The Visual Computer

, Volume 34, Issue 5, pp 707–719 | Cite as

Rotation-invariant object detection using Sector-ring HOG and boosted random ferns

  • Baozhen Liu
  • Hang Wu
  • Weihua Su
  • Wenchang Zhang
  • Jinggong Sun
Original Article


The histogram of oriented gradients (HOG) is widely used for image description and has proven to be very effective. In some practical applications that lack an assumption of the object’s orientation, rotation-invariant detection is of vital significance. To address this problem, this paper presents a new visual feature, Sector-ring HOG (SRHOG), which is obtained by improving the gradient binning and spatial binning based on HOG. The new feature can convert planar image rotations into cyclic shifts of the final descriptor and thereby facilitate rotated object detection. After modifying boosted random ferns in SRHOG feature domain, we further propose two strategies for rotation-invariant object detection: one depends completely on the new feature’s characteristic, and the other introduces an orientation estimation step. The former is more suitable to ‘finding objects’ and the latter can provide the higher orientation estimation accuracy. Both the use of supervised learning and working in the gradient space make our approaches effective and robust. We show these properties by thorough testing on the public Freestyle Motocross dataset and our dataset for victim detection in post-disaster rescue efforts.


Rotation-invariant detection Sector-ring HOG HOG Boosted random ferns (BRFs) 



This work was supported by Science & Technology Pillar Program of Tianjin, China (16YFZCSF00590).


