Buscar en
Revista Iberoamericana de Automática e Informática Industrial RIAI
Toda la web
Inicio Revista Iberoamericana de Automática e Informática Industrial RIAI Construcción automática de ortofotomapas: una aproximación fotométrica
Información de la revista
Vol. 10. Núm. 1.
Páginas 104-115 (Enero - Marzo 2013)
Compartir
Compartir
Descargar PDF
Más opciones de artículo
Visitas
4835
Vol. 10. Núm. 1.
Páginas 104-115 (Enero - Marzo 2013)
Artículo
Open Access
Construcción automática de ortofotomapas: una aproximación fotométrica
Automatic construction of ortophotomaps: a photometric approach
Visitas
4835
R. Pradosa,
Autor para correspondencia
rprados@eia.udg.edu

Autor para correspondencia.
, R. Garcíaa, L. Neumannb
a Computer Vision and Robotics Group, University of Girona, 17071 Spain
b Computer Vision and Robotics Group, University of Girona, 17071 Spain, ICREA, Barcelona, 08010 Spain
Este artículo ha recibido

Under a Creative Commons license
Información del artículo
Resumen
Texto completo
Bibliografía
Descargar PDF
Estadísticas
Resumen

La construcción de mosaicos de imágenes permite obtener representaciones de grandes dimensiones y resolución de una misma escena. Son frecuentes hoy día las cámaras fotográficas que incorporan un software destinado a su construcción o aplicaciones en línea como Google Maps que permiten visualizar mapas resultantes de la construcción de foto-mosaicos. Habitualmente los mosaicos panorámicos son generados a partir de imágenes adquiridas mediante una cámara que únicamente efectúa movimientos de rotación alrededor de un punto fijo. Cuando las condiciones de adquisición varían y la cámara también se traslada, surgen fenómenos, como el de paralaje, que dificultan la unión no perceptible de las imágenes. A ello hay que añadir las diferencias en apariencia que varias fotografías adyacentes pueden presentar debido a mecanismos automáticos de las cámaras, como el de control de exposición. En el presente trabajo se describe un procedimiento completo para la construcción automática de mosaicos con apariencia totalmente continua y consistente, en los que las uniones de las distintas imágenes que lo conforman no son visibles. Las imágenes son registradas mediante métodos que garantizan consistencia geométrica, y unidas utilizando técnicas de fusión (o blending), con el objetivo de asegurar una transición no visible entre imágenes y una apariencia global coherente en todo el mosaico. El procedimiento descrito es aplicado sobre una secuencia con el fin de evaluar su utilización en el contexto de las imágenes aéreas de grandes dimensiones.

Palabras clave:
Procesamiento de imagen
realzado de imagen
emparejamiento de imágenes
registro de imágenes
métodos de gradiente
Abstract

Mosaicing allows to obtain a high-resolution representation of a given scene. Off-the-shelf still cameras including built-in software to build photo-mosaics and online applications such as Google Maps allowing to visualize maps resulting from a photomosaic are common nowadays. In most cases panoramic mosaics are generated from images acquired by means of a camera undergoing uniquely a rotation movement. When the acquisition conditions change, and the camera also performs a translation movement, the parallax phenomenon appears. If parallax exists, the seamless combination of the images is even more challenging. Additionally, adjacent photographs may present differences in appearance due to some automatic camera mechanisms, such as the automatic exposure. In this work a full processing pipeline intended to automatically build seamless mosaics with continuous and consistent appearance is described. Images are joined using methods which guarantee geometrical consistency, and fused using blending techniques, to achieve a non-visible transition between images. The described pipeline is applied on a high-resolution image sequence in order to evaluate its application in the context of aerial images of large dimensions.

Keywords:
Image processing
image enhancement
image matching
image registration
gradient methods
Referencias
[Agarwala et al., 2004]
Agarwala, A., Dontcheva, M., Agrawala, M., Drucker, S., Colburn, A., Curless, B., Salesin, D., Cohen, M., August 2004. Interactive digital photomontage. In: Proc. SIGGRAPH04.
