Skip to main content
SpringerLink
Log in

Dynamic texture description using adapted bipolar-invariant and blurred features

  • Published:
Multidimensional Systems and Signal Processing Aims and scope Submit manuscript

Abstract

Encoding turbulent properties of dynamic textures (DTs) is a challenging issue of video understanding for various applications in computer vision. It is partly due to the negative impacts of noise, changes of illumination, and scales. In order to deal with those influences, this paper proposes a new approach in which local adapted features of multi-Gaussian-filtered outcomes are exploited for DT representation against the well-known problems. To this end, we firstly take multi-scale 2D/3D Gaussian-based filtering kernels into account video analysis in order to correspondingly obtain Gaussian-based filtered outcomes of which the blurred and bipolar-invariant characteristics are complementary. Secondly, due to the sensitivity to noise and near-uniform regions in the encoding of bipolar-invariant features, we propose an essential modification for completed local binary pattern operator to form a more discriminative operator, named Completed AdaptIve Pattern, so that it can be in accordance with the perplexity. Finally, a prominent framework is introduced to efficiently capture DTs’ shape and motion clues in Gaussian-based filtered results. The proposed descriptors are verified on benchmark datasets for DT classification task. Experimental results have validated the interest of our method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Notes

  1. The meaningful threshold \(\varepsilon \) is used to eliminate the noise caused by the close-to-zero pixels. Vu et al. (2014) investigated the influence of \(\varepsilon \) on the decomposition of the DoG-based responses. As a result, they have substantiated that the adapted threshold of \(\varepsilon \) should be set to 0.15 for textural image representation. In addition, it should be noted that DTs could be featured by a series of textural images in a temporal domain. Therefore, it can be inherited for DT description in this work.

References

  • Amit, Raman, B., & Sadhya, D. (2020). Dynamic texture recognition using local tetra pattern—Three orthogonal planes (ltrp-top). The Visual Computer,36(3), 579–592.

  • Andrearczyk, V., & Whelan, P. F. (2018). Convolutional neural network on three orthogonal planes for dynamic texture classification. Pattern Recognition, 76, 36–49.

    Article  Google Scholar 

  • Arashloo, S. R. (2019). Sparse binarised statistical dynamic features for spatio-temporal texture analysis. Signal, Image and Video Processing, 13(3), 575–582.

    Article  Google Scholar 

  • Arashloo, S. R., Amirani, M. C., & Noroozi, A. (2017). Dynamic texture representation using a deep multi-scale convolutional network. JVCIR, 43, 89–97.

    Google Scholar 

  • Arashloo, S. R., & Kittler, J. (2014). Dynamic texture recognition using multiscale binarized statistical image features. IEEE Transactions on Multimedia, 16(8), 2099–2109.

    Article  Google Scholar 

  • Chan, A. B., & Vasconcelos, N. (2007). Classifying video with kernel dynamic textures. In CVPR.

  • Chan, A. B., & Vasconcelos, N. (2008). Modeling, clustering, and segmenting video with mixtures of dynamic textures. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(5), 909–926.

    Article  Google Scholar 

  • Chen, L., Liu, J., & Wang, X. (2021). Background subtraction with Kronecker-basis-representation based tensor sparsity and l\({}_{\text{1, } \text{1, } \text{2 }}\) norm. Multidimensional Systems and Signal Processing, 32(1), 77–90.

    Article  MathSciNet  Google Scholar 

  • Chen, L., Peng, X., Tian, J., & Liu, J. (2018). A learning-based approach for leaf detection in traffic surveillance video. Multidimensional Systems and Signal Processing, 29(4), 1895–1904.

    Article  Google Scholar 

  • Chen, Y., Hua, C., & Guo, X. (2017). Face model fitting on video sequences based on incremental virtual active appearance model. Multidimensional Systems and Signal Processing, 28(1), 1–21.

    Article  MathSciNet  MATH  Google Scholar 

  • de Carvalho, G. H. F., Thomaz, L. A., da Silva, A. F., da Silva, E. A. B., & Netto, S. L. (2019). Anomaly detection with a moving camera using multiscale video analysis. Multidimensional Systems and Signal Processing, 30(1), 311–342.

    Article  MATH  Google Scholar 

  • de Mesquita Sá Junior, J. J., Ribas, L. C., & Bruno, O. M. (2019). Randomized neural network based signature for dynamic texture classification. Expert Systems with Applications, 135, 194–200.

