Robust aerial image mosaicing algorithm based on fuzzy outliers rejection

  • Abdelhai LatiEmail author
  • Mahmoud Belhocine
  • Noura Achour
Original Paper


The use of unmanned aerial vehicles (UAVs) imagery for acquiring data is constantly evolving, due to the ease of use and low data acquisition costs. All of these made UAVs very popular with end customers and data acquisition companies. For most cases, the acquired UAV images need further more processing before being analyzed, and that because of changing of illumination condition in aerial environment and fog generated because of UAV flying speed. Image mosaicing is a practical solution for these problems; in which overlapped views of the same scene are combined to form a large image with high quality. The common problem associated with image mosaicing algorithms is the false associations (outliers) produced when defining the overlapping region between every two successive views. This article presents an image mosaicing algorithm based on efficient fuzzy technique for outliers rejection. Our proposed technique is based on using RANdom SAmpling Consensus (RANSAC) and bidirectional approaches with a fuzzy inference system in order to separate between inliers and outliers. The experimental results prove that the proposed method has good performance for aerial images and gives better results when compared with other techniques. Thus our approach is insensitive to the ordering, orientation, scale and illumination of the images.


UAV images Bidirectional condition RANSAC Fuzzy outliers rejection 



  1. AerialRobotics Dataset. Accessed 30 Mar 2014Google Scholar
  2. Ait-Aoudia S, Mahiou R, Djebli H, Guerrout E (2012) Satellite and aerial image mosaicing—a comparative insight. In: 16th International. Conference on Information Visualisation, Montpellier, FranceGoogle Scholar
  3. Beckouche S, Leprince S, Sabater N, Ayoub F (2011) Robust outliers detection in image point matching. In: Computer Vision Workshops (ICCV Workshops), IEEE International Conference on IEEE, pp 180–187Google Scholar
  4. Bhushan R, Sunkaria RK (2014) A novel technique of image mosaicing based on discrete wavelet transform and its performance evaluation. Int J Comput Appl 98:15Google Scholar
  5. Bu S, Zhao Y, Wan G, Liu Z (2016) Map2DFusion: real-time incremental UAV image mosaicing based on monocular slam. In: Intelligent Robots and Systems (IROS’16), IEEE/RSJ International Conference on IEEE, pp 4564–4571Google Scholar
  6. Burghardt T, Damen D, Mayol-Cuevas W, Mirmehdi M (2015) Correspondence, matching and recognition. Int J Comput Vis 113(3):161–162CrossRefGoogle Scholar
  7. Capel D, Zisserman A (1998) Automated Mosaicing with Super-resolution Zoom. In: Robotics Research Group, Department of Engineering Science. University of Oxford Oxford OX1 3PJ, UKGoogle Scholar
  8. Fischler MA, Bolles RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24(6):381–395MathSciNetCrossRefGoogle Scholar
  9. Goshtasby AA (2005) 2-D and 3-D image registration for medical, remote sensing, and industrial applications. Wiley, Hoboken (Published simultaneously in Canada)Google Scholar
  10. Hafiane A, Seetharaman G, Zavidovique B (2007) Median binary pattern for textures classification. In: Proceedings of the 4th International Conference (ICIAR). Vol 4633 of Lecture Notes in Computer Science, pp 387–398, Montreal, CanadaGoogle Scholar
  11. Hassaballah M, Abdelmgeid AA, Hammam A (2016) Image features detection, description and matching. Springer International Publishing, SwitzerlandCrossRefGoogle Scholar
  12. Iftikhar H, Khurshid K (2011) Fusion of gabor filter and morphological operators for the detection of settlement zones in google earth satellite images. In: IEEE international conference on signal and image processing applications (ICSIPA), IEEEGoogle Scholar
  13. Jin H, Liu Q, Lu H, Tong X (2004) Face detection using improved LBP under Bayesian framework. In: Proceedings of the 3rd International Conference on Image and Graphics, (ICIG), pp 306–309, Hong Kong, ChinaGoogle Scholar
