Skip to main content

2017 | OriginalPaper | Buchkapitel

Dynamic Texture Recognition Using Time-Causal Spatio-Temporal Scale-Space Filters

verfasst von : Ylva Jansson, Tony Lindeberg

Erschienen in: Scale Space and Variational Methods in Computer Vision

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

This work presents an evaluation of using time-causal scale-space filters as primitives for video analysis. For this purpose, we present a new family of video descriptors based on regional statistics of spatio-temporal scale-space filter responses and evaluate this approach on the problem of dynamic texture recognition. Our approach generalises a previously used method, based on joint histograms of receptive field responses, from the spatial to the spatio-temporal domain. We evaluate one member in this family, constituting a joint binary histogram, on two widely used dynamic texture databases. The experimental evaluation shows competitive performance compared to previous methods for dynamic texture recognition, especially on the more complex DynTex database. These results support the descriptive power of time-causal spatio-temporal scale-space filters as primitives for video analysis.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Hubel, D.H., Wiesel, T.N.: Brain and Visual Perception: The Story of a 25-Year Collaboration. Oxford University Press, Oxford (2005) Hubel, D.H., Wiesel, T.N.: Brain and Visual Perception: The Story of a 25-Year Collaboration. Oxford University Press, Oxford (2005)
2.
3.
Zurück zum Zitat Lindeberg, T.: Generalized Gaussian scale-space axiomatics comprising linear scale-space, affine scale-space and spatio-temporal scale-space. J. Math. Imaging Vis. 40, 36–81 (2011)MathSciNetCrossRefMATH Lindeberg, T.: Generalized Gaussian scale-space axiomatics comprising linear scale-space, affine scale-space and spatio-temporal scale-space. J. Math. Imaging Vis. 40, 36–81 (2011)MathSciNetCrossRefMATH
5.
Zurück zum Zitat Chetverikov, D., Péteri, R.: A brief survey of dynamic texture description and recognition. In: Kurzyński, M., Puchała, E., Woźniak, M., Żołnierek, A. (eds.) Computer Recognition Systems. AINSC, vol. 30, pp. 17–26. Springer, Heidelberg (2005). doi:10.1007/3-540-32390-2_2 CrossRef Chetverikov, D., Péteri, R.: A brief survey of dynamic texture description and recognition. In: Kurzyński, M., Puchała, E., Woźniak, M., Żołnierek, A. (eds.) Computer Recognition Systems. AINSC, vol. 30, pp. 17–26. Springer, Heidelberg (2005). doi:10.​1007/​3-540-32390-2_​2 CrossRef
6.
Zurück zum Zitat Linde, O., Lindeberg, T.: Composed complex-cue histograms: an investigation of the information content in receptive field based image descriptors for object recognition. Comput. Vis. Image Underst. 116, 538–560 (2012)CrossRef Linde, O., Lindeberg, T.: Composed complex-cue histograms: an investigation of the information content in receptive field based image descriptors for object recognition. Comput. Vis. Image Underst. 116, 538–560 (2012)CrossRef
7.
Zurück zum Zitat Nelson, R.C., Polana, R.: Qualitative recognition of motion using temporal texture. CVGIP: Image Underst. 56, 78–89 (1992)CrossRefMATH Nelson, R.C., Polana, R.: Qualitative recognition of motion using temporal texture. CVGIP: Image Underst. 56, 78–89 (1992)CrossRefMATH
8.
Zurück zum Zitat Soatto, S., Doretto, G., Wu, Y.N.: Dynamic textures. In: IEEE International Conference on Computer Vision, vol. 2, pp. 439–446 (2001) Soatto, S., Doretto, G., Wu, Y.N.: Dynamic textures. In: IEEE International Conference on Computer Vision, vol. 2, pp. 439–446 (2001)
9.
