摘要： 针对水下养殖鱼类因遮挡，图像退化，难以对鱼群实现精准跟踪的问题，提出了一种基于改进YOLOv11n的检测模型LSD-YOLO。首先引入一种动态检测头（DynamicHead），使模型具有融合任务感知、尺度感知和空间感知的能力。其次，设计了一种轻量特征提取模块LiteODSE，该模块结合了动态卷积与通道注意力，增强了骨干网络中的特征提取能力。然后，引入SDI多层次特征融合模块，可以分离并融合多尺度空间信息。并且，使用GIOU损失函数代替CIOU损失函数，通过引入边界框以外的约束信息，可以改善小目标以及无重叠区域下的难定位问题。最后，结合目前比较先进的跟踪算法StrongSORT，有效提升了跟踪的精度。结果显示，与YOLOv11n相比，所设计的模型准确率提高了3.2%，mAP50提高了3%。与YOLOv11n+StrongSORT相比，MOTA提高了5.2%，ID切换次数减少了30%，证明改进的方法可以更好的应用于水下养殖鱼的目标检测和跟踪中。

关键词: YOLOv11n, StrongSORT, 目标检测, 目标跟踪

Abstract: A detection model LSD-YOLO based on improved YOLOv11n is proposed is proposed to address the problem of underwater aquaculture fish due to occlusion, image degradation, and difficulty in realizing accurate tracking of the fish. Firstly, a DynamicHead is introduced to give the model the ability to fuse task awareness, scale awareness, and spatial awareness. Second, a lightweight feature extraction module, LiteODSE, has been designed to combine dynamic convolution and channel attention to enhance the feature extraction capability in the backbone network. Then, the SDI multilevel feature fusion module is introduced, which can separate and fuse multi-scale spatial information. Moreover, the GIOU loss function is used instead of the CIOU loss function, and the difficult localization problem under small targets as well as non-overlapping regions can be improved by introducing the constraint information outside the bounding box. Finally, tracking accuracy is effectively improved by combining it with StrongSORT, which is currently a more advanced tracking algorithm. Experiments demonstrate that the accuracy of the designed model is improved by 3.2% and mAP50 by 3% compared with YOLOv11n. Compared with YOLOv11n+StrongSORT, the MOTA is improved by 5.2% and the number of ID switching is reduced by 30%, which proves that the improved method can be better applied in target detection and tracking of underwater farmed fish.

Key words: YOLOv11n, StrongSORT, target detection, target tracking