Translator Disclaimer
15 November 2018 A fine-grained recognition model of air targets based on bilayer faster R-CNN with feedback
Author Affiliations +
Proceedings Volume 10964, Tenth International Conference on Information Optics and Photonics; 1096439 (2018) https://doi.org/10.1117/12.2505925
Event: Tenth International Conference on Information Optics and Photonics (CIOP 2018), 2018, Beijing, China
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.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jiajia Wang, Kan Ren, Weixian Qian, Guohua Gu, and Qian Chen "A fine-grained recognition model of air targets based on bilayer faster R-CNN with feedback", Proc. SPIE 10964, Tenth International Conference on Information Optics and Photonics, 1096439 (15 November 2018); https://doi.org/10.1117/12.2505925
PROCEEDINGS
7 PAGES


SHARE
Advertisement
Advertisement
Back to Top