Zobrazeno 1 - 10
of 50
pro vyhledávání: '"A. S. Gorbatsevich"'
Publikováno v:
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XLII-2, Pp 707-714 (2018)
In this paper we propose a new technic called etalons, which allows us to interpret the way how convolution network makes its predictions. This mechanism is very similar to voting among different experts. Thereby CNN could be interpreted as a variety
Externí odkaz:
https://doaj.org/article/41eb0c074bdd4fc7a58bb3fa875c9fda
Autor:
V. S. Gorbatsevich, Yu. V. Vizilter
Publikováno v:
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XLI-B3, Pp 859-862 (2016)
In this paper, we propose an original method for objects detection based on a special tree-structured image representation – the trees of morphlets. The method provides robust detection of various types of objects in an image without employing a ma
Externí odkaz:
https://doaj.org/article/060d8eadf24942ea8fcab390c87f6a41
Autor:
V. S. Gorbatsevich
Publikováno v:
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XL-5/W6, Pp 107-111 (2015)
The paper presents an original method for object detection. The “texture” Hough transform is used as the main tool in the search. Unlike classical generalized Hough transform, this variation uses texture LBP descriptor as a primitive for voting.
Externí odkaz:
https://doaj.org/article/c16a6c5ce67248998b3c082d7b7d1cc5
Publikováno v:
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XL-3, Pp 357-364 (2014)
2D image matching problem is often stated as an image-to-shape or shape-to-shape matching problem. Such shape-based matching techniques should provide the matching of scene image fragments registered in various lighting, weather and season conditions
Externí odkaz:
https://doaj.org/article/22f047307729472788a5e6585bf4f2cf
Publikováno v:
Vestnik komp'iuternykh i informatsionnykh tekhnologii. :11-20
The paper proposes an architecture and training method of a deep convolutional neural network for simultaneous face detection and recognition. The implemented approach combines the ideas of SSD (Single Shot Detector) and Faster R-CNN (Region proposal
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5e49de08b47d6a5eb37a0af5ca794db4
https://doi.org/10.14489/vkit.2021.04.pp.011-020
https://doi.org/10.14489/vkit.2021.04.pp.011-020
Publikováno v:
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XLIII-B2-2020, Pp 415-420 (2020)
The paper addresses the problem of a city heightmap restoration using satellite view image and some manually created area with 3D data. We propose the approach based on generative adversarial networks. Our algorithm contains three steps: low quality
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1bebec32f3e79dbf08cb0de0cd2b33e0
https://doi.org/10.5194/isprs-archives-xliii-b2-2020-415-2020
https://doi.org/10.5194/isprs-archives-xliii-b2-2020-415-2020
Publikováno v:
Journal of the Belarusian State University. Physics. :86-90
The description is given of the study and research a modular-type training complex for studying the radiation of semiconductor lasers generated in the region of 400 – 950 nm. Structurally, the complex consists of emitter modules (there are 8 of the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::091b53668e2495b2a1801ebe4ce96945
https://doi.org/10.33581/2520-2243-2020-2-86-90
https://doi.org/10.33581/2520-2243-2020-2-86-90
Publikováno v:
Компьютерная оптика, Vol 43, Iss 5, Pp 886-900 (2019)
A general approach to a structure-functional analysis and synthesis (SFAS) of deep neural networks (CNN). The new approach allows to define regularly: from which structure-functional elements (SFE) CNNs can be constructed; what are required mathemati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9312821f5a15c58ea559761828d359a5
http://computeroptics.ru/KO/PDF/KO43-5/430521.pdf
http://computeroptics.ru/KO/PDF/KO43-5/430521.pdf
Publikováno v:
Journal of the Belarusian State University. Physics. :12-21
Based on statistical modeling, a numerical analysis of the effects exerted by different factors (fluctuations of the spontaneous emission intensity, nonequilibrium carrier concentration, injection current density) on the statistical characteristics o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::05d2cdb1160e641e6f200a98a6de4d2c
https://doi.org/10.33581/2520-2243-2019-3-12-21
https://doi.org/10.33581/2520-2243-2019-3-12-21
Publikováno v:
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XLIII-B2-2020, Pp 583-588 (2020)
In this paper, we propose a new method for knowledge distilling based on generative adversarial networks. Discriminator CNNs is used as an adaptive knowledge distilling loss. In experiments, single shot multibox detector SSD based on MobileNet v2 and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f2d4ba811fa95c4de1a4335c89ee6d6d
https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B2-2020/583/2020/
https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B2-2020/583/2020/
