Aircraft pose estimation based on polar function descriptor

Abstract

The problem of aircraft pose estimating in a single image is analyzed. A novel method combined mathematical morphological algorithm and Radon transform is introduced to detect classical aircraft pose using the feature of shapes and regions. Silhouettes obtained by image segmentation are simplified by mathematical morphological algorithm, and Radon transform is used to do line detection for the simplified image. Tow axises of the aircraft are determined by the feature of fuselage and wings, and pose of the aircraft are estimated by the angle of the lines. Experimental results show the effectiveness of the algorithm for aircraft pose estimation in a gray level image.