Infrared Variation Optimized Deep Convolutional Neural Network for Robust Automatic Ground Target Recognition

Sungho Kim, Woo-Jin Song, So-Hyun Kim; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 1-8

Abstract


ATR is a traditionally unsolved problem in military applications because of the wide range of infrared (IR) image variations and limited number of training images. Recently, deep convolutional neural network-based approaches in RGB images (RGB-CNN) showed breakthrough performance in computer vision problems. The direct use of the RGB-CNN to IR ATR problem fails to work because of the IR database problems. This paper presents a novel infrared variation-optimized deep convolutional neural network (IVO-CNN) by considering database management, such as increasing the database by a thermal simulator, controlling the image contrast automatically and suppressing the thermal noise to reduce the effects of infrared image variations in deep convolutional neural network-based automatic ground target recognition. The experimental results on the synthesized infrared images generated by the thermal simulator (OKTAL-SE) validated the feasibility of IVO-CNN for military ATR applications.

Related Material


[pdf]
[bibtex]
@InProceedings{Kim_2017_CVPR_Workshops,
author = {Kim, Sungho and Song, Woo-Jin and Kim, So-Hyun},
title = {Infrared Variation Optimized Deep Convolutional Neural Network for Robust Automatic Ground Target Recognition},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {July},
year = {2017}
}