    Article  Google Scholar 

  • Dimitropoulos, K., Barmpoutis, P., Kitsikidis, A., & Grammalidis, N. (2018). Classification of multidimensional time-evolving data using histograms of grassmannian points. IEEE Transactions on Circuits and Systems for Video Technology, 28(4), 892–905.

    Article  Google Scholar 

  • Dong, Y., Feng, J., Yang, C., Wang, X., Zheng, L., & Pu, J. (2018). Multi-scale counting and difference representation for texture classification. The Visual Computer, 34(10), 1315–1324.

    Article  Google Scholar 

  • Dubois, S., Péteri, R., & Ménard, M. (2015). Characterization and recognition of dynamic textures based on the 2d+t curvelet transform. Signal, Image and Video Processing, 9(4), 819–830.

    Article  Google Scholar 

  • Falconer, K. (1997). Techniques in fractal geometry. Hoboken: Wiley.

    MATH  Google Scholar 

  • Fan, K., & Hung, T. (2014). A novel local pattern descriptor—Local vector pattern in high-order derivative space for face recognition. IEEE Transactions on Image Processing, 23(7), 2877–2891.

    Article  MathSciNet  MATH  Google Scholar 

  • Fan, R., Chang, K., Hsieh, C., Wang, X., & Lin, C. (2008). LIBLINEAR: A library for large linear classification. JMLR, 9, 1871–1874.

    MATH  Google Scholar 

  • Fazekas, S., & Chetverikov, D. (2007). Analysis and performance evaluation of optical flow features for dynamic texture recognition. Signal Processing: Image Communication, 22(7–8), 680–691.

    Google Scholar 

  • Ghanem, B., & Ahuja, N. (2010). Maximum margin distance learning for dynamic texture recognition. In K. Daniilidis, P. Maragos, N. Paragios (Eds.), ECCV, LNCS, Vol. 6312, pp. 223–236.

  • Gnouma, M., Ejbali, R., & Zaied, M. (2018). Abnormal events’ detection in crowded scenes. Multimedia Tools and Applications, 77(19), 24843–24864.

    Article  Google Scholar 

  • Guo, Z., Zhang, L., & Zhang, D. (2010). A completed modeling of local binary pattern operator for texture classification. IEEE Transactions on Image Processing, 19(6), 1657–1663.

    Article  MathSciNet  MATH  Google Scholar 

  • Hoang, V., & Jo, K. (2016). Joint components based pedestrian detection in crowded scenes using extended feature descriptors. Neurocomputing, 188, 139–150.

    Article  Google Scholar 

  • Hong, S., Ryu, J., Im, W., & Yang, H. S. (2018). D3: Recognizing dynamic scenes with deep dual descriptor based on key frames and key segments. Neurocomputing, 273, 611–621.

    Article  Google Scholar 

  • Hong, S., Ryu, J., & Yang, H. S. (2018). Not all frames are equal: Aggregating salient features for dynamic texture classification. Multidimensional Systems and Signal Processing, 29(1), 279–298.

    Article  MathSciNet  Google Scholar 

  • Ji, H., Yang, X., Ling, H., & Xu, Y. (2013). Wavelet domain multifractal analysis for static and dynamic texture classification. IEEE Transactions on Image Processing, 22(1), 286–299.

    Article  MathSciNet  MATH  Google Scholar 

  • Jin, H., Liu, Q., Lu, H., & Tong, X. (2004). Face detection using improved LBP under bayesian framework. In ICIG, pp. 306–309.

  • Lovell, A. C., Baktashmotlagh, M., Harandi, M., Lovell, B. C., & Salzmann, M. (2014). Discriminative non-linear stationary subspace analysis for video classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(12), 2353–2366.

    Article  Google Scholar 

  • Lu, Z., Xie, W., Pei, J., & Huang, J. (2005). Dynamic texture recognition by spatio-temporal multiresolution histograms. In WACV/MOTION, pp. 241–246.

  • Mäenpää, T., & Pietikäinen, M. (2003). Multi-scale binary patterns for texture analysis. In SCIA, pp. 885–892.

  • Mandelbrot, B. (1977). Fractal geometry of nature. W. H. Freeman.

  • Mumtaz, A., Coviello, E., Lanckriet, G. R. G., & Chan, A. B. (2013). Clustering dynamic textures with the hierarchical EM algorithm for modeling video. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(7), 1606–1621.

