ISSN 2079-3537      

 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                                                                                             





Scientific Visualization, 2019, volume 11, number 4, pages 43 - 52, DOI: 10.26583/sv.11.4.04

Segmentation and visualization of obstacles for the enhanced vision system using generative adversarial networks

Authors: V.V.  Kniaz1,,, M.I.  Kozyrev2,A,C, A.N.  Bordodymov3,A, A.V. Papazian4,A, A.V. Yakhanov5,A

A State Res. Institute of Aviation Systems (GosNIIAS)

B Moscow Institute of Physics and Technology (MIPT)

C Bauman Moscow State Technical University (BMSTU)

1 ORCID: 0000-0003-2912-9986, vl.kniaz@gosniias.ru

2 ORCID: 0000-0001-9901-5664, j18r1l@gmail.com

3 ORCID: 0000-0001-8159-2375, bordodymov@gmail.com

4 ORCID: 0000-0003-0119-011X, ares.papazian@yandex.ru

5 ORCID: 0000-0003-4284-6197, yakhanovalexander@gmail.com

 

Abstract

Long range infrared cameras may provide increasing crew situational awareness in limited vision and night conditions.

Similar cameras are installed in modern civil aircraft's as part of an improved vision system. Correct thermal image interpretation by the crew requires certain experience, due to the fact that view of the scene very different from the visible range and may change within time of day and season. This paper discusses the deep generative-adversary neural network to automatically convert thermal images to semantically similar color images of the visible range.

 

Keywords: visualization, deep convolutional neural networks, pilot primary display, visual analytics.