[Arévalo and Gonzalez, 2008]
V. Arévalo, J. Gonzalez.
An Experimental Evaluation of Non-Rigid Registration Techniques on QuickBird Satellite Imagery.
International Journal of Remote Sensing, 29 (2008), pp. 513-527
[Bay et al., 2006]
Bay, H., Tuytelaars, T., Van Gool, L.J., 2006. SURF: Speeded Up Robust Features. In: European Conference on Computer Vision. pp. 404-417.
[Bertalmio et al., 2000]
Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C., July 2000. Image inpainting. In: Proceedings of SIGGRAPH. New Orleans, USA. pp. 417-424.
[Botterill et al., 2009]
Botterill, T., Mills, S., Green, R., 2009. New conditional sampling strategies for speeded-up RANSAC. In:;1; BMVC.
[Botterill et al., 2010]
Botterill, T., Mills, S., Green, R., November 2010. Real-time Aerial Image Mosaicing. In: Proceedings of Image and Vision Computing New Zealand. Queenstown, NZ, pp. 1-6.
[Burt and Adelson, 1983]
P. Burt, E. Adelson.
A multiresolution spline with application to image mosaics.
ACM Trans. Graph., 2 (1983), pp. 217-236
[Dibos and Koepfler, 1999]
F. Dibos, G. Koepfler.
Global total variation minimization.
SIAM J. Numer. Anal., 37 (1999), pp. 646-664
[Dijkstra, 1959]
E.W. Dijkstra.
A note on two problems in connexion with graphs.
Numerische Mathematik, 1 (1959), pp. 269-271
[Ding et al., 2008]
Ding, M., Lyngbaek, K., Zakhor, A., June 2008. Automatic registration of aerial imagery with untextured 3d lidar models. In: Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on. pp. 1-8.
[Elibol et al., 2008]
Elibol, A., Garcia, R., Delaunoy, O., Gracias, N., 2008. A new global alignment method for feature based image mosaicing. In: ISVC ‘08: Proceedings of the 4th International Symposium on Advances in Visual Computing, Part II. Springer-Verlag, Berlin, Heidelberg, pp. 257-266.
[Elibol et al., 2010]
Elibol, A., Gracias, N., Garcia, R., Sep. 2010. Augmented state-extended kalman filter combined framework for topology estimation in large-area underwater mapping. J. Field Robot. 27 (5), 656-674. URL: URL: http://dx.doi.org/10.1002/rob.v27:5 DOI: 10.1002/rob.v27:5.
[Escartín et al., 2008]
Escartín, J., García, R., Delaunoy, O., Ferrer, J., Gracias, N., Elibol, A., Cufi, X., Neumann, L., Fornari, D.J., Humphris, S.E., Renard, J., December 2008. Globally aligned photomosaic of the lucky strike hydrothermal vent field (mid-atlantic ridge, 37deg18.5’n): Release of georeferenced data, mosaic construction, and viewing software. Geochemistry, Geophysics, Geosystems 9, Q12009.
[Fattal et al., 2002]
R. Fattal, D. Lischinski, M. Werman.
Gradient domain high dynamic range compression.
ACM Trans. Graph., 21 (2002), pp. 249-256
[Faugeras et al., 1992]
Faugeras, O., Luong, Q.-T., Maybank, S., May 1992. Camera self calibration: theory and experiments. In: Proc. of the 2nd. European Conference on Computer Vision. Santa Margherita, Italy.
[Ferrer et al., 2007]
Ferrer, J., Elibol, A., Delaunoy, O., Gracias, N., Garcia, R., 2007. Large-area photo-mosaics using global alignment and navigation data. In: MTS/IEEE OCEANS.
[Fischler and Bolles, 1981]
M. Fischler, R. Bolles.
Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography.
Communications of the ACM, 6 (1981), pp. 381-395
[Girosi et al., 1989]
Girosi, F., Verri, A., Torre, V., 1989. Constraints for the computation of optical flow. In: Proc. of the IEEE Workshop on Visual Motion. pp. 116-124.
