Robustness Study of a Deep Convolutional Neural Network for Vehicle Detection in Aerial Imagery

被引：5

作者：

Ilina, O., V ^{[1
]}

Tereshonok, M., V ^{[1
,2
]}

机构：

[1] Moscow Tech Univ Commun & Informat, Moscow 111024, Russia

[2] Natl Res Univ, Moscow Inst Phys & Technol, Dolgoprudnyi 141701, Moscow Oblast, Russia

来源：

JOURNAL OF COMMUNICATIONS TECHNOLOGY AND ELECTRONICS | 2022年 / 67卷 / 02期

基金：

俄罗斯科学基金会;

关键词：

This work was supported by the Russian Science Foundation; grant no. 18-72-10118;

D O I：

10.1134/S1064226922020048

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The robustness of a deep convolutional neural network for vehicle detection in aerial imagery is analyzed. The study allows us to evaluate detection quality and correctness of a trained neural network. The method of improving noise immunity for an object detection system in aerial imagery is proposed.

引用

页码：164 / 170

页数：7