Zurück zum Zitat Ravichandran, A., Chaudhry, R., Vidal, R.: View-invariant dynamic texture recognition using a bag of dynamical systems. In: Computer Vision and Pattern Recognition, pp. 1651–1657 (2009) Ravichandran, A., Chaudhry, R., Vidal, R.: View-invariant dynamic texture recognition using a bag of dynamical systems. In: Computer Vision and Pattern Recognition, pp. 1651–1657 (2009)
10.
Zurück zum Zitat Wang, L., Liu, H., Sun, F.: Dynamic texture video classification using extreme learning machine. Neurocomputing 174, 278–285 (2016)CrossRef Wang, L., Liu, H., Sun, F.: Dynamic texture video classification using extreme learning machine. Neurocomputing 174, 278–285 (2016)CrossRef
11.
Zurück zum Zitat Wildes, R.P., Bergen, J.R.: Qualitative spatiotemporal analysis using an oriented energy representation. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 768–784. Springer, Heidelberg (2000). doi:10.1007/3-540-45053-X_49 CrossRef Wildes, R.P., Bergen, J.R.: Qualitative spatiotemporal analysis using an oriented energy representation. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 768–784. Springer, Heidelberg (2000). doi:10.​1007/​3-540-45053-X_​49 CrossRef
12.
Zurück zum Zitat Derpanis, K.G., Wildes, R.P.: Spacetime texture representation and recognition based on a spatiotemporal orientation analysis. IEEE Trans. Pattern Anal. Mach. Intell. 34, 1193–1205 (2012)CrossRef Derpanis, K.G., Wildes, R.P.: Spacetime texture representation and recognition based on a spatiotemporal orientation analysis. IEEE Trans. Pattern Anal. Mach. Intell. 34, 1193–1205 (2012)CrossRef
13.
Zurück zum Zitat Gonçalves, W.N., Machado, B.B., Bruno, O.M.: Spatiotemporal Gabor filters: a new method for dynamic texture recognition. arXiv preprint arXiv:1201.3612 (2012) Gonçalves, W.N., Machado, B.B., Bruno, O.M.: Spatiotemporal Gabor filters: a new method for dynamic texture recognition. arXiv preprint arXiv:​1201.​3612 (2012)
14.
Zurück zum Zitat Zhao, G., Pietikainen, M.: Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Trans. Pattern Anal. Mach. Intell. 29, 915–928 (2007)CrossRef Zhao, G., Pietikainen, M.: Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Trans. Pattern Anal. Mach. Intell. 29, 915–928 (2007)CrossRef
15.
Zurück zum Zitat Ren, J., Jiang, X., Yuan, J.: Dynamic texture recognition using enhanced LBP features. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2400–2404 (2013) Ren, J., Jiang, X., Yuan, J.: Dynamic texture recognition using enhanced LBP features. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2400–2404 (2013)
16.
Zurück zum Zitat Hong, S., Ryu, J., Yang, H.S.: Not all frames are equal: aggregating salient features for dynamic texture classification. In: Multidimensional Systems and Signal Processing (2016). doi:10.1007/s11045-016-0463-7 Hong, S., Ryu, J., Yang, H.S.: Not all frames are equal: aggregating salient features for dynamic texture classification. In: Multidimensional Systems and Signal Processing (2016). doi:10.​1007/​s11045-016-0463-7
17.
Zurück zum Zitat Arashloo, S.R., Kittler, J.: Dynamic texture recognition using multiscale binarized statistical image features. IEEE Trans. Multimedia 16, 2099–2109 (2014)CrossRef Arashloo, S.R., Kittler, J.: Dynamic texture recognition using multiscale binarized statistical image features. IEEE Trans. Multimedia 16, 2099–2109 (2014)CrossRef
18.
Zurück zum Zitat Quan, Y., Huang, Y., Ji, H.: Dynamic texture recognition via orthogonal tensor dictionary learning. In: IEEE International Conference on Computer Vision, pp. 73–81 (2015) Quan, Y., Huang, Y., Ji, H.: Dynamic texture recognition via orthogonal tensor dictionary learning. In: IEEE International Conference on Computer Vision, pp. 73–81 (2015)