    Article  Google Scholar 

  • Mumtaz, A., Coviello, E., Lanckriet, G. R. G., & Chan, A. B. (2015). A scalable and accurate descriptor for dynamic textures using bag of system trees. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(4), 697–712.

    Article  Google Scholar 

  • Nakahata, M. T., Thomaz, L. A., da Silva, A. F., da Silva, E. A. B., & Netto, S. L. (2018). Anomaly detection with a moving camera using spatio-temporal codebooks. Multidimensional Systems and Signal Processing, 29(3), 1025–1054.

    Article  MathSciNet  MATH  Google Scholar 

  • Nguyen, T. P., Manzanera, A., Garrigues, M., & Vu, N. (2014). Spatial motion patterns: Action models from semi-dense trajectories. IJPRAI, 28(7), 1460011.

    Google Scholar 

  • Nguyen, T. P., Manzanera, A., Kropatsch, W. G., & N’Guyen, X. S. (2016). Topological attribute patterns for texture recognition. Pattern Recognition Letters, 80, 91–97.

    Article  Google Scholar 

  • Nguyen, T. P., Vu, N., & Manzanera, A. (2016). Statistical binary patterns for rotational invariant texture classification. Neurocomputing, 173, 1565–1577.

    Article  Google Scholar 

  • Nguyen, T. T., Nguyen, T. P., & Bouchara, F. (2017). Completed local structure patterns on three orthogonal planes for dynamic texture recognition. In IPTA, pp. 1–6.

  • Nguyen, T. T., Nguyen, T. P., & Bouchara, F. (2018). Completed statistical adaptive patterns on three orthogonal planes for recognition of dynamic textures and scenes. Journal of Electronic Imaging, 27(05), 053044.

    Article  Google Scholar 

  • Nguyen, T. T., Nguyen, T. P., & Bouchara, F. (2019). Smooth-invariant gaussian features for dynamic texture recognition. In ICIP, pp. 4400–4404.

  • Nguyen, T. T., Nguyen, T. P., & Bouchara, F. (2020a). Dynamic texture representation based on hierarchical local patterns. In ACIVS, pp. 277–289.

  • Nguyen, T. T., Nguyen, T. P., & Bouchara, F. (2020b). Directional dense-trajectory-based patterns for dynamic texture recognition. IET Computer Vision,14(4), 162–176.

  • Nguyen, T. T., Nguyen, T. P., & Bouchara, F. (2020c). Rubik gaussian-based patterns for dynamic texture classification. Pattern Recognition Letters,135, 180–187.

  • Nguyen, T. T., Nguyen, T. P., & Bouchara, F. (2021). Prominent local representation for dynamic textures based on high-order gaussian-gradients. IEEE Transactions on Multimedia, 23, 1367–1382.

    Article  Google Scholar 

  • Nguyen, T. T., Nguyen, T. P., Bouchara, F., & Nguyen, X. S. (2018). Directional beams of dense trajectories for dynamic texture recognition. In J. Blanc-Talon, D. Helbert, W. Philips, D. Popescu, P. Scheunders (Eds.), ACIVS, pp. 74–86.

  • Nguyen, T. T., Nguyen, T. P., Bouchara, F., & Nguyen, X. S. (2020d). Momental directional patterns for dynamic texture recognition. CVIU,194, 102882.

  • Nguyen, T. T., Nguyen, T. P., Bouchara, F., & Vu, N. (2019). Volumes of blurred-invariant gaussians for dynamic texture classification. In M. Vento, G. Percannella (Eds.), CAIP, pp. 155–167.

  • Nguyen, X. S., Nguyen, T. P., Charpillet, F., & Vu, N. S. (2018). Local derivative pattern for action recognition in depth images. Multimedia Tools and Applications, 77(7), 8531–8549.

    Article  Google Scholar 

  • Ojala, T., Pietikäinen, M., & Mäenpää, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(7), 971–987.

    Article  MATH  Google Scholar 

  • Ortego, D., SanMiguel, J. C., & Martínez, J. M. (2017). Stand-alone quality estimation of background subtraction algorithms. CVIU, 162, 87–102.

    Google Scholar 

  • Peh, C., & Cheong, L. F. (2002). Synergizing spatial and temporal texture. IEEE Transactions on Image Processing, 11(10), 1179–1191.