  14. JF Keane, SS Carr (2013) A brief history of early unmanned aircraft. Johns Hopkins APL Tech Digest 32(3):558–571Google Scholar
  15. Kim J, Kim T, Shin D, Kim SH (2016) Robust mosaicking of Uav images with narrow overlaps. Int Arch Photogram Remote Sens Spatial Inf Sci 41:879CrossRefGoogle Scholar
  16. Laroze M, Courtrai L, Lefèvre S (2016) Human detection from aerial imagery for automatic counting of shellfish gatherers. In: VISIGRAPP (4: VISAPP) (pp 664–671)Google Scholar
  17. Li M, Li D, Dengke F (2012) A Study on automatic UAV image mosaic method for paroxysmal disaster. Int Arch Photogram Remote Sens Spatial Inf Sci 2012:123–128CrossRefGoogle Scholar
  18. Li X, Hui N, Shen H et al (2015) A robust mosaicking procedure for high spatial resolution remote sensing images. ISPRS J Photogram Remote Sens 109:108–125CrossRefGoogle Scholar
  19. Lin WY, Cheng MM, Lu J, Yang H, Do MN, Torr P (2014) Bilateral functions for global motion modeling. In: Proc. of European Conf. on Computer Vision, pp 341–356Google Scholar
  20. Lowe D (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110CrossRefGoogle Scholar
  21. McCormack ED, Trepanier T (2008) The use of small unmanned aircraft by the Washington State Department of Transportation. (No. WA-RD 703.1). Washington State Department of TransportationGoogle Scholar
  22. Nagaraja S, Prabhakar CJ, Praveen Kumar PU (2014) Parallax effect free mosaicing of underwater video sequence based o texture features. Signal Image Process Int J (SIPIJ) 5:5Google Scholar
  23. Nemra A (2010) Robust Airborne 3D visual simultaneous localisation and mapping. PHD Thesis. Cranfield UniversityGoogle Scholar
  24. Ning S, Zhenhai J, Cairong Z (2007) Gender classification based on local binary pattern. J Huazhong Univ Sci Technol 35:177–181 (Chinese)Google Scholar
  25. Paalanen P, Kämäräinen J-K, Kälviäinen H (2009) Image based quantitative mosaic evaluation with artificial video. In: 16th Scandinavian Conference, SCIA, Oslo, Norway, pp 470–479Google Scholar
  26. Rabin J, Delon J, Gousseau Y, Moisan L (2010) Mac-ransac:a robust algorithm for the recognition of multiple objects. In: 3D’PVTGoogle Scholar
  27. Reeff M, Gerhard F, Cattin PC, Székely G (2006) Mosaicing of endoscopic placenta images. GI Jahrestagung 1:467–474Google Scholar
  28. Saravanan C (2010) Color image to grayscale image conversion. In: Second international conference on computer engineering and applications, vol 2, IEEEGoogle Scholar
  29. Sun X et al (2016) Salient Region Detection Based on SLIC and Graph-based Segmentation. In: 4th International Conference on Advanced Materials and Information Technology Processing (AMITP 2016). Atlantis PressGoogle Scholar
  30. Zhengyou Z, Rachid D, Faugeras O, Quang-Tuan, Luong (1995) A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry. Artificial intelligence 78(1–2):87–119CrossRefGoogle Scholar
  31. Zhou Z (2014) FPGA implementation of computer vision algorithm. A thesis submitted in partial satisfaction of the requirement for the degree of Master of Science in Electrical Engineering. University of California (Riverside)Google Scholar
  32. Zhou X et al (2006) Real-time joint landmark recognition and classifier generation by an evolving fuzzy system. In: IEEE international conference on fuzzy systems, pp 1205–1212Google Scholar
  33. Zhou X et al (2007) Autonomous visual self-localization in completely unknown environment using evolving fuzzy rule-based classifier. In: IEEE symposium on computational intelligence in security and defense applicationsGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  • Abdelhai Lati
    • 1
    • 2
    Email author
  • Mahmoud Belhocine
    • 3
  • Noura Achour
    • 1
    • 2
  1. 1.Université de Sciences et Technologie de Houari Boumedian USTHBAlgerAlgeria
  2. 2.Laboratoire de RobotiqueParallélisme et Systèmes Embarqués LRPSEAlgerAlgeria
  3. 3.Centre du Développement des Technologies Avancées CDTAAlgerAlgeria

Personalised recommendations