Convolutional neural network on three orthogonal planes for dynamic texture classification. (April 2018)

• Record Type: Journal Article
• Authors: Andrearczyk, Vincent; Whelan, Paul F.
• Is Part Of: Pattern recognition. Volume 76(2018:Apr.)
• Page Start: 36
• Page End: 49
• Publication Date: 2018-04
• Subjects: Dynamic texture -- Image recognition -- Convolutional neural network -- Filter banks -- Spatiotemporal analysis; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2017.10.030
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A new CNN framework is introduced to analyze DTs on three orthogonal planes. Multiple texture specific CNNs are developed. An analysis of the contribution of each plane is conducted as well as the domain transferability. Experiments on various DT classification datasets show the superiority of our approach over existing ones. 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. Convolutional Neural Networks (CNNs) have recently proven to be well suited for texture analysis with a design similar to filter banks. We develop a new DT analysis method based on a CNN method applied on three orthogonal planes. We train CNNs on spatial frames and temporal slices extracted from the DT sequences and combine their outputs to obtain a competitive DT classifier trained end-to-end. 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.