<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">izvestswsu</journal-id><journal-title-group><journal-title xml:lang="ru">Известия Юго-Западного государственного университета</journal-title><trans-title-group xml:lang="en"><trans-title>Proceedings of the Southwest State University</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2223-1560</issn><issn pub-type="epub">2686-6757</issn><publisher><publisher-name>ЮЗГУ</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.21869/2223-1560-2019-23-3-113-134</article-id><article-id custom-type="elpub" pub-id-type="custom">izvestswsu-534</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>Информатика, вычислительная техника и управление</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>Computer science, computer engineering and IT managment</subject></subj-group></article-categories><title-group><article-title>Применение глубоких нейронных сетей в задаче получения карты глубины из двумерного изображения</article-title><trans-title-group xml:lang="en"><trans-title>Application of Deep Neural Networks in the Problem  of Obtaining Depth Maps from Two-Dimensional Images</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Михальченко</surname><given-names>Д. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Mihalchenko</surname><given-names>D. I.</given-names></name></name-alternatives><bio xml:lang="ru"/><bio xml:lang="en"/><email xlink:type="simple">tekatodsham@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Ивин</surname><given-names>А. Г.</given-names></name><name name-style="western" xml:lang="en"><surname>Ivin</surname><given-names>A. G.</given-names></name></name-alternatives><bio xml:lang="ru"/><bio xml:lang="en"/><email xlink:type="simple">arssivka@yandex.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Сивченко</surname><given-names>О. Ю.</given-names></name><name name-style="western" xml:lang="en"><surname>Sivchenko</surname><given-names>O. Yu.</given-names></name></name-alternatives><bio xml:lang="ru"/><bio xml:lang="en"/><email xlink:type="simple">adrelian@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Аксаментов</surname><given-names>Е. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Aksamentov</surname><given-names>E. A.</given-names></name></name-alternatives><bio xml:lang="ru"/><bio xml:lang="en"/><email xlink:type="simple">Egor.aksamentov.96@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Санкт-Петербургский институт информатики и автоматизации РАН</institution></aff><aff xml:lang="en"><institution>St. Petersburg Institute for Informatics and Auto-mation of the Russian Academy of Sciences</institution></aff></aff-alternatives><pub-date pub-type="collection"><year>2019</year></pub-date><pub-date pub-type="epub"><day>07</day><month>09</month><year>2019</year></pub-date><volume>23</volume><issue>3</issue><fpage>113</fpage><lpage>134</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Михальченко Д.И., Ивин А.Г., Сивченко О.Ю., Аксаментов Е.А., 2019</copyright-statement><copyright-year>2019</copyright-year><copyright-holder xml:lang="ru">Михальченко Д.И., Ивин А.Г., Сивченко О.Ю., Аксаментов Е.А.</copyright-holder><copyright-holder xml:lang="en">Mihalchenko D.I., Ivin A.G., Sivchenko O.Y., Aksamentov E.A.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://izvestswsu.elpub.ru/jour/article/view/534">https://izvestswsu.elpub.ru/jour/article/view/534</self-uri><abstract><sec><title>Цель исследования</title><p>Цель исследования. исследование подходов к генерации карт глубины для проверки и обучения глубоких нейронных сетей. Рассматривается проблема получения информации о расстоянии от камеры до объекта сцены по 2D-изображению при помощи глубоких нейронных сетей без использования стереокамеры.</p></sec><sec><title>Методы</title><p>Методы. Генерация 3D-сцен для обучения и оценки нейронной сети осуществлялась при помощи приложения 3D-компьютерной графики Blender. Для оценки точности обучения было использовано среднеквадратическое отклонение (СКО). Машинное обучение было реализовано при помощи библиотеки Keras, а оптимизация – с использованием подхода AdaGrad.</p></sec><sec><title>Результаты</title><p>Результаты. Представлена архитектура глубокой нейронной сети, которая на вход получает три последовательности 2D-изображений из видеопотока 3D-сцены и выдает на выходе предсказанную карту глубины для рассматриваемой 3D-сцены. Описан способ создания обучающих наборов данных, содержащих информацию о глубине карты с использованием программного обеспечения Blender. Рассматривается проблема переобучения, заключающаяся в следующем: созданные модели работают на специально сгенерированных наборах данных, но все еще не могут предсказать правильную карту глубины для случайных изображений. Представлены результаты тестирования актуальных способов создания карт глубины с использованием глубоких нейронных сетей.