Aiming at the background of sense and avoiding of unmanned aerial vehicle, a monocular vision method for distance measurement from motion was proposed. Firstly, two different images were chose from a sequence of images for the same target in different position. Then, feature points could be extracted and matched through scale-invariant feature transform algorithm for the two images. Through analysis the different positions for the same feature point on different images and combined with the movement parameters of the aircraft, the information between the aircraft and the obstacle could be got. With the proposed method, the target was located at different locations. The experimental results show that the measurement accuracy and effectiveness of the method can meet the demand of avoidance.