Advertisement

An Embedded Classifier for Mobile Robot Localization Using Support Vector Machines and Gray-Level Co-occurrence Matrix

  • Fausto Sampaio
  • Elias T. SilvaJrEmail author
  • Lucas C. da Silva
  • Pedro P. Rebouças Filho
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10841)

Abstract

Computer vision applications have been largely incorporated into robotics and industrial automation, improving quality and safety of processes. Such systems involve pattern classifiers for specific functions that, many times, demand high processing time and large data memory. Robotics applications usually deal with restricted resources platforms, in order to preserve battery time and to reduce weight and costs. To assist those applications, this paper presents an investigation on GLCM (Gray Level Co-occurrence Matrix) features and image size for an SVM (Support Vector Machines) classifier that can reduce computer resources utilization while preserving high classifier accuracy. Experimental results show a computing time on the embedded platform of 80.5 ms, with an accuracy above to 99%, to classify images of 80 \(\times \) 60 pixels.

Keywords

Computer vision Neural network applications Robotic applications GLCM SVM 

Notes

Acknowledgment

The authors would like to thank the sponsorship from FUNCAP and CAPES via Grant No. 05/2014 FUNCAP/CAPES.

References

  1. 1.
    Bessa, J., Almeida Barroso, D., Rocha Neto, A., Alexandria, A.: Global location of mobile robots using artificial neural networks in omnidirectional images. IEEE Lat. Am. Trans. 13, 3405–3414 (2015)CrossRefGoogle Scholar
  2. 2.
    Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to Algorithms, 2nd edn. The MIT Press, Cambridge (2001)zbMATHGoogle Scholar
  3. 3.
    Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)zbMATHGoogle Scholar
  4. 4.
    dGB Earth Sciences: Texture directional: a multi-trace attribute that returns textural information based on a statistical texture classification (2015)Google Scholar
  5. 5.
    Hall, M.A.: Correlation-based feature subset selection for machine learning. Ph.D. thesis, University of Waikato, Hamilton, New Zealand (1998)Google Scholar
  6. 6.
    Haralick, R.M.: Statistical and structural approaches to texture. Proc. IEEE 67, 786–804 (1979)CrossRefGoogle Scholar
  7. 7.
    Haralick, R.M., Shanmugam, K., Dinstein, I.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. SMC–3, 610–621 (1973)CrossRefGoogle Scholar
  8. 8.
    Lyons, R.G.: Understanding Digital Signal Processing, 3rd edn. Prentice-Hall, Upper Saddle River (2010)Google Scholar
  9. 9.
    Oliveira, D.C.D., Wehrmeister, M.A.: Towards real-time people recognition on aerial imagery using convolutional neural networks. In: IEEE 19th International Symposium on Real-Time Distributed Computing (ISORC), pp. 27–34, May 2016Google Scholar
  10. 10.
    Sethupathy, J., Veni, S.: Opencv based disease identification of mango leaves. Int. J. Eng. Technol. Sci. Res. - IJETSR 8(5), 1990–1998 (2016)Google Scholar
  11. 11.
    Siéler, L., Tanougast, C., Bouridane, A.: A scalable and embedded fpga architecture for efficient computation of grey level co-occurrence matrices and haralick textures features. Microprocess. Microsyst. 34(1), 14–24 (2010)CrossRefGoogle Scholar
  12. 12.
    da Silva, S.P.P., Marinho, L.B., Almeida, J.S., Rebouças Filho, P.P.: A novel approach for mobile robot localization in topological maps using classification with reject option from structural co-occurrence matrix. In: Felsberg, M., Heyden, A., Krüger, N. (eds.) CAIP 2017. LNCS, vol. 10424, pp. 3–15. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-64689-3_1CrossRefGoogle Scholar
  13. 13.
    Soh, L.K., Tsatsoulis, C.: Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Trans. Geosci. Remote Sens. 37(2), 780–795 (1999)CrossRefGoogle Scholar
  14. 14.
    Wang, H., Guo, X.H., Jia, Z.W., Li, H.K., Liang, Z.G., Li, K.C., He, Q.: Multilevel binomial logistic prediction model for malignant pulmonary nodules based on texture features of CT image. Eur. J. Radiol. 74, 124–129 (2010)CrossRefGoogle Scholar
  15. 15.
    Wang, Z.L., Cai, B.G., Yi, F.Z., Li, M.: Reviews on planar region detection for visual navigation of mobile robot under unknown environment. In: Lee, G. (ed.) Advances in Automation and Robotics, pp. 593–601. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-25646-2_77CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Fausto Sampaio
    • 1
  • Elias T. SilvaJr
    • 1
    Email author
  • Lucas C. da Silva
    • 1
  • Pedro P. Rebouças Filho
    • 1
  1. 1.Computer Science DepartmentFederal Institute of Education, Science and Technology of CearáFortalezaBrazil

Personalised recommendations