</p></sec><sec><title>Заключение</title><p>Заключение. Основной проблемой предложенного метода является переобучение, которое может быть выражено в прогнозировании некого среднего значения для разных изображений или предсказании одного и того же выхода для разных входов. Для решения данной проблемы могут быть использованы уже обученные сети или обучающие и вариационные выборки, содержащие 2D-изображения различных сцен.</p></sec></abstract><trans-abstract xml:lang="en"><p>Purpose of research is to study approaches to the depth map generation for deep neural networks testing and learning. The problem of obtaining information about the distance from the camera to the scenery object using a 2D image by means of deep neural networks without applying a stereocamera is considered.</p><sec><title>Methods</title><p>Methods. Generation of 3D scenery for training and assessment of the neural network was carried out using the 3D-computer graphics application Blender. The standard deviation (RMS) was used to estimate the accuracy of learning. Machine learning was implemented using the Keras library and optimization was implemented using the AdaGrad approach.</p></sec><sec><title>Results</title><p>Results. The architecture of a deep neural network which receives three sequences of 2D images from the 3D scenery video stream in the input and outputs the predicted depth map for the considered 3D scenery, is provided. The method for creating training data sets containing information about the depth of the map using Blender software is described. The problem of overtraining involving the fact that the created models work using specially generated data sets but still can not predict the correct depth map for random images is studied. The results of the testing actual methods for depth maps creation using deep neural networks are presented.</p></sec><sec><title>Conclusion</title><p>Conclusion. The main problem of the proposed method is overtraining which can be expressed in predicting a certain average value for different images or predicting the same output for different inputs. To solve this problem, we can use already trained networks or training and variation samples containing 2D images of different sceneries.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>компьютерное зрение</kwd><kwd>карты глубины</kwd><kwd>глубокое обучение</kwd><kwd>глубокие нейронные сети</kwd><kwd>цифровая обработка изображений</kwd><kwd>распознавание образов</kwd><kwd>нейронные сети</kwd><kwd>трехмерное очувствление</kwd></kwd-group><kwd-group xml:lang="en"><kwd>computer vision</kwd><kwd>depth map</kwd><kwd>deep learning</kwd><kwd>deep neural networks</kwd><kwd>digital image processing</kwd><kwd>image recognition</kwd><kwd>neural networks</kwd><kwd>3-D sensing</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Levonevskiy D., Vatamaniuk I., Saveliev A. Integration of corporate electronic services into a smart space using temporal logic of actions // International Conference on Interactive Collaborative Robotics. Springer, Cham. 2017. 10459. Р. 134143. DOI: 10.1007/9783319664712_15.</mixed-citation><mixed-citation xml:lang="en">Levonevskiy D., Vatamaniuk I., Saveliev A. Integration of corporate electronic services into a smart space using temporal logic of actions. International Conference on Interactive Collaborative Robotics, Springer, Cham 2017; 10459, pp. 134143. DOI: 10.1007/9783319664712_15.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Conceptual model of cyberphysical environment based on collaborative work of distributed means and mobile robots / A. Ronzhin, A. Saveliev, O. Basov, S. Solyonyj // International Conference on Interactive Collaborative Robotics. Springer, Cham. 2016. Vol. 9812. P. 3239. DOI: 10.1007/9783319439556_5.</mixed-citation><mixed-citation xml:lang="en">Ronzhin A., Saveliev A., Basov O., Solyonyj S. Conceptual model of cyberphysical environment based on collaborative work of distributed means and mobile robots. International Conference on Interactive Collaborative Robotics. Springer, Cham 2016; 9812, pp. 3239. DOI: 10.1007/9783319439556_5.