SARATOV FALL MEETING SFM 

© 2020 All Rights Reserved

Optical multi-band detection of unmanned aerial vehicles with YOLO v4 convolutional neural network

Anfimov D.R., Golyak Ig.S., Morozov A.N., Nazolin A.L., Scherbakova A.V. and Fufurin I.L.

Abstract

The paper presents a method for recognizing drones using the YOLO v4 neural network. Recognition performs simultaneously in the visible and infrared ranges. The results of UAVs detection on various backgrounds types of an urban environment in the daytime and at night are presented. An algorithm detecting unmanned object in the field of view of cameras in the visible and infrared ranges using neural networks in both ranges, is described.

Speaker

Anfimov Dmitriy
Bauman Moscow State Technical University
Russian Federation

Report



File with report

Discussion

Ask question