<?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">vimjour</journal-id><journal-title-group><journal-title xml:lang="ru">Сельскохозяйственные машины и технологии</journal-title><trans-title-group xml:lang="en"><trans-title>Agricultural Machinery and Technologies</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2073-7599</issn><publisher><publisher-name>Federal State Budgetary Scientific Institution «Federal Scientific Agroengineering Center VIM»</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.22314/2073-7599-2022-16-3-74-80</article-id><article-id custom-type="elpub" pub-id-type="custom">vimjour-486</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>ТЕХНИКА ДЛЯ РАСТЕНИЕВОДСТВА</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>MACHINERY FOR PLANT GROWING</subject></subj-group></article-categories><title-group><article-title>Разработка алгоритма роботизированного устройства точного внесения средств защиты растений</article-title><trans-title-group xml:lang="en"><trans-title>Developing an Algorithm for Robotic Precision Application of Crop Protection Products</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>Мирзаев</surname><given-names>М. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Mirzaev</surname><given-names>M. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Максим Арифович Мирзаев, аспирант, младший научный сотрудник</p><p>Москва</p></bio><bio xml:lang="en"><p>Maksim A. Mirzaev, Ph.D. student, junior researcher</p><p>Moscow</p></bio><email xlink:type="simple">mirza.pochta@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Федеральный научный агроинженерный центр ВИМ</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Federal Scientific Agroengineering Center VIM</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2022</year></pub-date><pub-date pub-type="epub"><day>02</day><month>10</month><year>2022</year></pub-date><volume>16</volume><issue>3</issue><fpage>74</fpage><lpage>80</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Мирзаев М.А., 2022</copyright-statement><copyright-year>2022</copyright-year><copyright-holder xml:lang="ru">Мирзаев М.А.</copyright-holder><copyright-holder xml:lang="en">Mirzaev M.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://www.vimsmit.com/jour/article/view/486">https://www.vimsmit.com/jour/article/view/486</self-uri><abstract><p>Показали, что широкий спектр методик и инструментов для идентификации растений ограничен в реальных агротехнических задачах. Отметили, что параметры изображений сильно отличаются в прикладных решениях. (Цель исследования) Разработать алгоритм распознавания культурных растений роботизированным устройством, основанный на современном методе глубокого обучения с использованием сверточной нейронной сети R-CNN. (Материалы и методы) Создали роботизированное устройство для дифференцированного внесения средств защиты растений, которое способно распознавать полезную культуру и сорную растительность, определять площадь обработки по координатам центра и рдиусу. Для обнаружения сельскохозяйственной культуры (белокочанной капусты) выбрали сегментирующие нейронные сети Mask R-CNN и Deeplabv3 plus. Алгоритм на основе данных сетей обнаруживает, сегментирует и позиционирует растения на основе набора данных, собранных в форматах «изображение – маска» и COCO dataset. Набор данных формировали путем аэросъемки с помощью беспилотного воздушного судна. Исходные изображения получили от веб-камеры Xiaovv HD Web USB с углом съемки 150 градусов, разрешением Full HD 1080P и веб-камеры Logitech C270 с разрешением HD 720p. Обученную нейронную сеть для роботизированного устройства установили на платформу Nvidia Jetson AGX Xavier. (Результаты и обсуждение) В результате оценки точности модели на тестовых данных получили следующие значения: количество найденных растений – 98 процентов, точность выделения контура – 94 процента. (Выводы) Доказали, что обученную нейронную сеть можно применять к любым выращиваемым культурам, учитывая неоднородность их расположения на поле, типы почвы, количество сорной растительности. По итогу модель обучили извлекать координаты ограничительной рамки и местоположение объекта (капусты) по пикселям с требуемой точностью как для синтетических, так и для реальных данных.