Bulletin of Surveying and Mapping ›› 2020, Vol. 0 ›› Issue (3): 1-6.doi: 10.13474/j.cnki.11-2246.2020.0067

    Next Articles

Aircraft target recognition based on saliency detection and feature matching

OUYANG Huan1,2, FAN Dazhao1, GUO Jing2, DAI Yazhen3   

  1. 1. Information Engineering University, Zhengzhou 450001, China;
    2. Troops 93920, Hanzhong 723213, China;
    3. Troops 61206, Beijing 100042, China
  • Received:2019-05-14 Revised:2019-12-22 Published:2020-04-09

Abstract: 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.

Key words: remote sensing images, aircraft target recognition, saliency detection, feature matching, type discrimination of aircrafts

CLC Number: