Current Science

Open Access Open Access  Restricted Access Subscription Access

Towards Generation of Effective 3D Surface Models from UAV Imagery Using Open Source Tools


Affiliations
1 North Eastern Space Applications Centre, Department of Space, Government of India, Umiam 793 103, India
2 Department of Computer Science, Assam Don Bosco University, Guwahati 781 017, India
 

There has been increasing popularity in large scale mapping for deriving 3D surface and elevation models of earth and building structures. The techniques of computer vision comprising feature detections and matching and photogrammetry play an important role in deriving near accurate 3D reconstruction of scenes from 2D images. Since the images captured by the unmanned aerial vehicle (UAVs) are of high resolution, there is need for more sophisticated processing and analysis of the imagery to generate 3D models and other useful imagery products. The open source softwares are excellent tools for research and can be modified or changed to suit our model, as specific or combinations of algorithms behave differently based on the nature of UAV image scene to be processed. Though many algorithms are available for performing feature extractions from images, few studies have been carried out to identify suitable detector algorithms to be used based on the nature of image or scene that the UAV captures. An attempt has been made to understand and analyse the suitability of feature detection and descriptor algorithms for different scene types. This article also describes the popular technique called structure from motion process pipeline for sequential processing of UAV images with high overlapping, which involves the estimation of 3D point clouds from the keypoint correspondences. The relative accuracy of the 3D point cloud derived from our approach is comparable with similar output from other state-of-the-art UAV processing systems and is found to match with high precision.

Keywords

3D Reconstruction, Open Source, Point Clouds, Remote Sensing, Structure from Motion, Unmanned Aerial Vehicle.
User
Notifications
Font Size

  • Bhandari, B., Oli, U., Panta, N. and Pudasaini, U., Generation of High Resolution DSM Using UAV Images, FIG Working Week Sofia, Bulgaria, 17–21 May 2015.

  • Alshawabkeh, Y., Haala, N. and Fritsch, D., 2d–3d feature extraction and registration of real world scenes, isprs Commission V Symposium Image Engineering and Vision Metrology, IAPRS Volume XXXVI, Part 5, Dresden 25–27 September 2006.

  • Changchang, W., Towards Linear-time Incremental Structure from Motion, 2013 International Conference on 3D Vision.

  • Hassaballah, M. et al., Image feature detectors and descriptors. Studies in Computational Intelligence 630, Springer International Publishing, Switzerland, 2016.

  • Mikolajczyk, K. et al., A comparison of affine region detectors. Int. J. Comput. Vision, 2006; doi:10.1007/s11263-005-3848-x.

  • Lowe, D. G., Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis., 2004. 60(2), 91–110.

  • Mancini, F. et al., Using unmanned aerial vehicles (UAV) for high-resolution reconstruction of topography: the structure from motion approach on coastal environments. Remote Sensing, 2013, 5, 6880–6898; doi:10.3390/rs5126880.

  • Mark, A. et al., Topographic structure from motion: a new development in photogrammetric measurement. Earth Surf. Proc. Landforms, 2013, 38(4), 421–430.

  • Westoby, M. J. et al., Structure-from motion’ photogrammetry: a low-cost, effective tool forgeoscience applications. Geomorphology, 2012, 179, 300–314.

  • Mike, R. James and Robson, S., Straightforward reconstruction of 3D surfaces and topography with a camera: Accuracy and geoscience application. J. Geophys. Res., 2012, 117, F03017.

  • Furukawa, Y. and Hernández. C., Multi-view stereo: a tutorial. Found. Trends in Comput. Graph. Vision, 2013, 9(1–2), 1–148; doi:10.1561/0600000052.

  • Hassaballah, M. et al., Image Features Detection, Description and Matching, Volume 630 of the series Studies in Computational Intelligence, pp. 11–45.

  • Mikolajczyk, K. and Schmid, C., A performance evaluation of local descriptors. CVPR, 2003.

  • Snavely, A., Seitz, S. and Szeliski, Building Rome in a day. International Conference on Computer Vision, 2009.

  • Furukawa, Y. et al., Towards Internet-scale Multi-view Stereo, CVPR, 2010.

  • Furukawa, Y. and Ponce, J., Accurate, dense and robust multiview stereopsis. IEEE Trans. Pattern Anal. Mach. Intell., 2010, 32(8), 1362–1376.

  • OpenSFM, https://github.com/mapillary/OpenSfM.

