<?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">zhps</journal-id><journal-title-group><journal-title xml:lang="ru">Журнал прикладной спектроскопии</journal-title><trans-title-group xml:lang="en"><trans-title>Zhurnal Prikladnoii Spektroskopii</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">0514-7506</issn><publisher><publisher-name>B. I. Stepanov Institute of Physics of the National Academy of Sciences</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.47612/0514-7506-2022-89-2-275-282</article-id><article-id custom-type="elpub" pub-id-type="custom">zhps-1012</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>Статьи</subject></subj-group></article-categories><title-group><article-title>Обнаружение и классификация транспортных средств на снимках сверхвысокого разрешения с помощью нейронных сетей</article-title><trans-title-group xml:lang="en"><trans-title>Detection and Classification of Vehicles in Ultra-High Resolutions Images Using Neural Networks</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>Chen</surname><given-names>Ch.</given-names></name><name name-style="western" xml:lang="en"><surname>Chen</surname><given-names>Ch.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Ханчжоу</p></bio><bio xml:lang="en"><p>Hangzhou</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Минальд</surname><given-names>А. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Мinald</surname><given-names>A. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Минск</p></bio><bio xml:lang="en"><p>Minsk </p></bio><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Богуш</surname><given-names>Р. П.</given-names></name><name name-style="western" xml:lang="en"><surname>Bohush</surname><given-names>R. P.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Новополоцк</p></bio><bio xml:lang="en"><p>Novopolotsk </p></bio><xref ref-type="aff" rid="aff-3"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Ma</surname><given-names>G.</given-names></name><name name-style="western" xml:lang="en"><surname>Ma</surname><given-names>G.</given-names></name></name-alternatives><bio xml:lang="ru"><p> Хучжоу</p></bio><bio xml:lang="en"><p>Huzhou </p></bio><xref ref-type="aff" rid="aff-4"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Weichen</surname><given-names>Y.</given-names></name><name name-style="western" xml:lang="en"><surname>Weichen</surname><given-names>Y.</given-names></name></name-alternatives><bio xml:lang="ru"><p> Хучжоу</p></bio><bio xml:lang="en"><p>Huzhou </p></bio><xref ref-type="aff" rid="aff-4"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Абламейко</surname><given-names>С. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Аblameyko</surname><given-names>S. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Минск</p></bio><bio xml:lang="en"><p>Minsk </p></bio><email xlink:type="simple">ablameyko@yandex.by</email><xref ref-type="aff" rid="aff-5"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Школа информационных наук и технологий Университета Чжэцзяна Шурен;&#13;
База международного научно-технического сотрудничества провинции Чжэцзян по обработке и применению изображений дистанционного зондирования</institution></aff><aff xml:lang="en"><institution>School of Information Science and Technology at Zhejiang Shuren University; International Science and Technology Cooperation Base of Zhejiang Province: Remote Sensing Image Processing and Application</institution></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Белорусский государственный университет</institution></aff><aff xml:lang="en"><institution>Belarusian State University</institution></aff></aff-alternatives><aff-alternatives id="aff-3"><aff xml:lang="ru"><institution>Полоцкий государственный университет</institution></aff><aff xml:lang="en"><institution>Polotsk State University</institution></aff></aff-alternatives><aff-alternatives id="aff-4"><aff xml:lang="ru"><institution>EarthView Image Inc.</institution></aff><aff xml:lang="en"><institution>EarthView Image Inc.</institution></aff></aff-alternatives><aff-alternatives id="aff-5"><aff xml:lang="ru"><institution>Белорусский государственный университет;&#13;
Объединенный институт проблем информатики НАН Беларуси</institution></aff><aff xml:lang="en"><institution>Belarusian State University;&#13;
