gyroscopyГироскопия и навигацияGiroskopiya i Navigatsiya0869-70352075-0927AO «Концерн «ЦНИИ «Электроприбор»10.17285/0869-7035.0012gyroscopy-261Research ArticleСтатьиСопоставление изображений с широкой базовой линией и отслеживание траектории БПЛА при его приближении к окну зданияCombination of Wide Baseline Image Matching and Tracking for Autonomous UAV Approaches to a WindowМюллерК.MuellerK.

Мюллер Карстен. Аспирант

АтманДж.AtmanJ.

Атман Джамаль. Аспирант

ТроммерГ. Ф.TrommerG.F.

Троммер Герт Франц. Профессор. Действительный член общественного объединения «Академия навигации и управления движением».

Институт оптимизации систем Технологического института Карлсруэ.ГерманияInstitute of Systems Optimization, Karlsruhe Institute of TechnologyGermanyИнститут оптимизации систем Технологического института КарлсруэГерманияInstitute of Systems Optimization, Karlsruhe Institute of TechnologyGermanyТехнологический институт Карлсруэ (Германия), Университет ИТМО (С.-Петербург, Россия)РоссияInstitute of Systems Optimization, Karlsruhe Institute of Technology, Germany; ITMO University, Saint Petersburg, RussiaRussian Federation2019181120252745268Copyright © Мюллер К., Атман Д., Троммер Г., 20252025Мюллер К., Атман Д., Троммер Г.Mueller K., Atman J., Trommer G.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.gyroscopy.ru/jour/article/view/261

Статья посвящена вопросам приближения автономного беспилотного летательного аппарата (БПЛА) к цели, заданной по эталонному изображению. Предложен устойчивый алгоритм сопоставления для достоверного проецирования выбранной точки эталонного изображения на снимки, полученные с камеры квадрокоптера в режиме реального времени. Чтобы выделить дополнительные ключевые точки и обеспечить инвариантность внеплоскостных перспективных преобразований, осуществляются трансформации проекций эталонных изображений. Поскольку алгоритм сопоставления не использует существенные характеристики последовательностей изображений и время его обработки слишком велико для высокой частоты смены кадров, то дополнительно вводится алгоритм отслеживания. Удалось добиться высокой частоты обнаружений даже для последовательностей изображений, полученных со значительно отличающихся ракурсов. Таким образом, предложенный алгоритм можно использовать для обеспечения входных данных для алгоритма управления движением БПЛА.

In this paper, the problem of an autonomous unmanned aerial vehicle (UAV) approach to a target which is selected in a reference image is addressed. A robust matching algorithm is proposed to reliably project the selected point in the reference image into the live images of a quadrotor helicopter. Projective transformations are applied to the reference image to extract additional keypoints and to gain invariance to out-of-plane perspective transformations. Since the matching algorithm does not exploit the beneficial characteristics of image sequences and because its processing time is not short enough for high frame rates, a tracking algorithm is introduced. High detection rates even for image sequences with large viewpoint changes are achieved. Therefore, the presented algorithm can be used as input to a guidance algorithm for UAVs.

