A Comprehensive Taxonomy of Dynamic Texture Representation

Nguyen-Thanh, Tuan; Phuong, NguyenThanh

doi:10.1145/3487892

Cited by 4 publications

(2 citation statements)

References 211 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DT description has been studied for over two decades and plenty of DT description methods have been reported. According to the recently published survey on DT representation [11], DT description approaches can be roughly arranged into six categories: optical-flow-based, modelbased, geometry-based, filter-based, local-feature-based, and learning-based. The proposed method belongs to the last category.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Texture Classification Using Directional Binarized Random Features

Zhao

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Dynamic texture description has been studied extensively due to its wide applications in the field of computer vision. Local binary pattern (LBP) and its various variants account for a large part of dynamic texture description methods because of its advantages, such as good discriminability and low computational complexity. However, many LBP-based methods directly extract feature from pixel intensities and only use a proportion of pixels in a local neighborhood. And their good classification performance is usually achieved at the cost of high feature dimensionality, which would limit their application scenarios. We argue that extracting features from the gradient domain will capture more discriminative features due to the additional directional information, and that making use of all the pixels in a local neighborhood would improve performance. In this paper, we propose a simply but effective dynamic texture descriptor that inherits the advantages of LBP while excluding its disadvantages. The proposed method consists of four stages of data processing: 1) gradients extraction; 2) random feature extraction from gradients; 3) binary hashing of directional random features; and 4) histogramming. Gaussian first-order derivatives are used as gradient filters such that stable gradients could be generated. Then random projection is applied to extract random features from each gradients. Both the above two stages are conducted via 3D filtering, and thus they are efficient. Thirdly, the random features from each gradient are binarized and encoded into integer codes, from which a histogram is built. Finally, the histograms from each gradient are concatenated into a feature vector. Because we use 8-bit codes, The feature dimensionality is very low. We evaluate the proposed method on three benchmark dynamic texture datasets with various test protocols. The results demonstrate its effectiveness and efficiency when comparing to many state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

“…To conduct effective DT classification, DTs must be processed and encoded into feature vectors which can be used for classification. However, DT description is not an easy task [11]. Spatial appearance in a DT would be affected by changes of illumination, viewpoint, scale, and rotation.…”

Section: Introductionmentioning

confidence: 99%