Aiming attheproblem thatthetargetsizeofthecurrentUAV aerialimagesissmalland theimagebackground is complex, which leads to low detection accuracy ofexisting UAV targetdetection algorithms, this article proposes an improved YOLOv8s UAV target detection algorithm. First, deformable convolution is used to replace standard convolution to enhance the network's feature extraction abilityforirregularly shaped targets. Then the separable large- kernelattention mechanism (LSKA) is used to improve the SPPF module to improve the problem of low detection accuracy due to large differences in target scales. The weighted bi-directional feature pyramid network (Bi-FPN) is combined attheneck ofthenetwork to achievemulti-scalefeaturefusion and improvethenetwork'smissed detection and false detection ofsmalltargets. Atthehead ofthenetwork, the dynamicdetection head (DyHead) isused to replacethe originaldetectionhead to enhancethedetection abilityofoccluded objectsand smalltargets. Finally, inorderto solvethe problem thata large number of low-quality samples in the datasethave a negative impact on the training process, the Wise-IOU loss function was used to improve the modelconvergence speed and detection accuracy. Experimentalresults show that the improved method achieved 41.7% mAP on the VisDrone2019 dataset. Compared with the original YOLOv8s algorithm , mAP@0.5 increased by3.0% , mAP@0.5 ∶ 0.95increased by1.9% , the numberofparameters decreased by 17.5% , and the amount of calculation dropped by 12.63%. It achieves both model lightweight and detection accuracy.