</p></abstract><trans-abstract xml:lang="en"><p>The existing range of plant identification methods and tools is considered limited in real agrotechnical tasks. The image parameters tend to differ significantly in applied solutions. (Research purpose) To develop an algorithm for crop plant recognition by a robotic device using a state-of-the-art convolutional neural network (R-CNN) and deep learning technology. (Materials and methods) A robotic device has been developed for variable rate application of plant protection products able to recognize both useful crops and weeds, determine the area of processing, namely the coordinates of the processing center and the processing radius. Mask R-CNN and Deeplabv3 plus segmenting neural networks were chosen for crop (white head cabbage) detection. The network-based algorithm detects, segments, and positions plants based on a dataset collected in the image-mask and COCO dataset formats. The data set was formed by aerial photography using an unmanned aircraft. The original images are taken by Xiaovv HD Web USB 150 degree Full HD 1080P webcam and Logitech C270 HD 720p webcam. The trained neural network for the robotic device was installed on the Nvidia Jetson AGX Xavier platform. (Results and discussion) As a result of assessing the accuracy of the model on the test data, the following values were obtained: the number of plants detected is 98 percent, the accuracy of contour detection is 94 percent. (Conclusions) It is proved that the trained neural network can be applied to any cultivated crops, taking into account the heterogeneity of their location in the field, soil types, and the percentage of weeds. As a result, the model is trained to extract the bounding box coordinates and the object (cabbage) location by pixels with the required accuracy for both synthetic and real data.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>дифференцированное внесение средств защиты растений</kwd><kwd>обучение нейронной сети</kwd><kwd>Mask R-CNN</kwd><kwd>Deeplabv3 plus</kwd><kwd>точное земледелие</kwd><kwd>распознавание растений</kwd></kwd-group><kwd-group xml:lang="en"><kwd>variable rate application of plant protection products</kwd><kwd>neural network training</kwd><kwd>Mask R-CNN</kwd><kwd>Deeplabv3 plus</kwd><kwd>precision farming</kwd><kwd>plant recognition.</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">Мирзаев М.А. Проектирование автономного полевого робота для дифференцированного внесения агрохимических средств // Электротехнологии и электрооборудование в АПК. 2021. Т. 68. N4(45). С. 131-136.</mixed-citation><mixed-citation xml:lang="en">Mirzaev M.A. Proektirovanie avtonomnogo polevogo robota dlya differentsirovannogo vneseniya agrokhimicheskikh sredstv [Design of an autonomous field robot for differentiated application of agrochemical agents]. Elektrotekhnologii i elektrooborudovanie v APK. 2021. Vol. 68. N4(45). 131-136 (In Russian).</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Zhao K., et al. Building extraction from satellite images using mask R-CNN with building boundary regularization. Proceedings of the IEEE conference on computer vision and pattern recognition workshops. 2018. 247-251.</mixed-citation><mixed-citation xml:lang="en">Zhao K., et al. Building extraction from satellite images using mask R-CNN with building boundary regularization. Proceedings of the IEEE conference on computer vision and pattern recognition workshops. 2018. 247-251 (In English).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Weber M., et al. Deeplab2: A tensorflow library for deep labeling. arXiv preprint arXiv:2106. 09748v1. 2021.</mixed-citation><mixed-citation xml:lang="en">Weber M., et al. Deeplab2: A tensorflow library for deep labeling. arXiv preprint arXiv:2106.09748v1. 2021 (In English).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Wang H., et al. Max-deeplab: End-to-end panoptic segmentation with mask transformers. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021. 5463-5474.</mixed-citation><mixed-citation xml:lang="en">Wang H., et al. Max-deeplab: End-to-end panoptic segmentation with mask transformers. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021. 5463-5474 (In English).</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Caesar H., Uijlings J., Ferrari V. Coco-stuff: Thing and stuff classes in context. Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. 1209-1218.</mixed-citation><mixed-citation xml:lang="en">Caesar H., Uijlings J., Ferrari V. Coco-stuff: Thing and stuff classes in context. Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. 1209-1218 (In English).</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Jeon J., et al. Run your visual-inertial odometry on NVIDIA Jetson: Benchmark tests on a micro aerial vehicle. IEEE Robotics and Automation Letters. 2021. Vol. 6. N3. 5332-5339.</mixed-citation><mixed-citation xml:lang="en">Jeon J., et al. Run your visual-inertial odometry on NVIDIA Jetson: Benchmark tests on a micro aerial vehicle. IEEE Robotics and Automation Letters. 2021. Vol. 6. N3. 