Fast Matching for Consecutive Frames of UAV Video

In the past few years, UAV has been more and more widely used in many fields. However, data of UAV video is too large to be processed easily. This paper proposes a novel method combined with PID prediction theory, which is in order to improve the processing speed of consecutive frame matching of UAV video. The experimental results indicate that the average matching time of our method is less than half of that of ORB algorithm. to the best of our knowledge, it is the first time to combine PID controller with image matching methods for UAV video, which we believe is an important attempt in practical applications.