Сличение базовых линийсопоставление изображенийалгоритм ORBобнаружение окналетательные микроаппараты.Wide baseline matchingimage matchingORBtrackingwindow detectionmicro aerial vehicles.ReferencesHartley, R. and Zisserman, A., Multiple View Geometry in Computer Vision, 2nd ed., Cambridge University Press, 2003.Hartley, R. and Zisserman, A., Multiple View Geometry in Computer Vision, 2nd ed., Cambridge University Press, 2003.Lowe, D.G., Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, 2004, pp. 91–110.Lowe, D.G., Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, 2004, pp. 91–110.Bay, H., Tuytelaars, T. and van Gool, L., SURF: Speeded up robust features, Proc. 9th European Conference on Computer Vision (ECCV), Graz, Austria, May 7-13, 2006, Part I, 2006, pp. 404–417.Bay, H., Tuytelaars, T. and van Gool, L., SURF: Speeded up robust features, Proc. 9th European Conference on Computer Vision (ECCV), Graz, Austria, May 7-13, 2006, Part I, 2006, pp. 404–417.Rublee, E., Rabaud, V., Konolige, K. and Bradski, G., ORB: An efficient alternative to SIFT or SURF, Proc. 2011 International Conference on Computer Vision, 2011, pp. 2564–2571.Rublee, E., Rabaud, V., Konolige, K. and Bradski, G., ORB: An efficient alternative to SIFT or SURF, Proc. 2011 International Conference on Computer Vision, 2011, pp. 2564–2571.Ferrari, V., Tuytelaars, T. and van Gool, L., Wide-baseline multiple-view correspondences, Proc. 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003, pp. 718–725.Ferrari, V., Tuytelaars, T. and van Gool, L., Wide-baseline multiple-view correspondences, Proc. 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003, pp. 718–725.Morel, J.-M. and Yu, G., ASIFT: A new framework for fully affine invariant image comparison, SIAM Journal on Imaging Sciences, 2009, vol. 2, no. 2, pp. 438–469.Morel, J.-M. and Yu, G., ASIFT: A new framework for fully affine invariant image comparison, SIAM Journal on Imaging Sciences, 2009, vol. 2, no. 2, pp. 438–469.Lin, W.Y. et al., CODE: Coherence based decision boundaries for feature correspondence, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, vol. 40, no. 1, pp. 34–47.Lin, W.Y. et al., CODE: Coherence based decision boundaries for feature correspondence, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, vol. 40, no. 1, pp. 34–47.Codreanu, V. et al., GPU-ASIFT: A fast fully affine-invariant feature extraction algorithm, Proc. 2013 International Conference on High Performance Computing Simulation (HPCS), 2013, pp. 474–481.Codreanu, V. et al., GPU-ASIFT: A fast fully affine-invariant feature extraction algorithm, Proc. 2013 International Conference on High Performance Computing Simulation (HPCS), 2013, pp. 474–481.Fischler, M.A. and Bolles, R.C., Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography, Communications of the ACM, 1981, vol. 24, no. 6, pp. 381–395.Fischler, M.A. and Bolles, R.C., Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography, Communications of the ACM, 1981, vol. 24, no. 6, pp. 381–395.Zhang, W. and Kosecka, J., Generalized RANSAC framework for relaxed correspondence problems, Proc. Third International Symposium on 3D Data Processing, Visualization, and Transmission, 2006, pp. 854–860.Zhang, W. and Kosecka, J., Generalized RANSAC framework for relaxed correspondence problems, Proc. Third International Symposium on 3D Data Processing, Visualization, and Transmission, 2006, pp. 854–860.Bay, H., Ferraris, V. and van Gool, L., Wide-baseline stereo matching with line segments, Proc. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), 2005, pp. 329–336.Bay, H., Ferraris, V. and van Gool, L., Wide-baseline stereo matching with line segments, Proc. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), 2005, pp. 329–336.Wang, L., Neumann, U. and You, S., Wide-baseline image matching using line signatures, Proc. 2009 IEEE 12th International Conference on Computer Vision, 2009, pp. 1311–1318.Wang, L., Neumann, U. and You, S., Wide-baseline image matching using line signatures, Proc. 2009 IEEE 12th International Conference on Computer Vision, 2009, pp. 1311–1318.Goedeme, T., Tuytelaars, T. and van Gool, L., Fast wide baseline matching for visual navigation, Proc. 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004, pp. 24–29.Goedeme, T., Tuytelaars, T. and van Gool, L., Fast wide baseline matching for visual navigation, Proc. 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004, pp. 24–29.Zhai, Y., Guo, X., He, P. and Han, D., Wide-baseline matching based on line intersection features, Proc. 10th International Conference on Digital Image Processing (ICDIP 2018), Shanghai, 2018. DOI: 10.1117/12.2502982.Zhai, Y., Guo, X., He, P. and Han, D., Wide-baseline matching based on line intersection features, Proc. 10th International Conference on Digital Image Processing (ICDIP 2018), Shanghai, 2018. DOI: 10.1117/12.2502982.Lee, J.A., Yow, K.C. and Chia, A.Y.S., Robust matching of building facades under large viewpoint changes, Proc. 2009 IEEE 12th International Conference on Computer Vision, 2009, pp. 1258–1264.Lee, J.A., Yow, K.C. and Chia, A.Y.S., Robust matching of building facades under large viewpoint changes, Proc. 2009 IEEE 12th International Conference on Computer Vision, 2009, pp. 1258–1264.Mueller, K., Kleis, R. and Trommer, G.F., Wide baseline matching for autonomous approaches of MAVs, Proc. 2018 IEEE/ION Position, Location and Navigation Symposium (PLANS), Monterey, CA, USA, 2018, pp. 801–808.Mueller, K., Kleis, R. and Trommer, G.F., Wide baseline matching for autonomous approaches of MAVs, Proc. 2018 IEEE/ION Position, Location and Navigation Symposium (PLANS), Monterey, CA, USA, 2018, pp. 801–808.Li, X. and Wang, J., Image matching techniques for vision-based indoor navigation systems: performance analysis for 3D map based approach, Proc. 2012 International Conference on Indoor Positioning and Indoor Navigation (IPIN), 2012, pp. 1–8.Li, X. and Wang, J., Image matching techniques for vision-based indoor navigation systems: performance analysis for 3D map based approach, Proc. 2012 International Conference on Indoor Positioning and Indoor Navigation (IPIN), 2012, pp. 1–8.Smith, J.R. and Chang, S.-F., Single color extraction and image query, Proc. International Conference on Image Processing, 1995, pp. 528–531.Smith, J.R. and Chang, S.-F., Single color extraction and image query, Proc. International Conference on Image Processing, 1995, pp. 528–531.Niblack, W. et al., The QBIC Project: Querying Images by Content Using Color, Texture, and Shape, IBM Research Division, 1993.Niblack, W. et al., The QBIC Project: Querying Images by Content Using Color, Texture, and Shape, IBM Research Division, 1993.Bouguet, J.-Y., Pyramidal Implementation of the Affine Lucas Kanade Feature Tracker: Description of the Algorithm, Intel Corporation, 2001.Bouguet, J.-Y., Pyramidal Implementation of the Affine Lucas Kanade Feature Tracker: Description of the Algorithm, Intel Corporation, 2001.

The authors declare that there are no conflicts of interest present.