Structure from Motion (SFM) – Uma Breve Revisão Histórica, Aplicações nas Geociências e Perspectivas Futuras
DOI:
https://doi.org/10.11137/1982-3908_2021_44_40853Keywords:
Visão computacional, Fotogrametria, VANTAbstract
O presente artigo de revisão narra a trajetória de um dos algoritmos mais utilizados na fotogrametria com Veículo Aéreo não Tripulado (VANT), que a partir da visão computacional, tem se destacado como solução de baixo custo para obtenção de informações da superfície terrestre. Apesar de sua concepção ter sido formulada em meados da década de 1950 e com propósitos distantes das geociências, foi a partir dos avanços da indústria da computação e robótica, no início da década de 1980, que o Structure from Motion (SfM) absorveu significativas melhorias para consagrá-lo como um importante recurso de modelagem tridimensional. No entanto, somente na última década (2010), observou-se um exponencial crescimento nas aplicações e análises do SfM nas geociências, principalmente a partir da popularização dos VANTs. Com isso, vieram à tona suas principais aplicações e limitações – neste estudo também serão abordadas suas características, principalmente as que diferem de técnicas já consagradas como o LiDAR, e perspectivas futuras dessa tecnologia.
References
Agarwal, S., Snavely, N., Seitz, S.M., Szeliski, R. 2010, 'Bundle Adjustment in the Large', Computer Vision, vol. 6312, pp. 29-42.
Agisoft Metashape 2020, User Manual Professional Edition, Version 1.6, acesso em 25 Jan 2021, <https://www.agisoft.com/pdf/metashape-pro_1_6_en.pdf>
Campos, M., Tommaselli, A., Ivánová, I. & Billen, R. 2015, 'Data Product Specification Proposal for Architectural Heritage Documentation with Photogrammetric Techniques: A Case Study in Brazil'. Remote Sensing, vol. 7, no. 10, pp. 13337-63. http://dx.doi.org/10.3390/rs71013337
Campoy, P., Correa, J.F., Mondragón, I., Martinez, C., Olivares, M., Mejias, L., Artieda J. 2008, 'Computer Vision Onboard UAVs for Civilian Tasks', International Symposium on Unmanned Aerial Vehicles, pp. 105-35. https://core.ac.uk/download/pdf/148653348.pdf
Fischler, M.A., Bolles, R.C. 1981, 'Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography', Communications of the ACM, vol. 24, pp. 381-95. https://doi.org/10.1145/358669.358692
Galland, O., Bertelen, H. S., Guldstrand, F., Girod, L. 2016, 'Application of open-source photogrammetric software MicMac for monitoring surface deformation in laboratory models', Journal of Geophysical Research: Solid Earth, vol. 121, no. 4, pp. 2852-72. https://doi.org/10.1002/2015JB012564
Graça, N., Mitishita, E., Gonçalves, J. 2014, 'Photogrammetric Mapping Using Unmanned Aerial Vehicle', The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XL-1, pp. 129-33. https://doi.org/10.5194/isprsarchives-XL-1-129-2014
Graham, L. 2018, Drone Mapping – SfM versus Low Precision LIDAR, acesso em 10 Dezembro 2020, <https://support.geocue.com/drone-mapping-sfm-versus-low-precision-lidar/>.
Grahame, J. 2008, Star Wars: Prehistoric Computer Graphics, acesso em 10 Dezembro 2020, <https://www.retrothing.com/2008/04/star-wars-prehi.html>.
Harris, C. & Stephens, M. 1988, 'A Combined Corner and Edge Detector', Proceedings of The 4th Alvey Vision Conference, pp. 147-51. http://www.bmva.org/bmvc/1988/avc-88-023.pdf
Hughes, J. F., Dan, A, Mcguire, M., Sklar, D. F., Foley, J. D., Feiner, S. K., Akeley, K. J. F. 2013, Computer graphics: Principles and practice. Addison-Wesley, USA.
Ilci, V., Toth, C. 2020, 'High-Definition 3D Map Creation Using GNSS/IMU/LIDAR Sensor Integration to Support Autonomous Vehicle Navigation', Sensors, vol. 20, no. 3, p. 899. https://doi.org/10.3390/s20030899
James, M. R., Robson, S. 2012, 'Straightforward reconstruction of 3D surfaces and topography with a camera: Accuracy and geoscience application', Journal of Geophysical Research: Earth Surface, vol. 117, no. F3. https://doi.org/10.1029/2011JF002289
Jebara, T., Azarbayejani, A., Pentland, A. 1999, '3D structure from 2D motion', IEEE Signal Processing Magazine, vol. 16, no. 3, pp. 66-84. https://doi.org/10.1109/79.768574
Jubanski, J. J. 2005, ‘Desenvolvimento e avaliação de um sistema de vôo apoiado por GPS para aerotriangulação por feixes de raios’, Dissertação de Mestrado. Universidade Federal do Paraná. http://educapes.capes.gov.br/handle/1884/3874
Kumar, A., Karthika, R., Soman, K. P. 2020, 'Stereo Camera and LIDAR Sensor Fusion-Based Collision Warning System for Autonomous Vehicles', Advances in Computational Intelligence Techniques pp. 239-52. http://dx.doi.org/10.1007/978-981-15-2620-6_17
Lowe, D.G. 2004, 'Distinctive Image Features from Scale-Invariant Keypoints', International Journal of Computer Vision, vol. 60, pp. 91-110. https://www.cs.ubc.ca/~lowe/papers/ijcv04.pdf
Lucas, B. D., Kanade, T. 1981, 'An Iterative Image Registration Technique with an Application to Stereo Vision', International Joint Conference on Artificial Intelligence, pp. 121-30.