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Scenarios of multimodal information navigation services for users in cyberphysical environment / I. Vatamaniuk, D. Levonevskiy, A. Saveliev, A. Denisov // International Conference on Speech and Computer. Springer, Cham. 2016. Vol. 9811. P. 588595. DOI: 10.1007/9783319439587_71.</mixed-citation><mixed-citation xml:lang="en">Vatamaniuk I., Levonevskiy D., Saveliev A., Denisov A Scenarios of multimodal information navigation services for users in cyberphysical environment. International Conference on Speech and Computer. Springer, Cham 2016; 9811, pp. 588595. DOI: 10.1007/9783319439587_71.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Richards H.W. Method and apparatus for user interaction for virtual measurement using a depth camera system // U.S. Patent Application No 20170302908. 2017. Т. 15/132. С. 822.</mixed-citation><mixed-citation xml:lang="en">Richards HW. Method and apparatus for user interaction for virtual measurement using a depth camera system. U.S. Patent Application no. 20170302908, 2017, no. 15(132), p. 822.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">An efficient holefilling method based on depth map in 3D view generation / H. Liang, X. Su, Y. Liu, H. Xu, Y. Wang, X. Chen // 2017 International Conference on Optical Instruments and Technology: Optoelectronic Imaging/Spectroscopy and Signal Processing Technology. 2018. Vol. 10620, DOI: 10.1117/12.2293301.</mixed-citation><mixed-citation xml:lang="en">Liang H., Su X., Liu Y., Xu H., Wang Y., Chen X. An efficient holefilling method based on depth map in 3D view generation. 2017 International Conference on Optical Instruments and Technology: Optoelectronic Imaging/Spectroscopy and Signal Processing Technology, 2018; 10620. DOI: 10.1117/12.2293301.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Girshick R. Efficient regression of generalactivity human poses from depth images //2011 International Conference on Computer Vision. IEEE, 2011. P. 415422.</mixed-citation><mixed-citation xml:lang="en">Girshick R., Shotton J., Kohli P., Criminisi A., Fitzgibbon A. Efficient regression of generalactivity human poses from depth images. 2011 International Conference on Computer Vision, 2011, pp. 415422.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Sun Y. Developing a multifilter convolutional neural network for semantic segmentation using highresolution aerial imagery and LiDAR data //ISPRS journal of photogrammetry and remote sensing. 2018. Vol. 143. P. 314.</mixed-citation><mixed-citation xml:lang="en">Sun Y., Zhang X., Xin Q., Huang, J. Developing a multifilter convolutional neural network for semantic segmentation using highresolution aerial imagery and LiDAR data. ISPRS journal of photogrammetry and remote sensing, 2018, vol. 143, pp. 314.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Watts K.W. , Konolige K. Ground plane detection to verify depth sensor status for robot navigation // US Patent No. 9886035. 2018.</mixed-citation><mixed-citation xml:lang="en">Watts K.W., Konolige K., Konolige K. Ground plane detection to verify depth sensor status for robot. US Patent no. 9886035, 2018.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Tee Kit Tsun M., Lau B.T., Jo H. Siswoyo An improved indoor robot humanfollowing navigation model using depth camera // Active IR marker and proximity sensors fusion, Robotics. 2018. Vol. 7. № 1. P. 4. DOI: 0.3390/robotics7010004.</mixed-citation><mixed-citation xml:lang="en">Tee Kit Tsun M., Lau B., Siswoyo Jo H. An improved indoor robot humanfollowing navigation model using depth camera, active IR marker and proximity sensors fusion. Robotics, 2018, no. 7(1),  4 p. DOI: 0.3390/robotics7010004.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Горобцов А.С. Особенности решения уравнений метода обратной задачи для синтеза устойчивого управляемого движения шагающих роботов // Труды СПИИРАН. 2019. Т. 18, №1. С. 85122. DOI: 10.15622/sp.18.1.85122.</mixed-citation><mixed-citation xml:lang="en">Gorobtsov A.S., Andreev A.E., Markov A.E., Skorikov A.V., Tarasov P.S. Osobennosti resheniya uravnenii metoda obratnoi zadachi dlya sinteza ustoichivogo upravlyaemogo dvizheniya shagayushchikh robotov [Features of solving the inverse dynamic method equations for the synthesis of stable walking robots controlled motion]. Trudy SPIIRAN = SPIIRAS Proceedings, 2019, no. 18, pp. 85122. DOI: 10.15622/sp.18.1.85122 (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Алтухов В.Г. Вычисление расстояния до объекта на основе карты глубин полученной методом зеркального разделения изображений //Автоматика и программная инженерия. 2017. Т. 1. С. 6569.</mixed-citation><mixed-citation xml:lang="en">Altukhov V.G., Kolker A.B. Vychislenie rasstoyaniya do ob"ekta na osnove karty glubin poluchennoi metodom zerkal'nogo razdeleniya izobrazhenii [Calculation of the distance to the object based on the depth map obtained by the method of mirror image separation]. Avtomatika i programmnaya inzheneriya = Automation and Software Engineering, 2017, no. 1,  pp. 6569 (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Ерофеев М.В. Многослойное решение проблемы полупрозрачных границ при построении стереоскопических изображений //International Journal of Open Information Technologies. 2016. Т. 4. № 8.</mixed-citation><mixed-citation xml:lang="en">Erofeev M., Vatolin D. Mnogosloinoe reshenie problemy poluprozrachnykh granits pri postroenii stereoskopicheskikh izobrazhenii [A multilayered solution to the problem of translucent boundaries when building stereoscopic images]. International Journal of Open Information Technologies, 2016, no.4(8) (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Lin K.Y., Hang H.M. Depth Map Enhancement on RGBD Video Captured by Kinect V2 //2018 AsiaPacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE, 2018. С. 15301535.</mixed-citation><mixed-citation xml:lang="en">Lin K.Y., Hang H.M. Depth Map Enhancement on RGBD Video Captured by Kinect V2. 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2018, pp. 15301535.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Ульянов С.В. Разработка системы стереозрения для мобильного робота //Программные продукты и системы. 2017. Т. 30. № 3.</mixed-citation><mixed-citation xml:lang="en">Ulyanov S.V., Reshetnikov A.G., Koshelev K.V. Razrabotka sistemy stereozreniya dlya mobil'nogo robota [Development of a stereo vision system for a mobile robot]. Programmnye produkty i sistemy = Software products and systems. 2017; no. 30(3) (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Koch T. Evaluation of CNNbased singleimage depth estimation methods //Proceedings of the European Conference on Computer Vision (ECCV). 2018. С. 00.</mixed-citation><mixed-citation xml:lang="en">Koch T. Evaluation of CNNbased singleimage depth estimation methods. Proceedings of the European Conference on Computer Vision (ECCV), 2018.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Eigen D., Puhrsch C., Fergus R. Depth map prediction from a single image using a multiscale deep network // Advances in Neural Information Processing Systems. 2014. С. 23662374. arXiv: 1406.2283v1.</mixed-citation><mixed-citation xml:lang="en">Eigen D., Puhrsch C., Fergus R. Depth map prediction from a single image using a multiscale deep network. Advances in Neural Information Processing Systems, 2014, pp. 23662374. arXiv: 1406.2283v1.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Liu F., Shen C., Lin G. Deep convolutional neural fields for depth estimation from a single image // The IEEE Conference on Computer Vision and Pattern Recognition. 2015. С. 51625170. DOI: 10.1109/ CVPR.2015.7299152.</mixed-citation><mixed-citation xml:lang="en">Liu F., Shen C., Lin G., Deep convolutional neural fields for depth estimation from a single. The IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 51625170. DOI: 10.1109/ CVPR.2015.7299152.</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Laina I., Rupprecht C., Belagiannis V., Tombari F., Navab N. Deeper depth prediction with fully convolutional residual networks. CoRR, abs/1606.00373. 2016. DOI: 10.1109/3dv.2016.32. arXiv: 1606.00373.</mixed-citation><mixed-citation xml:lang="en">Laina I., Rupprecht C., Belagiannis V., Tombari F., Navab N. Deeper depth prediction with fully convolutional residual networks. CoRR, abs/1606.00373. 2016. DOI: 10.1109/3dv.2016.32.  arXiv: 1606.00373.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Li J., Klein R., Yao A. A twostreamed network for estimating finescaled depth maps from single rgb images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017. p. 3372–3380.</mixed-citation><mixed-citation xml:lang="en">Li J., Klein R., Yao A. A twostreamed network for estimating finescaled depth maps from single rgb images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 3372–3380.</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Применение нечётких нейронных сетей для определения типа кристаллических решёток, наблюдаемых на нано-масштабных изображениях / О.П. Солдатова, И.А. Лёзин, И.В. Лёзина, А.В. Куприянов, Д.В. Кирш // Компьютерная оптика. 2015. Т. 39, № 5. С. 787795. DOI: 10.18287/013424522015395787794.</mixed-citation><mixed-citation xml:lang="en">Soldatova O.P., Lyozin I.A., Lyozina I.V., Kupriyanov A.V., Kirsh D.V. Primenenie nechetkikh neironnykh setei dlya opredeleniya tipa kristallicheskikh reshetok, nablyudaemykh na nanomasshtabnykh izobrazheniyakh [Application of fuzzy neural networks for defining crystal lattice types in nanoscale images]. Komp'yuternaya optika = Computer Optics. 2015; no. 39(5): 787795. (In Russ.). DOI: 10.18287/013424522015395787794.</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">On the application of reservoir computing networks for noisy image recognition / A. Jalalvand, K. Demuynck, W.D. Neve, J.P. Martensa // Neurocomputing. 2018. Т. 277. С. 237248. DOI: 10.1016/j.neucom.2016.11.100.</mixed-citation><mixed-citation xml:lang="en">Jalalvand A., Demuynck K., Neve W.D., Martensa J.P. On the application of reservoir computing networks for noisy image recognition. Neurocomputing. 2018; 277: 237248. DOI: 10.1016/j.neucom.2016.11.100.</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Dutta S. Classification of diabetic retinopathy images by using deep learning models / S. Dutta, B. CS Manideep, S.M. Basha, R.D. Caytiles, N.Ch.S.N. Iyengar // International Journal of Grid and Distributed Computing. 2018. Т. 11. № 1. С. 89106. DOI: 10.14257/ijgdc.2018.11.1.09.</mixed-citation><mixed-citation xml:lang="en">Dutta S., Manideep B.CS., Basha S.M., Caytiles R.D., Iyengar N.Ch.S.N. Classification of diabetic retinopathy images by using deep learning models. International Journal of Grid and Distributed Computing. 2018; no. 11(1), pp. 89106. DOI: 10.14257/ ijgdc.2018.11.1.09.</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Сирота А.А., Дрюченко М.А. Обобщённые алгоритмы сжатия изображений на фрагментах произвольной формы и их реализация с использованием искусственных нейронных сетей // Компьютерная оптика. 2015. Т. 39, № 5. С. 751761. DOI: 10.18287/013424522015395751761.</mixed-citation><mixed-citation xml:lang="en">Sirota A.A., Dryuchenko M.A. Obobshchennye algoritmy szhatiya izobrazhenii na fragmentakh proizvol'noi formy i ikh realizatsiya s ispol'zovaniem iskusstvennykh neironnykh setei  [Generalized image compression algorithms for arbitrarilyshaped fragments and their implementation using artificial neural networks]. Komp'yuternaya optika = Computer Optics. 2015; 39(5): 751761. (In Russ.). DOI: 10.18287/013424522015395751761.</mixed-citation></citation-alternatives></ref><ref id="cit24"><label>24</label><citation-alternatives><mixed-citation xml:lang="ru">Реконструкция изображений в дифракционнооптических системах на основе сверточных нейронных сетей и обратной свертки / А.В. Никоноров, М.В. Петров, С.А. Бибиков, В.В. Кутикова, А.А. Морозов, Н.Л. Казанский // Компьютерная оптика. 2017. Т. 41, № 6. С. 875887. DOI: 10.18287/241261792017416875887.</mixed-citation><mixed-citation xml:lang="en">Nikonorov A.V., Petrov M.V., Bibikov S.A., Kutikova V.V., Morozov A.A., Kazanskij N.L. Rekonstruktsiya izobrazhenii v difraktsionnoopticheskikh sistemakh na osnove svertochnykh neironnykh setei i obratnoi svertki [Image restoration in diffractive optical systems using deep learning and deconvolution]. Komp'yuternaya optika = Computer Optics. 2017; no. 41(6), pp. 875887. (In Russ.). DOI: 10.18287/241261792017416875887.</mixed-citation></citation-alternatives></ref><ref id="cit25"><label>25</label><citation-alternatives><mixed-citation xml:lang="ru">Олейник А.Л. Алгоритмы взаимной реконструкции изображений лиц на основе методов проекции в собственные подпространства // Труды СПИИРАН. 2018. Т. 2, №57. С. 4574. DOI: 10.15622/sp.57.3</mixed-citation><mixed-citation xml:lang="en">Oleinik A.L., Kukharev, G.A. Algoritmy vzaimnoi rekonstruktsii izobrazhenii lits na osnove metodov proektsii v sobstvennye podprostranst [ Algorithms for Face Image Mutual Reconstruction by Means of TwoDimensional Projection Methods]. Trudy SPIIRAN = SPIIRAS Proceedings.  2018; 2(57): 4574. (In Russ.). DOI: 10.15622/sp.57.3.</mixed-citation></citation-alternatives></ref><ref id="cit26"><label>26</label><citation-alternatives><mixed-citation xml:lang="ru">Silberman N., Fergus R. Indoor scene segmentation using a structured light sensor // ICCV Workshop on 3D Representation and Recognition. 2011. P. 601608.</mixed-citation><mixed-citation xml:lang="en">Silberman N, Fergus R. Indoor scene segmentation using a structured light sensor. Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on; 2011, pp. 601608.</mixed-citation></citation-alternatives></ref><ref id="cit27"><label>27</label><citation-alternatives><mixed-citation xml:lang="ru">Hu J. et al. Revisiting single image depth estimation: toward higher resolution maps with accurate object boundaries //2019 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 2019. P. 10431051.</mixed-citation><mixed-citation xml:lang="en">Hu J., Ozay M., Zhang Y., Okatani T. Revisiting single image depth estimation: toward higher resolution maps with accurate object boundaries. 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), 2019, pp. 10431051.</mixed-citation></citation-alternatives></ref><ref id="cit28"><label>28</label><citation-alternatives><mixed-citation xml:lang="ru">Zhu J. Ma R. (2016), Realtime depth estimation from 2D images. Available at: http://cs231n.stanford.edu/reports/ 2016/pdfs/407_Report.pdf (accessed May 1, 2018).</mixed-citation><mixed-citation xml:lang="en">Zhu J. Ma R. (2016), Realtime depth estimation from 2D images. Available at: http://cs231n.stanford.edu/reports/2016/pdfs/407_Report.pdf (accessed May 1, 2018).</mixed-citation></citation-alternatives></ref><ref id="cit29"><label>29</label><citation-alternatives><mixed-citation xml:lang="ru">Simonyan K., Zisserman A. Very deep convolutional networks for largescale image recognition // 3rd International Conference on Learning Representations (ICLR). 2015. P. 114. arXiv: 1409.1556.</mixed-citation><mixed-citation xml:lang="en">Simonyan K., Zisserman A. Very deep convolutional networks for largescale image recognition. 3rd International Conference on Learning Representations (ICLR), 2015, pp. 114. arXiv: 1409.1556.</mixed-citation></citation-alternatives></ref><ref id="cit30"><label>30</label><citation-alternatives><mixed-citation xml:lang="ru">He L., Wang G., Hu Z. Learning depth from single images with deep neural network embedding focal length // IEEE Transactions on Image Processing. 2018. Vol. 27. № 9. P. 46764689.</mixed-citation><mixed-citation xml:lang="en">He L., Wang G., Hu Z. Learning depth from single images with deep neural network embedding focal length. IEEE Transactions on Image Processing, 2018, no. 27(9), pp. 46764689.</mixed-citation></citation-alternatives></ref><ref id="cit31"><label>31</label><citation-alternatives><mixed-citation xml:lang="ru">Liu M., Salzmann M., He X. Discretecontinuous depth estimation from a single image // The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2014. С. 716723. DOI: 10.1109 / CVPR.2014.97.</mixed-citation><mixed-citation xml:lang="en">Liu M., Salzmann M., He X. Discretecontinuous depth estimation from a single image. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 716723. DOI: 10.1109 / CVPR.2014.97.</mixed-citation></citation-alternatives></ref><ref id="cit32"><label>32</label><citation-alternatives><mixed-citation xml:lang="ru">Luo W., Schwing A.G., Urtasun R. Efficient deep learning for stereo matching // The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016. P. 56955703. DOI: 10.1109/CVPR.2016.614.</mixed-citation><mixed-citation xml:lang="en">Luo W., Schwing A.G., Urtasun R. Efficient deep learning for stereo matching. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 56955703. DOI: 10.1109/CVPR.2016.614.</mixed-citation></citation-alternatives></ref><ref id="cit33"><label>33</label><citation-alternatives><mixed-citation xml:lang="ru">Eigen D., Fergus R. Predicting depth, surface normals and semantic labels with a common multiscale convolutional architecture // The IEEE International Conference on Computer Vision (ICCV). 2015. P. 26502658. DOI: 10.1109 / ICCV.2015.304.</mixed-citation><mixed-citation xml:lang="en">Eigen D., Fergus R. Predicting depth, surface normals and semantic labels with a common multiscale convolutional architecture. The IEEE International Conference on Computer Vision (ICCV), 2015, pp. 26502658. DOI: 10.1109 / ICCV.2015.304.</mixed-citation></citation-alternatives></ref><ref id="cit34"><label>34</label><citation-alternatives><mixed-citation xml:lang="ru">Vision meets robotics: the KITTI dataset / A. Geiger, A. Lenz, C. Stiller, R. Urtasun // The International Journal of Robotics Research. 2013. Vol. 32. № 11. P. 12311237. DOI: 10.1177/0278364913491297.</mixed-citation><mixed-citation xml:lang="en">Geiger A., Lenz A., Stiller C., Urtasun R. Vision meets robotics: the KITTI dataset. The International Journal of Robotics Research, 2013, vol. 32, no. 11, pp. 12311237.  DOI: 10.1177/0278364913491297.</mixed-citation></citation-alternatives></ref><ref id="cit35"><label>35</label><citation-alternatives><mixed-citation xml:lang="ru">Saxena A., Sun M., Ng A.Y. Make3d: learning 3D scene structure from a single still image // IEEE Transactions on Pattern Analysis and Machine Intelligence. 2009. Vol. 31. № 5. P. 824840. DOI: 10.1109 / TPAMI.2008.132.</mixed-citation><mixed-citation xml:lang="en">Saxena A., Sun M., Ng A. Y. Make3d: learning 3D scene structure from a single still image. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, no. 31(5), pp. 824840. DOI: 10.1109 / TPAMI.2008.132.</mixed-citation></citation-alternatives></ref><ref id="cit36"><label>36</label><citation-alternatives><mixed-citation xml:lang="ru">Bogart R., Kainz F., Hess D. OpenEXR image file format / // ACM SIGGRAPH. 2003. Sketches &amp; Applications.</mixed-citation><mixed-citation xml:lang="en">Bogart R., Kainz F., Hess D. OpenEXR image file format. ACM SIGGRAPH 2003, Sketches &amp; Applications, 2003.</mixed-citation></citation-alternatives></ref><ref id="cit37"><label>37</label><citation-alternatives><mixed-citation xml:lang="ru">Kent B.R. 3D Scientific Visualization with Blender®, Morgan &amp; Claypool, San Rafael, 2015.</mixed-citation><mixed-citation xml:lang="en">Kent B.R. 3D Scientific Visualization with Blender, Morgan &amp; Claypool, San Rafael, 2015.</mixed-citation></citation-alternatives></ref><ref id="cit38"><label>38</label><citation-alternatives><mixed-citation xml:lang="ru">Valenza E. Blender 2.6 Cycles: Materials and Textures Cookbook – Third Edition. Packt Publishing Ltd. Birmingham. Mumbai. 2013. 280 с.</mixed-citation><mixed-citation xml:lang="en">Valenza E. Blender 2.6 Cycles: Materials and Textures Cookbook – Third Edition. Packt Publishing Ltd. Birmingham, Mumbai, 2013, 280 p.</mixed-citation></citation-alternatives></ref><ref id="cit39"><label>39</label><citation-alternatives><mixed-citation xml:lang="ru">Saxena A. Learning depth from single monocular images / A. Saxena, S.H. Chung, Y. Ng. Andrew // Neural Information Processing Systems (NIPS). 2005. P. 11611168. DOI: 10.1109/TPAMI.2015.2505283.</mixed-citation><mixed-citation xml:lang="en">Saxena A., Chung S.H., Andrew Y.Ng. Learning depth from single monocular images. Neural Information Processing Systems (NIPS), 2005, pp. 11611168. DOI: 10.1109/TPAMI.2015.2505283.</mixed-citation></citation-alternatives></ref><ref id="cit40"><label>40</label><citation-alternatives><mixed-citation xml:lang="ru">Saxena A., Chung S.H., Andrew Y. Ng. 3D depth reconstruction from a single still image // International Journal of Computer Vision. 2008. Vol. 76. № 1. P. 5369. DOI: 10.1109 / TPAMI.2008.132.</mixed-citation><mixed-citation xml:lang="en">Saxena A., Chung S.H., Andrew Y. Ng. 3D depth reconstruction from a single still image. International Journal of Computer Vision, 2008, no. 76(1), pp. 5369. DOI: 10.1109 / TPAMI.2008.132.</mixed-citation></citation-alternatives></ref><ref id="cit41"><label>41</label><citation-alternatives><mixed-citation xml:lang="ru">Glorot X., Bengio Y. Understanding the difficulty of training deep feedforward neural networks // Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. 2010. Vol. 9. P. 249256.</mixed-citation><mixed-citation xml:lang="en">Glorot X., Bengio Y. Understanding the difficulty of training deep feedforward neural networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010, no. 9, pp. 249256.</mixed-citation></citation-alternatives></ref><ref id="cit42"><label>42</label><citation-alternatives><mixed-citation xml:lang="ru">Heaton J. Artificial Intelligence For Humans: Deep Learning and Neural Networks / J. Heaton Heaton Research. Inc., St Louis, MO, 2015. Vol. 3. 375 p.</mixed-citation><mixed-citation xml:lang="en">Heaton J. Artificial Intelligence For Humans: Deep Learning and Neural Networks, Heaton Research. Inc., St Louis, MO 2015; no. 3.</mixed-citation></citation-alternatives></ref><ref id="cit43"><label>43</label><citation-alternatives><mixed-citation xml:lang="ru">Delving deep into rectifiers: surpassing humanlevel performance on imagenet classification / K. He, X. Zhang, S. Ren, J. Sun // Proceedings of the IEEE international conference on computer vision. 2015. P. 10261034. DOI: 10.1109 / ICCV.2015.123</mixed-citation><mixed-citation xml:lang="en">He K., Zhang X., Ren S., Sun J. Delving deep into rectifiers: surpassing humanlevel performance on imagenet. Proceedings of the IEEE international conference on computer vision, 2015; 10261034. DOI: 10.1109 / ICCV.2015, 123 p.</mixed-citation></citation-alternatives></ref><ref id="cit44"><label>44</label><citation-alternatives><mixed-citation xml:lang="ru">Keras: The Python Deep Learning library. Available at: https://keras.io/ (acceessed 31.08.2018)</mixed-citation><mixed-citation xml:lang="en">Keras library. Available at: https://keras.io/ (acceessed 31.08.2018).</mixed-citation></citation-alternatives></ref><ref id="cit45"><label>45</label><citation-alternatives><mixed-citation xml:lang="ru">Backends – TensorFlow or Theano. Available at: https://www.tensorflow.org/ (acceessed 31.08.2018)</mixed-citation><mixed-citation xml:lang="en">Backends–TensorFlow or Theano. Available at: www.tensorflow.org/ (acceessed 31.08.2018).</mixed-citation></citation-alternatives></ref><ref id="cit46"><label>46</label><citation-alternatives><mixed-citation xml:lang="ru">TensorFlow: a system for largescale machine learning / M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, M. Kudlur, J. Levenberg, R. Monga, S. Moore, D.G. Murray, B. Steiner, P. Tucker, V. Vasudevan, P. Warden, M. Wicke, Y. Yu, X. Zheng, G. Brain // the 12th USENIX Symposium on Operating Systems Designand Implementation (OSDI ’16). Nov. 24. 2016. P. 265283.</mixed-citation><mixed-citation xml:lang="en">Abadi M., Barham P., Chen J., Chen Z., Davis A., Dean J., Devin M., Ghemawat S., Irving G., Isard M., Kudlur M., Levenberg J., Monga R., Moore S., Murray D.G., Steiner B., Tucker P., Vasudevan V., Warden P., Wicke M., Yu Y., Zheng X., Brain G. TensorFlow: a system for largescale machine learning. The 12th USENIX Symposium on Operating Systems Designand Implementation (OSDI ’16), Nov. 24, 2016; pp. 265283.</mixed-citation></citation-alternatives></ref><ref id="cit47"><label>47</label><citation-alternatives><mixed-citation xml:lang="ru">Tensorflow: largescale machine learning on heterogeneous distributed systems / M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G.S. Corrado, A. Davis, J. Dean, M. Devin, S. Ghemawat, I. Goodfellow, A. Harp, G. Irving, M. Isard, Y. Jia, R. Jozefowicz, L. Kaiser, M. Kudlur, J. Levenberg, D. Mane, R. Monga, S. Moore, D. Murray, C. Olah, M. Schuster, J. Shlens, B. Steiner, I. Sutskever, K. Talwar, P. Tucker, V. Vanhoucke, V.Vasudevan, F. Viegas, O. Vinyals, P. Warden, M. Wattenberg, M. Wicke, Y. Yu, X. Zheng // (2016b). Available at: https://arxiv.org/pdf/1603.04467.pdf (accessed May 1, 2018).</mixed-citation><mixed-citation xml:lang="en">Abadi M., Agarwal A., Barham P., Brevdo E., Chen Z., Citro C., Corrado G.S., Davis A., Dean J., Devin M., Ghemawat S., Goodfellow I., Harp A., Irving G., Isard M., Jia Y., Jozefowicz R., Kaiser L., Kudlur M., Levenberg J., Mane D., Monga R., Moore S., Murray D., Olah C., Schuster M., Shlens J., Steiner B., Sutskever I., Talwar K., Tucker P., Vanhoucke V., Vasudevan V., Viegas F., Vinyals O., Warden P., Wattenberg M., Wicke M., Yu Y., Zheng X. Tensorflow: largescale machine learning on heterogeneous distributed systems. (2016b). Available at: https://arxiv.org/pdf/ 1603.04467.pdf (accessed May 1, 2018).</mixed-citation></citation-alternatives></ref><ref id="cit48"><label>48</label><citation-alternatives><mixed-citation xml:lang="ru">Duchi J., Hazan E., Singer Y. Adaptive subgradient methods for online learning and stochastic optimization // Journal of Machine Learning Research. July. 2011. Vol. 12. P. 21212159.</mixed-citation><mixed-citation xml:lang="en">Duchi J., Hazan E., Singer Y. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research. July 2011; 12: pp. 21212159.</mixed-citation></citation-alternatives></ref><ref id="cit49"><label>49</label><citation-alternatives><mixed-citation xml:lang="ru">Reduction of overfitting in diabetes prediction using deep learning neural network / A. Ashiquzzaman, A.K. Tushar, Md. R. Islam, D. Shon, K. Im, J.H. Park, D.S. Lim, J. Kim // 2017 IT Convergence and Security. Springer, Singapore. 2018. Vol. 449. P. 3543. DOI: 10.1007/9789811064517_5.</mixed-citation><mixed-citation xml:lang="en">Ashiquzzaman A., Tushar A.K., Islam MdR., Shon D., Im K., Park J.H, Lim D.S, Kim J, Reduction of overfitting in diabetes prediction using deep learning neural network. 2017 IT Convergence and Security, Springer, Singapore 2018; 449, pp. 3543. DOI: 10.1007/9789811064517_5.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
