Aiming at the problem of small target detection of unmanned aerial vehicle (UAV) platform with limited computing resources, a lightweight small target detection algorithm for UAV platforms based on YOLOv5 is proposed. The algorithm retains the original FPN + PAN and YOLOHead of YOLOv5 as the Neck network and Head network, respectively. Firstly, the original CSPDarknet53 structure of Backbone is lightweight, the original Focus layer is replaced with the Conv_BN_SiLu layer, and the Resblock body structure is replaced with the Inverted Resblock structure. Secondly, DSConv is used to lighten the Neck and reduce the number of the model model’s parameters. Finally, SPD-Conv is used to convert features from space to depth, strengthen the low-resolution features, and improve the model’s small targets detected ability. Results of the experiments show that the proposed algorithm achieves a good balance between the number of model parameters and the accuracy.