[González et al., 2001]
González, J., Ambrosio, G., Arévalo, V., Nov. 2001. Automatic Urban Change Detection from the IRS-1D PAN. In: IEEE-ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas. Rome, Italy, pp. 320-323.
[Harris and Stephens, 1988]
Harris, C., Stephens, M., August 1988. A combined corner and edge detector. In: Proceedings Alvey Conference. Manchester, UK, pp. 189-192.
[Hartley and Zisserman, 2003]
Hartley, R., Zisserman, A., 2003. Multiple view geometry in computer vision, 2nd edition. Cambridge University Press.
[Horn and Shunck, 1981]
B. Horn, B. Shunck.
Determining optical flow.
Artificial Intelligence, 17 (1981), pp. 185-203
[Kanatani and Ohta, 1999]
Kanatani, K., Ohta, N., September 1999. Accuracy bounds and optimal computation of homography for image mosaicing applications. In: Proc. of the Seventh International Conference on Computer Vision. Vol. 1. IEEE, pp. 73-78.
[Kazhdan and Hoppe, 2008]
M. Kazhdan, H. Hoppe.
Streaming multigrid for gradient-domain operations on large images.
ACM Trans. Graph., 27 (2008), pp. 1-10
[Kumar et al., 1995]
Kumar, R., Anandan, P., Irani, M., Bergen, J., Hanna, K., June 1995. Representation of scenes from collections of images. In: Proc. of the IEEE Computer Society Workshop on Visual Scenes Representation. Cambridge, MA.
[Kumar et al., 1998]
Kumar, R., Sawhney, H., Asmuth, J., Pope, A., Hsu, S., August 1998. Registration of video to geo-referenced imagery. In: Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on. Vol. 2. pp. 1393-1400 vol.2.
[Lear, 1997]
A. Lear.
Digital orthophotography: mapping with pictures.
Computer Graphics and Applications, IEEE, 17 (1997), pp. 12-14
[Levin et al., 2004]
Levin, A., Zomet, A., Peleg, S.,Weiss, Y., May 2004. Seamless image stitching in the gradient domain. In: Proc. of the European Conference on Computer Vision (ECCV04). Prague, Czech Republic.
[Lindeberg, 1993]
Lindeberg, T., 1993. Detecting salient blob-like image structures and their sca scales with a scale-space primal sketch: A method for focus-of-attention. International Journal of Computer Vision 11, 283-318, 10.1007/BF01469346.
[Lowe, 2004]
D. Lowe.
Distinctive image features from scale-invariant keypoints.
Int. J. Comput. Vision, 60 (2004), pp. 91-110
[Lowe, 1999]
Lowe, D.G., 1999. Object recognition from local scale-invariant features. In: ICCV ‘99: Proceedings of the International Conference on Computer Vision-Volume 2. IEEE Computer Society, Washington, DC, USA, p. 1150.
[Milgram, 1975]
D. Milgram.
Computer methods for creating photomosaics.
IEEE Transactions on Computers, 24 (1975), pp. 1113-1119
[Milgram, 1977]
Milgram, D., November 1977. Adaptive techniques for photomosaicking. IEEE Transactions on Computers C-26 (11), 1175-1180.
[Mills and Dudek, 2009]
A. Mills, G. Dudek.
Image stitching with dynamic elements.
Image and Vision Computing, 27 (2009), pp. 1593-1602
[Morse et al., 2010]
Morse, B. S., Engh, C. H., Goodrich, M. A., 2010. Uav video coverage quality maps and prioritized indexing for wilderness search and rescue. In: Proceeding of the 5th ACM/IEEE international conference on Human-robot interaction. HRI ‘10. ACM, New York, NY, USA, pp. 227-234.
[Naydenova and Jelev, 2009]
Naydenova, V., Jelev, G., June 2009. Forest dynamics study using aerial photos and satellite images with very high spatial resolution. In: Recent Advances in Space Technologies, 2009. RAST ‘09. 4th International Conference on. pp. 344-348.
