Aiming attheproblemsofstrip steelsurfacedefectswith varioustypesand inconspicuousfeatures, which lead to leakage and misdetection, an improved YOLOv8n strip steelsurface defectdetection method is proposed. Firstly, to adapt to smaller size targets, a P2 detection layer is added to identify various types of defects and reduce leakage detection, as wellas an efficientPConv detection head isdesigned to maintain the inferencespeed. Secondly, a fusion of the C2fmodule in the neck of YOLOv8n and the deformable convolutional DCNv2 is adopted to enhance the feature extraction capability ofthe model. Furthermore, a large dynamics selective module is introduced in the outputlayer of the backbone network LSKNet, to expand the sensory field of the model and improve the accuracy of targetdetection. Finally, the SIoU loss function is chosen to replace the CIoU loss function to enhance the network convergence effect, thus improvingtherecognition accuracy. Theimproved YOLOv8n method istested ontheCSU_STEEL dataset, and the experimentalresults show thatthe mAP@0.5 is improved by8.6% the originalmodelto 82.3% , and the volumeonly increases by0.5 MB. The improved method has better detection results for strip surface defects, which can provide a reference significance forthe research ofthe defectdetection method ofstrip steel.