Dynamic texture-based scene classification using Deep Belief Networks

Dynamic Textures (DTs) are sequences of images that exhibit stationarity properties in time such as waves, fire, and water fountain. In particular, DTs for scene classification are fundamental to understanding natural video content. However, the extraction of robust and powerful features is a crucial step towards solving these tasks. In this paper, we suggested a novel approach to extracting and learning texture features from natural scenes. First, we model the textures using Local Binary Patterns on Three Orthogonal Planes (LBP-TOP) as well as Volume Local Binary Patterns (VLBP) respectively. Thereafter, we use those descriptors for training Deep Belief Networks (DBNs) to perform the scene classification. Our experimental results on a wide range of commonly used DTs classification benchmark datasets, including Dyntex++ and UCLA prove the robustness of our approach.

[1]  Paul F. Whelan,et al.  Convolutional neural network on three orthogonal planes for dynamic texture classification , 2017, Pattern Recognit..

[2]  Fuchun Sun,et al.  Dynamic texture video classification using extreme learning machine , 2016, Neurocomputing.

[3]  Vipin Tyagi,et al.  Dynamic texture recognition based on completed volume local binary pattern , 2016, Multidimens. Syst. Signal Process..

[4]  Matti Pietikäinen,et al.  Dynamic Texture Recognition Using Volume Local Binary Patterns , 2006, WDV.

[5]  Subhransu Maji,et al.  Bilinear CNN Models for Fine-Grained Visual Recognition , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[6]  Subhransu Maji,et al.  Deep filter banks for texture recognition and segmentation , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Marko Heikkilä,et al.  A Texture-based Method for Detecting Moving Objects , 2004, BMVC.

[8]  Hao Su,et al.  Objects as Attributes for Scene Classification , 2010, ECCV Workshops.

[9]  Subhransu Maji,et al.  Visualizing and Understanding Deep Texture Representations , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Ling Shao,et al.  Learning Object-to-Class Kernels for Scene Classification , 2014, IEEE Transactions on Image Processing.

[11]  Matti Pietikäinen,et al.  Human Activity Recognition Using a Dynamic Texture Based Method , 2008, BMVC.

[12]  El-Houssine Bouyakhf,et al.  Discriminative Deep Belief Network for Indoor Environment Classification Using Global Visual Features , 2017, Cognitive Computation.

[13]  Xuelong Li,et al.  Biologically Inspired Features for Scene Classification in Video Surveillance , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[14]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[15]  Sangram Ganguly,et al.  A theoretical analysis of Deep Neural Networks for texture classification , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[16]  Stefano Soatto,et al.  Dynamic Textures , 2003, International Journal of Computer Vision.

[17]  M. Giger,et al.  Volumetric texture analysis of breast lesions on contrast‐enhanced magnetic resonance images , 2007, Magnetic resonance in medicine.

[18]  Matti Pietikäinen,et al.  Dynamic texture and scene classification by transferring deep image features , 2015, Neurocomputing.

[19]  Matti Pietikäinen,et al.  Local Binary Pattern Descriptors for Dynamic Texture Recognition , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[20]  Andrew Zisserman,et al.  Scene Classification Via pLSA , 2006, ECCV.

[21]  Matti Pietikäinen,et al.  Local Binary Patterns for Still Images , 2011 .

[22]  Paul Smolensky,et al.  Information processing in dynamical systems: foundations of harmony theory , 1986 .

[23]  Subhransu Maji,et al.  Deep convolutional filter banks for texture recognition and segmentation , 2014, ArXiv.

[24]  Narendra Ahuja,et al.  Maximum Margin Distance Learning for Dynamic Texture Recognition , 2010, ECCV.

[25]  Yin Chen,et al.  Orthogonal combination of local binary patterns for dynamic texture recognition , 2015, International Symposium on Multispectral Image Processing and Pattern Recognition.