Distortion Adaptive Descriptors: Extending Gradient-Based Descriptors to Wide Angle Images

  • Antonino FurnariEmail author
  • Giovanni Maria Farinella
  • Arcangelo Ranieri Bruna
  • Sebastiano Battiato
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9280)


Gradient-based descriptors have proven successful in a wide variety of applications. Their standard implementations usually assume that the input images have been acquired using classic perspective cameras. In practice many real-world systems make use of wide angle cameras which allow to obtain wider Fields of View (FOV) but introduce radial distortion which breaks the rectilinear assumption. The most straightforward way to overcome such a problem is to compensate the distortion by unwarping the original image prior to computing the descriptor. The rectification process, however, is computationally expansive and introduces artefacts which can deceive the subsequent analysis (e.g., feature matching). We propose the Distortion Adaptive Descriptors (DAD), a new paradigm to correctly compute local descriptors directly in the distorted domain. We combine the DAD with existing techniques to correctly estimate the gradient of distorted images and hence derive a set of SIFT and HOG-based descriptors. Experiments show that the DAD paradigm allows to improve the matching ability of the SIFT and HOG descriptors when they are computed directly in the distorted domain.


Gradient-based descriptors Wide angle images Gradient estimation SIFT HOG 


  1. 1.
    Furnari, A., Farinella, G.M., Puglisi, G., Bruna, A.R., Battiato, S.: Affine Region Detectors on the Fisheye Domain. In: IEEE International Conference on Image Processing (2014)Google Scholar
  2. 2.
    Miyamoto, K.: Fish eye lens. Journal of the Optical Society of America, 2–3 (1964)Google Scholar
  3. 3.
    Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms. In: Proceedings of the international conference on Multimedia, pp. 1469–1472, (2010)Google Scholar
  4. 4.
    Puig, L., Guerrero, J.J.: Omnidirectional Vision Systems. Springer (2013)Google Scholar
  5. 5.
    Baker, S., Nayar, S.K.: A theory of catadioptric image formation. In: International Conference on Computer Vision, pp. 35–42 (1998)Google Scholar
  6. 6.
    Lourenço, M., Barreto, J.P., Vasconcelos, F.: sRD-SIFT: keypoint detection and matching in images with radial distortion. IEEE Transactions on Robotics 28(3), 752–760 (2012)CrossRefGoogle Scholar
  7. 7.
    Cinaroglu, I., Bastanlar, Y.: A direct approach for human detection with catadioptric omnidirectional cameras. In: Signal Processing and Communications Applications Conference, pp. 2275–2279 (2014)Google Scholar
  8. 8.
    Cruz-Mota, J., Bogdanova, I., Paquier, B., Bierlaire, M., Thiran, J.: Scale invariant feature transform on the sphere: theory and applications. International Journal of Computer Vision 98(2), 217–241 (2011)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Lowe, D.G.: Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision 60, 91–110Google Scholar
  10. 10.
    Furnari, A., Farinella, G.M., Bruna, A.R., Battiato, S.: Generalized Sobel filters for gradient estimation of distorted images. In: The International Conference on Image Processing (submitted 2015)Google Scholar
  11. 11.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. Computer Vision and Pattern Recognition 1, 886–893 (2005)Google Scholar
  12. 12.
    Hughes, C., Glavin, M., Jones, E., Denny, P.: Wideangle camera technology for automotive applications: a review. IET Intelligent Transport Systems 3(1), 19–31 (2009)CrossRefGoogle Scholar
  13. 13.
    Battiato, S., Farinella, G.M., Furnari, A., Puglisi, G., Snijders, A., Spiekstra, J.: A Customized System for Vehicle Tracking and Classification, Expert Systems With Applications (2015)Google Scholar
  14. 14.
    Battiato, S., Gallo, G., Puglisi, G., Scellato, S.: SIFT features tracking for video stabilization. In: International Conference on Image Analysis and Processing, pp. 825–830 (2007)Google Scholar
  15. 15.
    Dorko, G., Schmid, C.: Selection of Scale-Invariant Parts for Object Class Recognition. In: International Conference on Computer Vision, pp. 634–640 (2003)Google Scholar
  16. 16.
    Brown M., Lowe, D.: Recognising Panoramas. In: International Conference on Computer Vision, pp. 1218–1227 (2003)Google Scholar
  17. 17.
    Fitzgibbon, A.W.: Simultaneous linear estimation of multiple view geometry and lens distortion. In: Computer Vision and Pattern Recognition, vol. 1 (2001)Google Scholar
  18. 18.
    Mikolajczyk, K., Schmid, C.: Performance evaluation of local descriptors. Pattern Analysis and Machine Intelligence 27(10), 1615–30 (2005)CrossRefGoogle Scholar
  19. 19.
    Liu, C., Yuen, J., Torralba, A.: SIFT flow: dense correspondence across scenes and its applications. Pattern Analysis and Machine Intelligence 33(5) (2011)Google Scholar
  20. 20.
    Farinella, G.M., Allegra, D., Stanco, F.: A benchmark dataset to study the representations of food images. In: Assistive Computer Vision and Robotics in conjunction with the European Conference on Computer Vision (2011)Google Scholar
  21. 21.
    Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Computer Vision and Pattern Recognition, vol. 2 (2006)Google Scholar
  22. 22.
    Achanta, R., Hemami, S., Estrada, F., Susstrunk, S.: Frequency-tuned salient region detection. In: Computer Vision and Pattern Recognition, pp. 1597–1604 (2009)Google Scholar
  23. 23.
    Felzenszwalb, P.F., Grishick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. Pattern Analysis and Machine Intelligence (2009)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Antonino Furnari
    • 1
    Email author
  • Giovanni Maria Farinella
    • 1
  • Arcangelo Ranieri Bruna
    • 2
  • Sebastiano Battiato
    • 1
  1. 1.Department of Mathematics and Computer ScienceUniversity of CataniaCataniaItaly
  2. 2.Advanced System Technology - Computer VisionSTMicroelectronicsCataniaItaly

Personalised recommendations