Soccer serving technology has an important role and value in the game, and excellent serving technology can create a variety of offensive opportunities. Computer vision technology, especially target detection technology, has a wide range of applications in soccer. This paper is simplified based on YOLOv5, and the structure of CSPDarkNet53 is streamlined into MobileNet structure, which reduces the number of parameters of the model and improves the detection speed of the model. Aiming at the problems of target occlusion and uneven illumination conditions, different attention mechanisms are embedded into the network model respectively, which improves the detection ability of the model on the target. The improved YOLOv5 model is tested for performance on a publicly available dataset, and the experimental results show that the model proposed in this paper has better detection performance.