    Article  MathSciNet  Google Scholar 

  • Péteri, R., & Chetverikov, D. (2004). Qualitative characterization of dynamic textures for video retrieval. In K. W. Wojciechowski, B. Smolka, H. Palus, R. Kozera, W. Skarbek, L. Noakes (Eds.), ICCVG, computational imaging and vision, Vol. 32, pp. 33–38.

  • Péteri, R., & Chetverikov, D. (2005). Dynamic texture recognition using normal flow and texture regularity. In J. S. Marques, N. P. de la Blanca, & P. Pina (Eds.), IbPRIA, LNCS, Vol. 3523, pp. 223–230.

  • Péteri, R., Fazekas, S., & Huiskes, M. J. (2010). Dyntex: A comprehensive database of dynamic textures. Pattern Recognition Letters, 31(12), 1627–1632.

    Article  Google Scholar 

  • Qi, X., Li, C. G., Zhao, G., Hong, X., & Pietikäinen, M. (2016). Dynamic texture and scene classification by transferring deep image features. Neurocomputing, 171, 1230–1241.

    Article  Google Scholar 

  • Quan, Y., Bao, C., & Ji, H. (2016). Equiangular kernel dictionary learning with applications to dynamic texture analysis. In CVPR, pp. 308–316.

  • Quan, Y., Huang, Y., & Ji, H. (2015). Dynamic texture recognition via orthogonal tensor dictionary learning. In ICCV, pp. 73–81.

  • Quan, Y., Sun, Y., & Xu, Y. (2017). Spatiotemporal lacunarity spectrum for dynamic texture classification. CVIU, 165, 85–96.

    Google Scholar 

  • Rajasekar, M., Kavida, A. C., & Bennet, M. A. (2020). A pattern analysis based underwater video segmentation system for target object detection. Multidimensional Systems and Signal Processing, 31(4), 1579–1602.

    Article  Google Scholar 

  • Ranganath, A., Senapati, M. R., & Sahu, P. K. (2020). Estimating the fractal dimension of images using pixel range calculation technique. The Visual Computer, 37, 635–650.

    Article  Google Scholar 

  • Ravichandran, A., Chaudhry, R., & Vidal, R. (2009). View-invariant dynamic texture recognition using a bag of dynamical systems. In CVPR, pp. 1651–1657.

  • Ren, J., Jiang, X., & Yuan, J. (2013). Dynamic texture recognition using enhanced LBP features. In ICASSP, pp. 2400–2404.

  • Ren, J., Jiang, X., Yuan, J., & Wang, G. (2014). Optimizing LBP structure for visual recognition using binary quadratic programming. SPL, 21(11), 1346–1350.

    Google Scholar 

  • Ren, J., Xu, M., Smith, J. S., & Cheng, S. (2016). Multi-view and multi-plane data fusion for effective pedestrian detection in intelligent visual surveillance. Multidimensional Systems and Signal Processing, 27(4), 1007–1029.

    Article  MathSciNet  MATH  Google Scholar 

  • Rivera, A. R., & Chae, O. (2015). Spatiotemporal directional number transitional graph for dynamic texture recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(10), 2146–2152.

    Article  Google Scholar 

  • Saisan, P., Doretto, G., Wu, Y. N., & Soatto, S. (2001). Dynamic texture recognition. In CVPR, pp. 58–63

  • Shrivastava, N., & Tyagi, V. (2014). An effective scheme for image texture classification based on binary local structure pattern. The Visual Computer, 30(11), 1223–1232.

    Article  Google Scholar 

  • Tabatabaei, S. M., & Chalechale, A. (2020). Noise-tolerant texture feature extraction through directional thresholded local binary pattern. The Visual Computer, 36(5), 967–987.

    Article  Google Scholar 

  • Tiwari, D., & Tyagi, V. (2016a). Dynamic texture recognition based on completed volume local binary pattern. Multidimensional Systems and Signal Processing, 27(2), 563–575.

  • Tiwari, D., & Tyagi, V. (2016b). A novel scheme based on local binary pattern for dynamic texture recognition. CVIU, 150, 58–65.

  • Tiwari, D., & Tyagi, V. (2017a). Dynamic texture recognition using multiresolution edge-weighted local structure pattern. Computers & Electrical Engineering, 62, 485–498.

  • Tiwari, D., & Tyagi, V. (2017b). Improved weber’s law based local binary pattern for dynamic texture recognition. Multimedia Tools and Applications, 76(5), 6623–6640.

