Aircraft Target Recognition Combining Saliency Detection and Feature Matching

According to the difference of visual saliency between target and background together with the morphological characteristics of the aircrafts. This paper proposes a novel aircraft target recognition algorithm based on saliency detection. The algorithm first detects the saliency of the pre-processed remote sensing image and eliminates the influence of shadow for the region of interest extraction distinguish the region of interest based on the morphological characteristics of the aircrafts, and then achieve aircraft target recognition. Finally, calculates the aircraft fuselage length, wingspan and relative moments. Afterwards, the aircraft type discrimination can be achieved via feature matching. Extensive experiments show that the algorithm has accurate feature extraction results and high target recognition accuracy.