Share Email Print
cover

Proceedings Paper

A fine-grained recognition model of air targets based on bilayer faster R-CNN with feedback
Author(s): Jiajia Wang; Kan Ren; Weixian Qian; Guohua Gu; Qian Chen
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The accuracy of air target identification is of great significance for air defense operations and civilian management. A fine-grained recognition model of aerial target based on bilayer faster regions with convolution neural network (Faster R-CNN) with feedback is proposed in the paper. Faster R-CNN model is a typical target detection model based on deep learning. However, its ability to distinguish categories with subtle differences is not enough. In the proposed model, Faster R-CNN model is used for the first training to get a classification model and the clustering analysis of the classification result is used to get confused categories. Then the first training model is fine-tuned to retrain the confusing categories. The model is tested in the FGVC-Aircraft-2013b data set, and the average training accuracy is raised from 88.7% to 89.3%, the accuracy of the classification is raised from 88.98% to 91.21%, which shows that this model is effective in improving the fine-grained identification of air targets.

Paper Details

Date Published: 15 November 2018
PDF: 7 pages
Proc. SPIE 10964, Tenth International Conference on Information Optics and Photonics, 1096439 (15 November 2018); doi: 10.1117/12.2505925
Show Author Affiliations
Jiajia Wang, Nanjing Univ. of Science and Technology (China)
Beijing Univ. of Posts and Telecommunications (China)
Kan Ren, Nanjing Univ. of Science and Technology (China)
Beijing Univ. of Posts and Telecommunications (China)
Weixian Qian, Nanjing Univ. of Science and Technology (China)
Guohua Gu, Nanjing Univ. of Science and Technology (China)
Qian Chen, Nanjing Univ. of Science and Technology (China)


Published in SPIE Proceedings Vol. 10964:
Tenth International Conference on Information Optics and Photonics
Yidong Huang, Editor(s)

© SPIE. Terms of Use
Back to Top