Convolutional Neural Network on Three Orthogonal Planes for Dynamic Texture Classification

TL;DR

This paper introduces a novel CNN-based method for dynamic texture classification that analyzes three orthogonal planes of video data, demonstrating superior performance on benchmark datasets.

Contribution

The paper presents a new CNN approach applying on three orthogonal planes for dynamic texture analysis, improving classification accuracy over existing methods.

Findings

Achieved significant accuracy improvements on benchmark datasets.

Demonstrated robustness and effectiveness of the three-plane CNN approach.

Outperformed state-of-the-art methods on larger datasets.

Abstract

Dynamic Textures (DTs) are sequences of images of moving scenes that exhibit certain stationarity properties in time such as smoke, vegetation and fire. The analysis of DT is important for recognition, segmentation, synthesis or retrieval for a range of applications including surveillance, medical imaging and remote sensing. Deep learning methods have shown impressive results and are now the new state of the art for a wide range of computer vision tasks including image and video recognition and segmentation. In particular, Convolutional Neural Networks (CNNs) have recently proven to be well suited for texture analysis with a design similar to a filter bank approach. In this paper, we develop a new approach to DT analysis based on a CNN method applied on three orthogonal planes x y , xt and y t . We train CNNs on spatial frames and temporal slices extracted from the DT sequences and combine their outputs to obtain a competitive DT classifier. Our results on a wide range of commonly used DT classification benchmark datasets prove the robustness of our approach. Significant improvement of the state of the art is shown on the larger datasets.