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

Igor S. Golyak; Dmitriy R. Anfimov; Igor L. Fufurin; Andrey L. Nazolin; Sergey V. Bashkin; Vladimir L. Glushkov; Andrey N. Morozov

doi:10.1117/12.2584591

Translator Disclaimer

8 November 2020 Optical multi-band detection of unmanned aerial vehicles with YOLO v4 convolutional neural network

Igor S. Golyak, Dmitriy R. Anfimov, Igor L. Fufurin, Andrey L. Nazolin, Sergey V. Bashkin, Vladimir L. Glushkov, Andrey N. Morozov

Author Affiliations +

Proceedings Volume 11525, SPIE Future Sensing Technologies; 115250Y (2020) https://doi.org/10.1117/12.2584591
Event: SPIE Future Sensing Technologies, 2020, Online Only

Abstract

The paper presents a method for optical detection drones using the YOLO v4 neural network. Recognition performs simultaneously in the visible (Vis) and long-wave infrared (LWIR) ranges. The results of UAV detection on various types of urban background environment at day and night conditions, as well as at different distances from cameras, are presented. An algorithm for detecting of unmanned vehicles in the video cameras field of view of the Vis and LWIR ranges is described. This algorithm takes as input the outputs of two neural networks that recognize the drone in two ranges and estimates the probability of detection. Its shown that the YOLO v4 neural network recognizes unmanned objects on various background substrates with a minimum temperature difference of 0.4 degrees on the NEC 2640 thermal imager.

Conference Presentation

Citation Download Citation

Igor S. Golyak, Dmitriy R. Anfimov, Igor L. Fufurin, Andrey L. Nazolin, Sergey V. Bashkin, Vladimir L. Glushkov, and Andrey N. Morozov "Optical multi-band detection of unmanned aerial vehicles with YOLO v4 convolutional neural network", Proc. SPIE 11525, SPIE Future Sensing Technologies, 115250Y (8 November 2020); https://doi.org/10.1117/12.2584591

ACCESS THE FULL ARTICLE