Locality-Constrained Linear Coding with Spatial Pyramid Matching for SAR Image Classification

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 215)

Abstract

We propose a linear spatial pyramid matching using locality-constraint linear coding for SAR image classification based on MSTAR database. Recently, works have little consideration about targets’ randomly distributed poses when applying sparse coding in coding scheme. We do the preprocessing of pose estimation to generate over-complete codebook and therefore reduce reconstruction error. SIFT descriptors extracted from images are projected into its local-coordinate system by Locality-constrained linear coding instead of sparse coding. Locality constraint ensures similar patches will share similar codes. The codes are then pooled within each sub-region partitioned according to spatial pyramid and concatenated to form the final feature vectors. We use max-pooling which is more salient and robust to local translation. With linear SVM classifier, the proposed approach achieves better performance than traditional ScSPM method.

Keywords

SAR recognition Locality-constrained linear coding Spatial pyramid matching 

References

  1. 1.
    Ross T, Worrell S, Velten V, Mossing J, Bryant M (1998) Standard SAR ATR evaluation experiments using the MSTAR public release data set. In: Proceedings of SPIE, algorithms for synthetic aperture radar imagery V, vol 3370. Orlando, FL, pp 566–573Google Scholar
  2. 2.
    Bryant M, Garber F (1999) SVM classifier applied to the MSTAR public data set. In: Proceedings of SPIE, algorithms for synthetic aperture radar imagery VI, vol 3721. Orlando, FL, pp 355–360Google Scholar
  3. 3.
    Sun Y, Liu Z, Todorovic S, Li J (2007) Adaptive boosting for SAR automatic target recognition. IEEE Trans Aerosp Electron Syst 43:1CrossRefGoogle Scholar
  4. 4.
    Wei G, Qi Q, Jiang L, Zhang P (2008) A new method of SAR image target recognition based on adaboost algorithm. In: Geoscience and remote sensing symposiumGoogle Scholar
  5. 5.
    Yin H, Cao Y, Sun H (2011) Combining pyramid representation and AdaBoost for urban scene classification using high-resolution synthetic aperture radar images. IET Radar Sonar Navig 5(1):58–64Google Scholar
  6. 6.
    Cande`s E (2006) Compressive sampling. In: Proceedings of the international congress of mathematicians, Madrid, Spain, pp 1433–1452Google Scholar
  7. 7.
    Wright J, Yang AY, Ganesh A, Sastry SS, Ma Y (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell 31(2):210–227CrossRefGoogle Scholar
  8. 8.
    Thiagarajan JJ, Ramamurthy KN, Knee P, Spanias A, Berisha V (2010) Sparse representations for automatic target classification in SAR images. In: Proceedings of IEEE 4th international symposium on communications, control and signal processing (ISCCSP), pp 1–4 Google Scholar
  9. 9.
    Knee P, Thiagarajan JJ, Ramamurthy KN, Spanias A (2011) SAR target classification using sparse representations and spatial pyramids. In: Radar conference (RADAR), pp 294–298Google Scholar
  10. 10.
    Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of CVPR’06, vol 2, New York, pp 2169–21785Google Scholar
  11. 11.
    Yang J, Yu K, Gong Y, Huang T (2009) Linear spatial pyramid matching using sparse coding for image classification. In: Proceedings of IEEE conference on computer vision and pattern recognition, CVPR, pp 1794–1801Google Scholar
  12. 12.
    Wang J, Yang J, Yu K, Lv F, Huang T, Gong Y (2010) Locality-constrained linear coding for image classification. 2010 IEEE conference on computer vision and pattern recognitionGoogle Scholar
  13. 13.
    Yu K, Zhang T, Gong Y. (2009) Nonlinear learning using local coordinate coding. In: Advances in neural information processing systems, vol 22, pp 2223–2231Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  1. 1.State Key Laboratory of Intelligent Technology and Systems, Department of Computer Science and TechnologyTsinghua UniversityBeijingPeople’s Republic of China

Personalised recommendations