Prominent Local Representation for Dynamic Textures Based on High-Order Gaussian-Gradients

Understanding dynamic textures (DTs) is a challenge in various computer vision applications due to the negative impacts of noise, changes of environment, illumination, and scales on capturing turbulent characteristics. In this work, we propose an efficient shallow framework for DT representation by addressing the following novel concepts. First, it is the first time in DT analysis that 2D/3D Gaussian-gradient filterings are taken into account as a pre-processing step to point out robust components against those influences in effect. Second, high-order partial derivatives of the Gaussian kernels and their informative magnitudes are exploited to forcefully capture multi-order Gaussian-gradient features. Third, these gradient kernels are investigated in multiscale analysis of different orders and standard deviations in order to enrich more useful scale-gradient information. Finally, the obtained complementary components are shallowly encoded using a simple local operator to construct robust descriptors of Highorder 2D/3D Gaussian-gradient-based Features (HoGF2D/3D) against the well-known issues of DT description. Experiments for DTclassification on various benchmarks have validated the interest of our approach since its performance is comparable to state-of-theart results, including that of deep-learning methods, while it only has a small dimension.