Moskovskiy fiziko-tehnicheskiy institut (gosudarstvennyy universitet)
Moskovskiy Gosudarstvennyy Tehnicheskiy Universitet Imeni N. E. Baumana
GRNTI 50.07 Теоретические основы вычислительной техники
BBK 3297 Вычислительная техника
Long range infrared cameras may provide increasing crew situational awareness in limited vision and night conditions. Similar cameras are installed in modern civil aircrafts as part of an improved vision system. Correct thermal image interpritation by the crew requires certain expiriance, 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.
visualization, deep convolutional neural networks, pilot primary display, visual analytics
1. Berg Amanda, Ahlberg Jorgen, Felsberg Michael. Generating Visible Spectrum Images From Thermal Infrared // The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. — 2018. — June.
2. Arthur Jarvis J., Norman R. Michael, Kramer Lynda J. et al. Enhanced vision flight deck technology for commercial aircraft lowvisibility surface operations. — 2013. — Access mode: https://doi.org/10.1117/12.2016386.
3. Generative adversarial nets / Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza et al. // Advances in neural information processing systems. — 2014. — P. 2672–2680.
4. Image-to-Image Translation with Conditional Adversarial Networks / Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A Efros // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). — IEEE, 2017. — P. 5967– 5976.
5. Kniaz V. V., Bordodymov A. N. LONG WAVE INFRARED IMAGE COLORIZATION FOR PERSON RE-IDENTIFICATION // ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. — 2019. — Vol. XLII-2/W12. — P. 111–116. — Access mode: https://www.int-arch-photogramm-remote-sens-spatialinf-sci.net/XLII-2-W12/111/2019/.
6. Knyaz Vladimir. Multimodal data fusion for object recognition. — Vol. 110590. — 2019. — P. 110590P. — Access mode: https://doi.org/10.1117/12.2526067.
7. Petro Ana Belén, Sbert Catalina, Morel Jean-Michel. Multiscale retinex // Image Processing On Line. — 2014. — P. 71–88.
8. Ronneberger Olaf, Fischer Philipp, Brox Thomas. U-net: Convolutional networks for biomedical image segmentation // International Conference on Medical image computing and computer-assisted intervention / Springer. — 2015. — P. 234–241.
9. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric / Richard Zhang, Phillip Isola, Alexei A Efros et al. // The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). — 2018. — Jun.
10. ThermalGAN: Multimodal Color-to-Thermal Image Translation for Person Re-Identification in Multispectral Dataset / Vladimir V. Kniaz, Vladimir A. Knyaz, Jiří Hladůvka et al. // Computer Vision – ECCV 2018 Workshops. — Springer International Publishing, 2018.
11. Vygolov Oleg, Zheltov Sergey. Enhanced, synthetic and combined vision technologies for civil aviation // Computer Vision in Control Systems-2. — Springer, 2015. — P. 201–230.