19.
Zurück zum Zitat Schiele, B., Crowley, J.: Recognition without correspondence using multidimensional receptive field histograms. Int. J. Comput. Vis. 36, 31–50 (2000)CrossRef Schiele, B., Crowley, J.: Recognition without correspondence using multidimensional receptive field histograms. Int. J. Comput. Vis. 36, 31–50 (2000)CrossRef
20.
Zurück zum Zitat Xu, Y., Quan, Y., Zhang, Z., Ling, H., Ji, H.: Classifying dynamic textures via spatiotemporal fractal analysis. Pattern Recogn. 48, 3239–3248 (2015)CrossRef Xu, Y., Quan, Y., Zhang, Z., Ling, H., Ji, H.: Classifying dynamic textures via spatiotemporal fractal analysis. Pattern Recogn. 48, 3239–3248 (2015)CrossRef
21.
Zurück zum Zitat Ji, H., Yang, X., Ling, H., Xu, Y.: Wavelet domain multifractal analysis for static and dynamic texture classification. IEEE Trans. Image Process. 22, 286–299 (2013)MathSciNetCrossRef Ji, H., Yang, X., Ling, H., Xu, Y.: Wavelet domain multifractal analysis for static and dynamic texture classification. IEEE Trans. Image Process. 22, 286–299 (2013)MathSciNetCrossRef
22.
Zurück zum Zitat Ghanem, B., Ahuja, N.: Maximum margin distance learning for dynamic texture recognition. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6312, pp. 223–236. Springer, Heidelberg (2010). doi:10.1007/978-3-642-15552-9_17 CrossRef Ghanem, B., Ahuja, N.: Maximum margin distance learning for dynamic texture recognition. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6312, pp. 223–236. Springer, Heidelberg (2010). doi:10.​1007/​978-3-642-15552-9_​17 CrossRef
23.
Zurück zum Zitat Yang, F., Xia, G.S., Liu, G., Zhang, L., Huang, X.: Dynamic texture recognition by aggregating spatial and temporal features via ensemble SVMs. Neurocomputing 173, 1310–1321 (2016)CrossRef Yang, F., Xia, G.S., Liu, G., Zhang, L., Huang, X.: Dynamic texture recognition by aggregating spatial and temporal features via ensemble SVMs. Neurocomputing 173, 1310–1321 (2016)CrossRef
24.
Zurück zum Zitat Qi, X., Li, C., Guoying, Z., Hong, X., Pietikäinen, M.: Dynamic texture and scene classification by transferring deep image features. Neurocomputing 171, 1230–1241 (2016)CrossRef Qi, X., Li, C., Guoying, Z., Hong, X., Pietikäinen, M.: Dynamic texture and scene classification by transferring deep image features. Neurocomputing 171, 1230–1241 (2016)CrossRef
26.
Zurück zum Zitat Péteri, R., Fazekas, S., Huiskes, M.J.: Dyntex: a comprehensive database of dynamic textures. Pattern Recogn. Lett. 31, 1627–1632 (2010)CrossRef Péteri, R., Fazekas, S., Huiskes, M.J.: Dyntex: a comprehensive database of dynamic textures. Pattern Recogn. Lett. 31, 1627–1632 (2010)CrossRef
27.
Zurück zum Zitat Dubois, S., Péteri, R., Ménard, M.: Characterization and recognition of dynamic textures based on the 2D+T curvelet transform. Sig. Image Video Process. 9, 819–830 (2015)CrossRef Dubois, S., Péteri, R., Ménard, M.: Characterization and recognition of dynamic textures based on the 2D+T curvelet transform. Sig. Image Video Process. 9, 819–830 (2015)CrossRef
28.
Zurück zum Zitat Jansson, Y., Lindeberg, T.: Dynamic texture recognition using time-causal and time-recursive spatio-temporal receptive fields (2017, in preparation) Jansson, Y., Lindeberg, T.: Dynamic texture recognition using time-causal and time-recursive spatio-temporal receptive fields (2017, in preparation)
Metadaten
Titel
Dynamic Texture Recognition Using Time-Causal Spatio-Temporal Scale-Space Filters
verfasst von
Ylva Jansson
Tony Lindeberg
Copyright-Jahr
2017
DOI
https://doi.org/10.1007/978-3-319-58771-4_2

Premium Partner