  • Vu, N., Nguyen, T. P., & Garcia, C. (2014). Improving texture categorization with biologically-inspired filtering. Image and Vision Computing, 32(6–7), 424–436.

    Article  Google Scholar 

  • Wang, L., Liu, H., & Sun, F. (2016). Dynamic texture video classification using extreme learning machine. Neurocomputing, 174, 278–285.

    Article  Google Scholar 

  • Wang, Y., & Hu, S. (2015). Exploiting high level feature for dynamic textures recognition. Neurocomputing, 154, 217–224.

    Article  Google Scholar 

  • Wang, Y., & Hu, S. (2016). Chaotic features for dynamic textures recognition. Soft Computing, 20(5), 1977–1989.

    Article  Google Scholar 

  • Wu, X., & Sun, J. (2017). Joint-scale LBP: A new feature descriptor for texture classification. The Visual Computer, 33(3), 317–329.

    Article  Google Scholar 

  • Xu, Y., Huang, S. B., Ji, H., & Fermüller, C. (2012). Scale-space texture description on sift-like textons. CVIU, 116(9), 999–1013.

    Google Scholar 

  • Xu, Y., Quan, Y., Ling, H., & Ji, H. (2011). Dynamic texture classification using dynamic fractal analysis. In ICCV, pp. 1219–1226.

  • Xu, Y., Quan, Y., Zhang, Z., Ling, H., & Ji, H. (2015). Classifying dynamic textures via spatiotemporal fractal analysis. Pattern Recognition, 48(10), 3239–3248.

    Article  Google Scholar 

  • Zeng, Z., Jia, J., Zhu, Z., & Yu, D. (2016). Adaptive maintenance scheme for codebook-based dynamic background subtraction. CVIU, 152, 58–66.

    Google Scholar 

  • Zhang, B., Gao, Y., Zhao, S., & Liu, J. (2010). Local derivative pattern versus local binary pattern: Face recognition with high-order local pattern descriptor. IEEE Transactions on Image Processing, 19(2), 533–544.

    Article  MathSciNet  MATH  Google Scholar 

  • Zhao, G., Ahonen, T., Matas, J., & Pietikäinen, M. (2012). Rotation-invariant image and video description with local binary pattern features. IEEE Transactions on Image Processing, 21(4), 1465–1477.

    Article  MathSciNet  MATH  Google Scholar 

  • Zhao, G., & Pietikäinen, M. (2007). Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(6), 915–928.

    Article  Google Scholar 

  • Zhao, X., Lin, Y., & Heikkilä, J. (2018). Dynamic texture recognition using volume local binary count patterns with an application to 2d face spoofing detection. IEEE Transactions on Multimedia, 20(3), 552–566.

    Article  Google Scholar 

  • Zhao, X., Lin, Y., Liu, L., Heikkilä, J., & Zheng, W. (2019). Dynamic texture classification using unsupervised 3d filter learning and local binary encoding. IEEE Transactions on Multimedia, 21(7), 1694–1708.

    Article  Google Scholar 

  • Zhao, Y., Huang, D. S., & Jia, W. (2012). Completed local binary count for rotation invariant texture classification. IEEE Transactions on Image Processing, 21(10), 4492–4497.

    Article  MathSciNet  MATH  Google Scholar 

Download references

Acknowledgements

We would like to express our sincere appreciation to the editors and reviewers, who granted us the insightful and valuable comments to clarify the presentation of this work. Also, we are so grateful for those in HCMC University of Technology and Education, Faculty of IT, Thu Duc City, Ho Chi Minh City, Vietnam, who gave us crucial supports.

Author information

Authors and Affiliations

  1. Université de Toulon, Aix Marseille Univ, CNRS, LIS, Marseille, France

    Thanh Tuan Nguyen, Thanh Phuong Nguyen & Frédéric Bouchara

  2. HCMC University of Technology and Education, Faculty of IT, Thu Duc City, Ho Chi Minh City, Vietnam

    Thanh Tuan Nguyen

Authors
  1. Thanh Tuan Nguyen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Thanh Phuong Nguyen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Frédéric Bouchara
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Thanh Phuong Nguyen.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Nguyen, T.T., Nguyen, T.P. & Bouchara, F. Dynamic texture description using adapted bipolar-invariant and blurred features. Multidim Syst Sign Process 33, 945–979 (2022). https://doi.org/10.1007/s11045-022-00826-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11045-022-00826-y

Keywords

Search

Navigation