects. Furthermore, We employed the Generalized Feature Pyramid Network (GFPN) for feature fusion in the network's neck, enhancing the network's adaptability to features of varying scales. Finally, we design a new detection head, CLLAHead, which reduces computational costs and strengthens the robustness of the model through cross-layer local attention. At the same time, the DFL loss function is introduced to reduce regression and classification errors. Experiments conducted on public datasets, including URPC, Brackish, and TrashCan, showed that the mAP@0.5 reached 74.1%, 97.5%, and 66.2%, respectively, with parameter sizes and computational complexities of 2.7M and 7.2 GFLOPs, and the model size is only 5.9 Mb. Compared to mainstream vision models, our model demonstrates superior performance. Additionally, deployment on the NVIDIA Jetson AGX Orin edge computing device confirms its high real-time performance and suitability for underwater applications, further showcasing the exceptional capabilities of LFN-YOLO.