  • Shao, Z., A multi-view dense point cloud generation algorithm based on low-altitude remote sensing images. Remote Sensing, MDPI, 2016, 8, 381; doi:10.3390/rs8050381.

  • Habbecke, M. and Kobbelt, L., Iterative multi-view plane fitting. Proceedings of the 11th Fall Workshop Vision, Modeling, and Visualization, 2006.

  • Kushal, A. and Ponce, J., A novel approach to modeling 3D objects from stereo views and recognizing them in photographs. Proceedings of the European Conference Computer Vision, 2006, vol. 2, pp. 563–574.

  • Maiellaro, N., Zonno, M. and Lavalle, P., Laser scanner and cameraequipped uav architectural surveys, Int. Arch. Photogramm. Remote Sensing Spatial Inf. Sci., 2015, XL-5/W4, 381–386.

  • Seitz, S. M., Curless, B., Diebel, J., Scharstein, D. and Szeliski, R., A comparison and evaluation of multi-view stereo reconstruction algorithms. CVPR, 1, 2006.

  • Kazhdan, M., Bolitho, M. and Hoppe, H., Poisson Surface Reconstruction, Eurographics Symposium on Geometry Processing, 2006.

  • Waechter, M., Moehrle, N. and Goesele, M., Let there be Color! Large-scale texturing of 3D Reconstructions, European Conference on Computer Vision (ECCV 2014), Zurich, Switzerland, 6–12 September 2014.

  • TexRecon – 3D Reconstruction Texturing. http://www.gcc.tudarmstadt.de/home/proj/texrecon/

  • Waechter, M., Moehrle, N. and Goesele, M., Let There Be Color! Large-Scale Texturing of 3D Reconstructions, Volume 8693 of the series Lecture Notes in Computer Science, Computer Vision – ECCV 2014, 2014, pp. 836–850.

  • Jancosek, M. and Pajdla, T., Multi-View Reconstruction Preserving Weakly-Supported Surfaces, CVPR 2011 – IEEE Conference on Computer Vision and Pattern Recognition, 2011.


Abstract Views: 469

PDF Views: 129




  • Towards Generation of Effective 3D Surface Models from UAV Imagery Using Open Source Tools

Abstract Views: 469  |  PDF Views: 129

Authors

P. S. Singh
North Eastern Space Applications Centre, Department of Space, Government of India, Umiam 793 103, India
Mayuri Sharma
Department of Computer Science, Assam Don Bosco University, Guwahati 781 017, India
Victor Saikhom
North Eastern Space Applications Centre, Department of Space, Government of India, Umiam 793 103, India
Dibyajyoti Chutia
North Eastern Space Applications Centre, Department of Space, Government of India, Umiam 793 103, India
Chirag Gupta
North Eastern Space Applications Centre, Department of Space, Government of India, Umiam 793 103, India
Avinash Chouhan
North Eastern Space Applications Centre, Department of Space, Government of India, Umiam 793 103, India
P. L. N. Raju
North Eastern Space Applications Centre, Department of Space, Government of India, Umiam 793 103, India

Abstract


There has been increasing popularity in large scale mapping for deriving 3D surface and elevation models of earth and building structures. The techniques of computer vision comprising feature detections and matching and photogrammetry play an important role in deriving near accurate 3D reconstruction of scenes from 2D images. Since the images captured by the unmanned aerial vehicle (UAVs) are of high resolution, there is need for more sophisticated processing and analysis of the imagery to generate 3D models and other useful imagery products. The open source softwares are excellent tools for research and can be modified or changed to suit our model, as specific or combinations of algorithms behave differently based on the nature of UAV image scene to be processed. Though many algorithms are available for performing feature extractions from images, few studies have been carried out to identify suitable detector algorithms to be used based on the nature of image or scene that the UAV captures. An attempt has been made to understand and analyse the suitability of feature detection and descriptor algorithms for different scene types. This article also describes the popular technique called structure from motion process pipeline for sequential processing of UAV images with high overlapping, which involves the estimation of 3D point clouds from the keypoint correspondences. The relative accuracy of the 3D point cloud derived from our approach is comparable with similar output from other state-of-the-art UAV processing systems and is found to match with high precision.

Keywords


3D Reconstruction, Open Source, Point Clouds, Remote Sensing, Structure from Motion, Unmanned Aerial Vehicle.

References





DOI: https://doi.org/10.18520/cs%2Fv114%2Fi02%2F314-321