  1. 1.
    Cai, N., Su, Z., Lin, Z., Wang, H., Yang, Z., Ling, W.K.B.: Blind inpainting using the fully convolutional neural network. Vis. Comput. (2015). doi: 10.1007/s00371-015-1190-z
  2. 2.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)Google Scholar
  3. 3.
    He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask r-cnn. arXiv preprint arXiv:1703.06870, (2017)
  4. 4.
    Cheng, G., Zhou, P., Han, J.: Learning rotation-invariant convolutional neural networks for object detection in vhr optical remote sensing images. IEEE Trans. Geosci. Remote Sens. 54(12), 7405–7415 (2016)CrossRefGoogle Scholar
  5. 5.
    Cheng, G., Zhou, P., Han, J.: Rifd-cnn: rotation-invariant and fisher discriminative convolutional neural networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2884–2893 (2016)Google Scholar
  6. 6.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05). IEEE, vol. 1, pp. 886–893 (2005)Google Scholar
  7. 7.
    Murtza, I., Abdullah, D., Khan, A., Arif, M., Mirza, S.M.: Cortex-inspired multilayer hierarchy based object detection system using phog descriptors and ensemble classification. Vis. Comput. 33(1), 99–112 (2017)CrossRefGoogle Scholar
  8. 8.
    Kong, Y., Dong, W., Mei, X., Zhang, X., Paul, J.C.: Simlocator: robust locator of similar objects in images. Vis. Comput. 29(9), 861–870 (2013)CrossRefGoogle Scholar
  9. 9.
    Liu, K., Skibbe, H., Schmidt, T., Blein, T., Palme, K., Brox, T., Ronneberger, O.: Rotation-invariant hog descriptors using fourier analysis in polar and spherical coordinates. Int. J. Comput. Vis. 106(3), 342–364 (2014)MathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    Villamizar, M., Moreno-Noguer, F., Andrade-Cetto, J., Sanfeliu, A.: Efficient rotation invariant object detection using boosted random ferns. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 1038–1045 (2010)Google Scholar
  11. 11.
    David, G.L.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)CrossRefGoogle Scholar
  12. 12.
    Andriluka, M., Schnitzspan, P., Meyer, J., Kohlbrecher, S., Petersen, K., Von Stryk, O., Roth, S., Schiele, B.: Vision based victim detection from unmanned aerial vehicles. In: 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pp. 1740–1747 (2010)Google Scholar
  13. 13.
    Huang, C., Ai, H., Li, Y., Lao, S.: Vector boosting for rotation invariant multi-view face detection. In: Tenth IEEE International Conference on Computer Vision (ICCV’05) Volume 1. IEEE, vol. 1, pp. 446–453 (2005)Google Scholar
  14. 14.
    Torralba, A., Murphy, K.P., Freeman, W.T.: Sharing visual features for multiclass and multiview object detection. IEEE Trans. Pattern Anal. Mach. Intell. 29(5), 854–869 (2007)CrossRefGoogle Scholar
  15. 15.
    Vedaldi, A., Blaschko, M., Zisserman, A.: Learning equivariant structured output svm regressors. In: 2011 IEEE International Conference on Computer Vision. IEEE, pp. 959–966 (2011)Google Scholar
  16. 16.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1615–1630 (2005)CrossRefGoogle Scholar
  17. 17.
    Zhang, W., Sun, X., Fu, K., Wang, C., Wang, H.: Object detection in high-resolution remote sensing images using rotation invariant parts based model. IEEE Geosci. Remote Sens. Lett. 11(1), 74–78 (2014)CrossRefGoogle Scholar
  18. 18.
    Gauglitz, S., Turk, M., Höllerer, T.: Improving keypoint orientation assignment. In: BMVC, pp. 1–11 (2011)Google Scholar
  19. 19.
    Skibbe, H., Reisert, M.: Circular fourier-hog features for rotation invariant object detection in biomedical images. In: ISBI, pp. 450–453 (2012)Google Scholar
  20. 20.
    Zhao, G., Ahonen, T., Matas, J., Pietikainen, M.: Rotation-invariant image and video description with local binary pattern features. IEEE Trans. Image Process. 21(4), 1465–1477 (2012)MathSciNetCrossRefzbMATHGoogle Scholar
  21. 21.
    Qi, X., Xiao, R., Li, C.G., Qiao, Y., Guo, J., Tang, X.: Pairwise rotation invariant co-occurrence local binary pattern. IEEE Trans. Pattern Anal. Mach. Intell. 36(11), 2199–2213 (2014)CrossRefGoogle Scholar
  22. 22.
    Takacs, G., Chandrasekhar, V., Tsai, S., Chen, D., Grzeszczuk, R., Girod, B.: Unified real-time tracking and recognition with rotation-invariant fast features. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 934–941 (2010)Google Scholar
  23. 23.
    Takacs, G., Chandrasekhar, V., Tsai, S.S., Chen, D., Grzeszczuk, R., Girod, B.: Fast computation of rotation-invariant image features by an approximate radial gradient transform. IEEE Trans. Image Process. 22(8), 2970–2982 (2013)MathSciNetCrossRefzbMATHGoogle Scholar
  24. 24.
    Lepetit, V., Fua, P.: Keypoint recognition using randomized trees. IEEE Trans. Pattern Anal. Mach. Intell. 28(9), 1465–1479 (2006)CrossRefGoogle Scholar
  25. 25.
    Ozuysal, M., Fua, P., Lepetit, V.: Fast keypoint recognition in ten lines of code. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, pp. 1–8 (2007)Google Scholar
  26. 26.
    Schapire, R.E., Singer, Y.: Improved boosting algorithms using confidence-rated predictions. Mach. Learn. 37(3), 297–336 (1999)CrossRefzbMATHGoogle Scholar
  27. 27.
    Liu, K., Wang, Q., Driever, W., Ronneberger, O.: 2d/3d rotation-invariant detection using equivariant filters and kernel weighted mapping. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 917–924 (2012)Google Scholar
  28. 28.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. IEEE, vol. 2, pp. II-264 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2017

Authors and Affiliations

  • Baozhen Liu
    • 1
  • Hang Wu
    • 1
  • Weihua Su
    • 1
  • Wenchang Zhang
    • 1
  • Jinggong Sun
    • 1
  1. 1.Institute of Medical EquipmentAcademy of Military Medical ScienceTianjinChina

Personalised recommendations