Martín, S., Uzkeda, H., Poblet, J., Bulnes, M., Rubio, R. 2013, 'Construction of accurate geological cross-sections along trenches, cliffs and mountain slopes using photogrammetry', Computers & Geosciences, vol. 51, pp. 90-100. https://doi.org/10.1016/j.cageo.2012.09.014
Moravec, H. 1981, 'Rover Visual Obstacle Avoidance', Proceedings of the 7th international joint conference on Artificial intelligence, vol. 2, pp. 785-90. https://dl.acm.org/doi/10.5555/1623264.1623304
Nakano, T., Iwahashi, J., Kamiya, I., Nakajima, H., Tobita, M. 2014, 'Landform monitoring in active volcano by UAV and SFM-MVS technique', ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XL-8, pp. 71-5. http://dx.doi.org/10.5194/isprsarchives-XL-8-71-2014
Prosdocimi, M., Calligaro, S., Sofia, G., Fontana, G., Tarolli, P. 2015, 'Bank erosion in agricultural drainage networks: new challenges from structure‐from‐motion photogrammetry for post‐event analysis', Earth Surface Processes and Landforms, vol. 40, no. 14, pp. 1891-906. https://doi.org/10.1002/esp.3767
Scopus 2021, Pesquisa com as palavras-chave: Fotogrametria e SfM. Acessada em Maio de 2021, <https://www.scopus.com/term/analyzer.uri?sid=ef146539d71adfced54efd8f62a6dc7e&origin=resultslist&src=s&s=TITLE-ABS-KEY+%28SFM%2c+photogrammetry%29&sort=plf-f&sdt=b&sot=b&sl=35&count=946&analyzeResults=Analyze+results&txGid=72c6b7bc10c617ea8eef955486c8234a>
Shervais, K. 2016, Structure from Motion (SfM) Photogrammetry Field Methods Manual for Students acessado em 23 Setembro 2020, <https://d32ogoqmya1dw8.cloudfront.net/files/getsi/teaching_materials/high-rez-topo/sfm_field_methods_manual.v3.pdf>
Silveira, M. T., Feitosa, R. Q., Brito, J., Jacobsen, K. 2011, 'Correspondência eficiente de descritores SIFT para construção de mapas densos de pontos homólogos em imagens de sensoriamento remoto', Boletim de Ciências Geodésicas, vol. 17, no. 1, pp. 130-60. https://revistas.ufpr.br/bcg/article/view/21162
Snavaley, N. 2008, 'Scene Reconstruction and Visualization from Internet Photo Collections: A Survey', Tese de Doutorado, University of Washington. https://www.cs.cornell.edu/~snavely/publications/thesis/thesis.pdf
Tang, L., Shi, Y., He, Q., Sadek, A., Qiao, C. 2020, 'Performance Test of Autonomous Vehicle Lidar Sensors Under Different Weather Conditions', Journal of the Transportation Research Board, vol. 2674, no. 1. https://doi.org/10.1177%2F0361198120901681
Ullman, S. 1979, 'The Interpretation of Structure from Motion', Proceedings of the Royal Society of London, vol. 203, no. 1153, p. 405. http://www.jstor.org/stable/77505
Verhoeven, G., Doneus, M., Briese, C., Vermeulen, F. 2012, 'Mapping by matching: a computer vision-based approach to fast and accurate georeferencing of archaeological aerial photographs', Journal of Archaeological Science, vol. 39, no. 7, pp. 2060-70. https://doi.org/10.1016/j.jas.2012.02.022
Wagenamns, J. 2015, The Oxford Handbook of Perceptual Organization, Oxford University Press, UK.
Wallach, H., O'connell, D. N., Neisser, U. 1953, 'The memory effect of visual perception of three-dimensional form', Journal of Experimental Psychology, vol. 45, no. 5, pp. 360-68. https://doi.org/10.1037/h0063368
Westoby, M. J., Brasington, J., Glasser, N. F., Hambrey, M. J., Reynoldsj, M. 2012, 'Structure-from-Motion photogrammetry: A low-cost, effective tool for geoscience applications', Geomorphology, vol. 179, no. 15, pp. 300-14. https://doi.org/10.1016/j.geomorph.2012.08.021
Yoshimura, R., Date, H., Kanai, S., Honma, R., Oda, K., Ikeda, T. 2016, 'Automatic registration of MLS point clouds and SfM meshes of urban area', Geo-spatial Information Science, vol. 19, no. 3, pp. 171-81. https://doi.org/10.1080/10095020.2016.1212517
Downloads
Published
Issue
Section
License
Copyright (c) 2021 Anuário do Instituto de Geociências
This work is licensed under a Creative Commons Attribution 4.0 International License.
This journal is licensed under a Creative Commons — Attribution 4.0 International — CC BY 4.0, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
Except where otherwise noted, content on this site is licensed under a license 