ABSTRACT

In this paper, we study a deep learning (DL)-based multimodal technology for military, surveillance, and defense applications based on a pixel-by-pixel classification of soldier’s image dataset. We explore the acquisition of images from a remote tactical-robot to a ground station, where the detection and tracking of soldiers can help the operator to take actions or automate the tactical-robot in battlefield. The soldier detection is achieved by training a convolutional neural network to learn the patterns of the soldier’s uniforms. Our CNN learns from the initial dataset and from the actions taken by the operator, as opposed to the old-fashioned and hard-coded image processing algorithms. Our system attains an accuracy of over 81% in distinguishing the specific soldier uniform and the background. These experimental results prove our hypothesis that dilated convolutions can increase the segmentation performance when compared with patch-based, and fully connected networks.

摘要

在本文中，我们研究了基于深度学习（DL）的多模式技术，该技术基于士兵图像数据集的逐像素分类，适用于军事，监视和国防应用。我们探索从远程战术机器人到地面站的图像采集，在那里士兵的检测和跟踪可以帮助操作员在战场上采取行动或使战术机器人自动化。士兵的检测是通过训练卷积神经网络来学习士兵制服的图案来实现的。与老式的硬编码图像处理算法相反，我们的CNN从初始数据集和操作员采取的行动中学习。我们的系统在区分特定士兵制服和背景方面的准确性达到81％以上。