5332-5339 (In English).</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Hossain S., Lee D. Deep learning-based real-time multiple-object detection and tracking from aerial imagery via a flying robot with GPU-based embedded devices. Sensors. 2019. Vol. 19. N15. 3371.</mixed-citation><mixed-citation xml:lang="en">Hossain S., Lee D. Deep learning-based real-time multiple-object detection and tracking from aerial imagery via a flying robot with GPU-based embedded devices. Sensors. 2019. Vol. 19. N15. 3371 (In English).</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Carneiro T., et al. Performance analysis of google colaboratory as a tool for accelerating deep learning applications. IEEE Access. 2018. Vol. 6. 61677-61685.</mixed-citation><mixed-citation xml:lang="en">Carneiro T. et al. Performance analysis of google colaboratory as a tool for accelerating deep learning applications. IEEE Access. 2018. Vol. 6. 61677-61685 (In English).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Meyer G.E., Neto J.C. Verification of color vegetation indices for automated crop imaging applications. Computers and electronics in agriculture. 2008. Vol. 63. N2. 282-293.</mixed-citation><mixed-citation xml:lang="en">Meyer G.E., Neto J.C. Verification of color vegetation indices for automated crop imaging applications. Computers and electronics in agriculture. 2008. Vol. 63. N2. 282-293 (In English).</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Демин Е.Е. и др. Аналитические исследования технических параметров самодвижущихся опрыскивателей // Аграрный научный журнал. 2021. N12. С. 112-114.</mixed-citation><mixed-citation xml:lang="en">Demin E.E., et al. Analiticheskie issledovaniya tekhnicheskikh parametrov samodvizhushchikhsya opryskivateley [Analytical studies of technical parameters of self-propelled sprayers]. Agrarnyy nauchnyy zhurnal. 2021. N12. 112-114 (In Russian).</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Балабанов В.И. и др. Технологии, машины и оборудование для координатного (точного) земледелия. М.: Росинформагротех. 2016. 240 с.</mixed-citation><mixed-citation xml:lang="en">Balabanov V.I., et al. Tekhnologii, mashiny i oborudovanie dlya koordinatnogo (tochnogo) zemledeliya [Technologies, machines and equipment for coordinate (precision) farming]. Moscow: Rosinformagrotekh. 2016. 240 (In Russian).</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Лысов А.К., Воробьев Н.И. Вычисление с помощью математической модели траекторий движения распыляемых аэрозольных капель // АгроЭкоИнженерия. 2021. N2(107). С. 96-106.</mixed-citation><mixed-citation xml:lang="en">Lysov A.K., Vorob'ev N.I. Vychislenie s pomoshchyu matematicheskoy modeli traektoriy dvizheniya raspylyaemykh aerozol'nykh kapel' [Calculation of droplets trajectories of a sprayed aerosol with the use of mathematical model]. Agro-EkoInzheneriya. 2021. N2(107). 96-106 (In Russian).</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Бредихин А.И. Алгоритмы обучения сверточных нейронных сетей // Вестник Югорского государственного университета. 2019. N1(52). С. 41-54.</mixed-citation><mixed-citation xml:lang="en">Bredikhin A.I. Algoritmy obucheniya svertochnykh neyronnykh setey [Training algorithms for convolutional neural networks]. Vestnik Yugorskogo gosudarstvennogo universiteta. 2019. N1(52). 41-54 (In Russian).</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Henaff O. Data-efficient image recognition with contrastive predictive coding. International Conference on Machine Learning. PMLR. 2020. 4182-4192.</mixed-citation><mixed-citation xml:lang="en">Henaff O. Data-efficient image recognition with contrastive predictive coding. International Conference on Machine Learning. PMLR. 2020. 4182-4192 (In English).</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Bardou D., Zhang K., Ahmad S. M. Classification of breast cancer based on histology images using convolutional neural networks. IEEE Access. 2018. Vol. 6. 24680-24693.</mixed-citation><mixed-citation xml:lang="en">Bardou D., Zhang K., Ahmad S. M. Classification of breast cancer based on histology images using convolutional neural networks. IEEE Access. 2018. Vol. 6. 24680-24693 (In English).</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Polyzotis N., Zinkevich M., Roy S., Breck E., Whang S. Data Validation for Machine Learning. Proceedings of Machine Learning and Systems. 2019.</mixed-citation><mixed-citation xml:lang="en">Polyzotis N., Zinkevich M., Roy S., Breck E., Whang S. Data Validation for Machine Learning. Proceedings of Machine Learning and Systems. 2019 (In English).</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>
