Dynamic Texture Recognition using PDV Hashing and Dictionary Learning on Multi-scale Volume Local Binary Pattern

TL;DR

This paper introduces a novel method for dynamic texture recognition that uses PDV hashing and dictionary learning on multi-scale volume local binary patterns to effectively handle high-dimensional data and improve recognition accuracy.

Contribution

It proposes a new encoding scheme that maps pixel difference vectors to binary vectors and dictionaries, enabling larger neighborhood analysis without high-dimensional feature issues.

Findings

Outperforms state-of-the-art methods on DynTex++ and UCLA datasets.

Effectively captures discriminant information from larger video neighborhoods.

Reduces dimensionality while maintaining recognition accuracy.

Abstract

Spatial-temporal local binary pattern (STLBP) has been widely used in dynamic texture recognition. STLBP often encounters the high-dimension problem as its dimension increases exponentially, so that STLBP could only utilize a small neighborhood. To tackle this problem, we propose a method for dynamic texture recognition using PDV hashing and dictionary learning on multi-scale volume local binary pattern (PHD-MVLBP). Instead of forming very high-dimensional LBP histogram features, it first uses hash functions to map the pixel difference vectors (PDVs) to binary vectors, then forms a dictionary using the derived binary vector, and encodes them using the derived dictionary. In such a way, the PDVs are mapped to feature vectors of the size of dictionary, instead of LBP histograms of very high dimension. Such an encoding scheme could extract the discriminant information from videos in a much larger neighborhood effectively. The experimental results on two widely-used dynamic textures datasets, DynTex++ and UCLA, show the superiority performance of the proposed approach over the state-of-the-art methods.