A direct approach for object detection with catadioptric omnidirectional cameras


In this paper, we present an omnidirectional vision-based method for object detection. We first adopt the conventional camera approach that uses sliding windows and histogram of oriented gradients (HOG) features. Then, we describe how the feature extraction step of the conventional approach should be modified for a theoretically correct and effective use in omnidirectional cameras. Main steps are modification of gradient magnitudes using Riemannian metric and conversion of gradient orientations to form an omnidirectional sliding window. In this way, we perform object detection directly on the omnidirectional images without converting them to panoramic or perspective images. Our experiments, with synthetic and real images, compare the proposed approach with regular (unmodified) HOG computation on both omnidirectional and panoramic images. Results show that the proposed approach should be preferred.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11


  1. 1.



  1. 1.

    Agarwal, S., Roth, D.: Learning a sparse representation for object detection. European Conference on Computer Vision (ECCV) (2002)

  2. 2.

    Amaral, F.H., Costa, A.H.R.: Object Class Detection in Omnidirectional Images. Workshop de Visao Computacional (WVC) (2009)

  3. 3.

    Arican, Z., Frossard, P.: OMNISIFT: Scale Invariant Features in Omnidirectional Images. In: IEEE 17th International Conference on Image Processing (ICIP) (2010)

  4. 4.

    Bogdanova, I., Bresson, X., Thiran, J.P., Vandergheynst, P.: Scale space analysis and active contours for omnidirectional images. IEEE Trans. Image Process. 16(7), 1888–1901 (2007)

    MathSciNet  Article  Google Scholar 

  5. 5.

    Bulow, T.: Spherical diffusion for 3D surface smoothing. IEEE Trans. PAMI 25, 1650–1654 (2004)

    Article  Google Scholar 

  6. 6.

    Cinaroglu, I., Bastanlar, Y.: A direct approach for human detection with catadioptric omnidirectional cameras. In: IEEE Conference on Signal Processing and Communications Applications (2014)

  7. 7.

    Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2005)

  8. 8.

    Daniilidis, K., Makadia, A., Bulow, T.: Image processing in catadioptric planes: spatiotemporal derivatives and optical flow computation. In: International Workshop on Omnidirectional Vision (OmniVis) (2002)

  9. 9.

    Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. PAMI 34(4), 743–761 (2012)

    Article  Google Scholar 

  10. 10.

    Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model, computer vision and pattern recognition (CVPR) (2008)

  11. 11.

    Geyer, C., Daniilidis, K.: A unifying theory for central panoramic systems and practical applications. In: European Conference on Computer Vision (ECCV) (2000)

  12. 12.

    Hansen, P. Corke, P., Boles, W., Daniilidis, K.: Scale Invariant Features on the Sphere. In: IEEE International Conference on Computer Vision (ICCV) (2007)

  13. 13.

    Iraqui, A., Dupuis, Y., Boutteau, R., Ertaud, J., Savatier, X.: Fusion of omnidirectional and PTZ cameras for face detection and tracking. In: International Conference on Emerging Security Technologies (2010)

  14. 14.

    Kang, S., Roh, A., Nam, B., Hong, H.: People detection method using GPUs for a mobile robot with an omnidirectional camera. Opt. Eng. 50(12), 127204 (2011)

    Article  Google Scholar 

  15. 15.

    Leibe, B., Leonardis, A., Schiele, B.: Combined object categorization and segmentation with an implicit shape model. In: Proceedings of the Workshop on Statistical Learning in Computer Vision (2004)

  16. 16.

    Lourenco, M., Barreto, J.P., Vasconcelos, F.: sRD-SIFT: keypoint detection and matching in images with radial distortion. IEEE Trans. Robot. 28(3), 752–760 (2012)

    Article  Google Scholar 

  17. 17.

    Lowe, D.: Distinctive image features from scale invariant keypoints. Int. J. Comput. Vision (IJCV) 60, 91–110 (2004)

    Article  Google Scholar 

  18. 18.

    Maji, S., Berg, A.C., Malik, J.: Classification using Intersection Kernel Support Vector Machines is Efficient. Computer Vision and Pattern Recognition (CVPR) (2008)

  19. 19.

    Mei, C., Rives, P.: Single Viewpoint Omnidirectional Camera Calibration from Planar Grids. In: Proceedings of International Conference on Pattern Recognition (ICPR) (2007)

  20. 20.

    Puig, L., Guerrero, J.J.: Scale Space for Central Catadioptric Systems: Towards a Generic Camera Feature Extractor. In: International Conference on Computer Vision (ICCV) (2011)

  21. 21.

    Puig, L., Bastanlar, Y., Sturm, P., Guerrero, J., Barreto, J.: Calibration of central catadioptric cameras using a DLT-like approach. Int. J. Comput. Vision (IJCV) 93(1), 101–114 (2011)

    Article  Google Scholar 

  22. 22.

    Puig, L., Guerrero, J.J., Daniilidis, K.: Scale space for camera invariant features. IEEE Trans. PAMI 36(9), 1832–1846 (2014)

  23. 23.

    Tang, Y., Li, Y., Bai, T., Zhou, X.: Human Tracking in Thermal Catadioptric Omnidirectional Vision. In: International Conference on Information and Automation (ICIA) (2011)

  24. 24.

    Walk, S., Majer, N., Schindler, K., Schiele, B.: New Features and Insights for Pedestrian Detection. In: IEEE Conference on Computer Vision and Pattern Recognition (2010)

  25. 25.

    Wang, M.L., Lin, H.Y.: Object Recognition from Omnidirectional Visual Sensing for Mobile Robot Applications. In: IEEE International Conference on Systems, Man and Cybernetics (2009)

Download references

Author information



Corresponding author

Correspondence to Yalin Bastanlar.

Additional information

This work was supported by the TUBITAK Project 113E107.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 195 KB)

Supplementary material 2 (pdf 912 KB)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Cinaroglu, I., Bastanlar, Y. A direct approach for object detection with catadioptric omnidirectional cameras. SIViP 10, 413–420 (2016). https://doi.org/10.1007/s11760-015-0768-2

Download citation


  • Catadioptric omnidirectional cameras
  • Object detection
  • Human detection
  • Car detection
  • Vehicle detection