[Neumann et al., 1998]
L. Neumann, K. Matkovic, W. Purgathofer.
Automatic exposure in computer graphics based on the minimum information loss principle.
Computer Graphics International Conference, 0 (1998), pp. 666-667
[Nicosevici and Garcia, 2009]
Nicosevici, T., Garcia, R., October 2009. On-line visual vocabularies for robot navigation and mapping. In: Intelligent Robots and Systems, 2009. IROS 2009. IEEE/RSJ International Conference on. pp. 205-212.
[Nicosevici et al., 2009]
T. Nicosevici, N. Gracias, S. Negahdaripour, R. Garcia.
E_cient threedimensional scene modeling and mosaicing.
J. Field Robot., 26 (2009), pp. 759-788
[Osher and Rudin, 1990]
S. Osher, L. Rudin.
Feature-oriented image enhancement using shock filters.
SIAM J. Numer. Anal., 27 (1990), pp. 919-940
[Peleg, 1981]
Peleg, S., 1981. Elimination of seams from photomosaics. In: Pattern Recognition and Image Processing. Vol. 16. pp. 90-94.
[Pérez et al., 2003]
P. Pérez, M. Gangnet, A. Blake.
Poisson image editing.
ACM Transactions on Graphics (SIGGRAPH’03), 22 (2003), pp. 313-318
[Reinhard et al., 2001]
E. Reinhard, M. Adhikhmin, B. Gooch, P. Shirley.
Color transfer between images.
Computer Graphics and Applications, IEEE, 21 (2001), pp. 34-41
[Solberg et al., 1996]
Solberg, R., Solberg, A., Koren, H., Aas, K., May 1996. The suitability of future high-resolution satellite imagery for forest inventory. In: Geoscience and Remote Sensing Symposium, 1996. IGARSS ‘96. ‘Remote Sensing for a Sustainable Future.’, International. Vol. 4. pp. 2307-2309 vol.4.
[Tegolo and Valenti, 2001]
D. Tegolo, C. Valenti.
A naive approach to compose aerial images in a mosaic fashion.
Image Analysis and Processing, International Conference on, 0 (2001), pp. 0512
[Tsai, 1986]
Tsai, R., 1986. An e_cient and accurate camera calibration technique for 3D machine vision. In: IEEE International Conference on Computer Vision and Pattern Recognition CVPR86. Miami Beach, Florida.
[Wehn et al., 2002]
Wehn, H., Goldstein, N., Ameri, B., Moshkovitz, A., Zwick, H., june 2002. Frequent-image-frames enhanced digital ortho-rectified mapping (fifedom) airborne mapping system. In: Geoscience and Remote Sensing Symposium, 2002. IGARSS ‘02. 2002 IEEE International. Vol. 2. pp. 1296-1298 vol.2.
[Wen and Zhou, 2008]
Wen, H., Zhou, J., dec. 2008. An improved algorithm for image mosaic. In: Information Science and Engineering, 2008. ISISE ‘08. International Symposium on. Vol. 1. pp. 497-500.
[Zebedin et al., 2006]
Zebedin, L., Klaus, A., Gruber-Geymayer, B., Karner, K., 2006. Towards 3d map generation from digital aerial images. ISPRS Journal of Photogrammetry and Remote Sensing 60 (6), 413-427, digital Aerial Cameras.
[Zhao, 2006]
W. Zhao.
Flexible image blending for image mosaicing with reduced artifacts.
International Journal of Pattern Recognition and Artificial Intelligence, 20 (2006), pp. 609-628
[Zhu and Yang, 2000]
Zhu, S., Yang, X., 2000. The seamline removing in the generation of orthophoto maps. In: International Archives of Photogrammetry and Remote Sensing. Vol. 33. International Society for Photogrammetry and Remote Sensing, Amsterdam, The Netherlands, pp. 1247-1251.
[Zitová and Flusser, 2003]
B. Zitová, J. Flusser.
Image Registration Methods: A Survey.
Image and Vision Computing, 21 (2003), pp. 977-1000
Copyright © 2011. CEA
Opciones de artículo
Herramientas