Dynamic wireless power transfer has created a new possibility for charging the electric vehicles (EVs) in motion, which would help to reduce the battery capacity and prolong the vehicle mileage. However, the misalignments between the transmitter coil and receiver coil vary randomly as the vehicle moves, which reduces the stability of the output power. Therefore, a guiding approach is needed to maintain the alignment between the transmitter coil and receiver coil within an acceptable range. In this paper, a vision-based alignment detection method is proposed to improve the stability of the system output power. The results show that the proposed method can accurately acquire the coil misalignments and then rapidly regulate the system output power in comparison with the conventional discrete proportional-integral (PI) control algorithm.