Brain-computer interface (BCI) can provide a way for the disabled to interact with the outside world. Steady-state visual evoked potential (SSVEP), which evokes potential through visual stimulation is one of important BCI paradigms. In laboratory environment, the classification accuracy of SSVEPs is excellent. However, in motion state, the accuracy will be greatly affected and reduce quite a lot. In this paper, in order to improve the classification accuracy of the SSVEP signals in the motion state, we collected SSVEP data of five targets at three speeds of 0km/h, 2.5km/h and 5km/h. A compare network based on convolutional neural network (CNN) was proposed to learn the relationship between EEG signal and the template corresponding to each stimulus frequency and classify. Compared with traditional methods (i.e., CCA, FBCCA and SVM) and state-of-the-art method (CNN) on the collected SSVEP datasets of 20 subjects, the method we proposed always performed best at different speeds. Therefore, these results validated the effectiveness of the method. In addition, compared with the speed of 0 km / h, the accuracy of the compare network at a high walking rate (5km/h) did not decrease much, and it could still maintain a good performance.