United Institute for Informatics Problems, National Academy of Sciences of Belarus</institution></aff></aff-alternatives><pub-date pub-type="collection"><year>2022</year></pub-date><pub-date pub-type="epub"><day>24</day><month>03</month><year>2022</year></pub-date><volume>89</volume><issue>2</issue><fpage>275</fpage><lpage>282</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Chen C., Минальд А.А., Богуш Р.П., Ma G., Weichen Y., Абламейко С.В., 2022</copyright-statement><copyright-year>2022</copyright-year><copyright-holder xml:lang="ru">Chen C., Минальд А.А., Богуш Р.П., Ma G., Weichen Y., Абламейко С.В.</copyright-holder><copyright-holder xml:lang="en">Chen C., Мinald A.A., Bohush R.P., Ma G., Weichen Y., Аblameyko S.V.</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://zhps.ejournal.by/jour/article/view/1012">https://zhps.ejournal.by/jour/article/view/1012</self-uri><abstract><p>Предлагается архитектура глубокой нейронной сети, основанная на интеграции сверточной нейронной сети Faster R-CNN с модулем Feature Pyramid Network. На основе данного подхода разработан алгоритм обнаружения и классификации транспортных средств на изображениях и соответствующая модель. Для обучения предложенной модели использована кроссплатформенная среда ML.NET. Представлены результаты сравнения эффективности применения предложенного подхода и сверточных нейронных сетей YOLO v4 и Faster R-CNN. Показано улучшение точности обнаружения и локализации разных типов транспортных средств на снимках сверхвысокого разрешения. Приведены примеры обработки изображений земной поверхности сверхвысокого разрешения и даны соответствующие рекомендации.</p></abstract><trans-abstract xml:lang="en"><p>The paper proposes a deep neural network architecture based on the integration of the convolutional neural network Faster R-CNN with the Feature Pyramid Network module. Based on this approach, an algorithm for detecting and classifying vehicles in images and a corresponding model have been developed. A cross-platform environment ML.NET was used to train the proposed model. The results of comparing the effectiveness of the proposed approach and convolutional neural networks YOLO v4 and Faster R-CNN are presented. The improvement of the accuracy of detection and localization of different types of vehicles in ultra-high resolutions images is shown. Examples of processing ultra-high resolutions remote sensing images and appropriate recommendations are given.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>обнаружение и классификация объектов</kwd><kwd>изображения земной поверхности</kwd><kwd>изображения сверхвысокого разрешения</kwd><kwd>нейронная сеть</kwd></kwd-group><kwd-group xml:lang="en"><kwd>object detection and classification</kwd><kwd>remote sensing images</kwd><kwd>ultra-high resolutions images</kwd><kwd>neural network</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Работа выполнена при частичной финансовой поддержке Национальной программы набора иностранных экспертов (гранты № G2021016001L, G2021016002L) и Базовой программы исследований общественного благосостояния провинции Чжэцзян (грант № LGJ19F020002).</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Yuntao Li, Zhihuan Wu, Lei Li, Daoning Yang, Hongfeng Pang. J. Appl. Remote Sens., 15, N 2 (2021) 026505, doi: 10.1117/1.JRS.15.026505</mixed-citation><mixed-citation xml:lang="en">Yuntao Li, Zhihuan Wu, Lei Li, Daoning Yang, Hongfeng Pang. J. Appl. Remote Sens., 15, N 2 (2021) 026505, doi: 10.1117/1.JRS.15.026505</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Q. Tan, J. Ling, J. Hu, X. Qin, J. Hu. IEEE Access, 8 (2020) 153394—153402, doi: 10.1109/ACCESS.2020.3017894</mixed-citation><mixed-citation xml:lang="en">Q. Tan, J. Ling, J. Hu, X. Qin, J. Hu. IEEE Access, 8 (2020) 153394—153402, doi: 10.1109/ACCESS.2020.3017894</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Y. Koga, H. Miyazaki, R. Shibasaki. Remote Sens., 12 (2020) 575, doi: 10.3390/rs12030575</mixed-citation><mixed-citation xml:lang="en">Y. Koga, H. Miyazaki, R. Shibasaki. Remote Sens., 12 (2020) 575, doi: 10.3390/rs12030575</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">L. Yongxi, T. Javidi. Proc. 53rd Annual Allerton Conf. Communication, Control, and Computing (2015) 1091—1098, doi: 10.1109/ALLERTON.2015.7447130</mixed-citation><mixed-citation xml:lang="en">L. Yongxi, T. Javidi. Proc. 53rd Annual Allerton Conf. Communication, Control, and Computing (2015) 1091—1098, doi: 10.1109/ALLERTON.2015.7447130</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">W. Shao, W. Yang, G. Liu, J. Liu. Proc. IEEE Int. Geoscience and Remote Sensing Symposium (2012) 4379—4382, doi: 10.1109/IGARSS.2012.6350403</mixed-citation><mixed-citation xml:lang="en">W. Shao, W. Yang, G. Liu, J. Liu. Proc. IEEE Int. Geoscience and Remote Sensing Symposium (2012) 4379—4382, doi: 10.1109/IGARSS.2012.6350403</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">D. Vorobjov, I. Zakharova, R. Bohush, S. Ablameyko. Advances in Neural Networks-ISNN2018.</mixed-citation><mixed-citation xml:lang="en">D. Vorobjov, I. Zakharova, R. Bohush, S. Ablameyko. Advances in Neural Networks-ISNN2018.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Lecture Notes in Computer Science, 10878 (2018) 503—510, doi: 10.1007/978-3-319-92537-0</mixed-citation><mixed-citation xml:lang="en">Lecture Notes in Computer Science, 10878 (2018) 503—510, doi: 10.1007/978-3-319-92537-0</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">И. Н. Пугачев, Г. Я. Маркелов, В. С. Тормозов. Вестн. ТОГУ, 45, № 2 (2017) 13—20</mixed-citation><mixed-citation xml:lang="en">И. Н. Пугачев, Г. Я. Маркелов, В. С. Тормозов. Вестн. ТОГУ, 45, № 2 (2017) 13—20</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Xungen Li, Feifei Men, Shuaishuai Lv, Xiao Jiang, Mian Pan, Qi Ma, Haibin Yu. ISPRS Int. J. GeoInformation, 10 (2021) 549, doi: 10.3390/ijgi10080549</mixed-citation><mixed-citation xml:lang="en">Xungen Li, Feifei Men, Shuaishuai Lv, Xiao Jiang, Mian Pan, Qi Ma, Haibin Yu. ISPRS Int. J. GeoInformation, 10 (2021) 549, doi: 10.3390/ijgi10080549</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">A. Froidevaux, A. Julier, A. Lifschitz, M. Pham, R. Dambreville, S. Lefèvre, P. Lassalle, T. Huynh. IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium, Sept. (2020) 256—259, ff10.1109/IGARSS39084.2020.9323827ff. ffhal-03213855</mixed-citation><mixed-citation xml:lang="en">A. Froidevaux, A. Julier, A. Lifschitz, M. Pham, R. Dambreville, S. Lefèvre, P. Lassalle, T. Huynh. IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium, Sept. (2020) 256—259, ff10.1109/IGARSS39084.2020.9323827ff. ffhal-03213855</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">R. Girshick, J. Donahue, T. Darrell, J. Malik. IEEE Transact. Pattern Analysis and Machine Intelligence, 38 (2016) 142—158</mixed-citation><mixed-citation xml:lang="en">R. Girshick, J. Donahue, T. Darrell, J. Malik. IEEE Transact. Pattern Analysis and Machine Intelligence, 38 (2016) 142—158</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">R. Girshick. Proc. IEEE Int. Conf. Computer Vision. Santiago, Chile (2015) 1440—1448</mixed-citation><mixed-citation xml:lang="en">R. Girshick. Proc. IEEE Int. Conf. Computer Vision. Santiago, Chile (2015) 1440—1448</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">S. Ren, K. He, R. Girshick, J. Sun. IEEE Transact. Pattern Analysis and Machine Intelligence, 39 (2015) 1137—1149</mixed-citation><mixed-citation xml:lang="en">S. Ren, K. He, R. Girshick, J. Sun. IEEE Transact. Pattern Analysis and Machine Intelligence, 39 (2015) 1137—1149</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">D. R. Lucio, R. Laroca, L. A. Zanlorensi, G. Moreira, D. Menotti. Region Detection Using Coarse Annotations, doi: 10.1109/SIBGRAPI.2019.00032, arXiv:1908.00069</mixed-citation><mixed-citation xml:lang="en">D. R. Lucio, R. Laroca, L. A. Zanlorensi, G. Moreira, D. Menotti. Region Detection Using Coarse Annotations, doi: 10.1109/SIBGRAPI.2019.00032, arXiv:1908.00069</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">T.-Yi Lin, P. Dollar, R. Girshick, K. He, B. Hariharan, S. Belongie. Feature Pyramid Networks for Object Detection arXiv:1612.03144v2 [cs.CV] 19 Apr 2017</mixed-citation><mixed-citation xml:lang="en">T.-Yi Lin, P. Dollar, R. Girshick, K. He, B. Hariharan, S. Belongie. Feature Pyramid Networks for Object Detection arXiv:1612.03144v2 [cs.CV] 19 Apr 2017</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">https://github.com/jekhor/aerial-cars-dataset</mixed-citation><mixed-citation xml:lang="en">https://github.com/jekhor/aerial-cars-dataset</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">M. Everingham, L. V. Gool, C. K. I. Williams, J. Winn, A. Zisserman. Int. J. Computer Vision, 88 (2010) 303—338, doi: 10.1007/s11263-009-0275-4</mixed-citation><mixed-citation xml:lang="en">M. Everingham, L. V. Gool, C. K. I. Williams, J. Winn, A. Zisserman. Int. J. Computer Vision, 88 (2010) 303—338, doi: 10.1007/s11263-009-0275-4</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">https://arxiv.org/pdf/2004.10934.pdf</mixed-citation><mixed-citation xml:lang="en">https://arxiv.org/pdf/2004.10934.pdf</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>
