Dynamic Texture Representation Based on Hierarchical Local Patterns

Nguyen, Thanh Tuan; Nguyễn, Thanh Phương; Bouchara, Frédéric

doi:10.1007/978-3-030-40605-9_24

Cited by 12 publications

(5 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed method achieves a rate of 99.50% on UCLA 50-class breakdown with LOO scheme. It is on par with MBSIF-TOP [16], MPCAF-TOP [20], FoSIG [63], V-BIG [64], CSAP-TOP [72], HILOP [73], B3DF_SMC [22], and ICFV [24]. Among these methods, MPCAF-TOP is a filter-learning-based multi-scale descriptor and ICFV involves two learning processes of filter learning and codebook construction, while our method is learning-free and thus has no dependence on data.…”

Section: ) Results On the Ucla Datasetmentioning

confidence: 96%

“…A relatively good result of 95.18% is provided by our DBRF on this dataset. It is slightly outperformed by ASF-TOP [17], MBSIF-TOP [16], MPCAF-TOP [20], FoSIG [63], V-BIG [64], HoGF 2D [25], HoGF 3D [25], DoDGF 2D [65], DoDGF 3D [65], DDLBP [66], novel LBP [18], MEWLSP [78], HILOP [73], MEMDP [76], RUBIG [74], B3DF_SMC [22], ICFV [24], and DT-RNNs [91] by 0.22%, 1.99%, 1.34%, 0.81%, 1.47%, 2.01%, 2.45%, 1.96%, 2.34%, 0.62%, 1.1%, 3.3%, 1.03%, 0.85%, 1.9%, 0.4%, and 1.33%, respectively. Despite the fact that many of these methods use SVM classifier, we think it is unworthy to significantly increase complexity and feature dimensionality for marginal performance improvement.…”

Section: ) Results On the Dyntex++ Datasetmentioning

confidence: 99%

“…Later, they further extended CLSP and proposed the complete statistical adaptive pattern (CSAP-TOP) [72]. In 2020, they proposed three other methods: (1) hierarchical local pattern [73],…”

Section: E Local-feature-based Methodsmentioning

confidence: 99%

See 2 more Smart Citations

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: ) Results On the Ucla Datasetmentioning

confidence: 96%

Section: ) Results On the Dyntex++ Datasetmentioning

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

show abstract

“…The dynamic texture segmentation system was proposed by Paygude and Vyas [14] based on local and global spatiotemporal techniques. Dynamic texture representation was proposed by Nguyen et al [15] based on hierarchical local patterns.…”

Section: System Overviewmentioning

confidence: 99%

An Early Flame Detection System Based on Image Block Threshold Selection Using Knowledge of Local and Global Feature Analysis

et al. 2020

View full text Add to dashboard Cite

Fire is one of the mutable hazards that damage properties and destroy forests. Many researchers are involved in early warning systems, which considerably minimize the consequences of fire damage. However, many existing image-based fire detection systems can perform well in a particular field. A general framework is proposed in this paper which works on realistic conditions. This approach filters out image blocks based on thresholds of different temporal and spatial features, starting with dividing the image into blocks and extraction of flames blocks from image foreground and background, and candidates blocks are analyzed to identify local features of color, source immobility, and flame flickering. Each local feature filter resolves different false-positive fire cases. Filtered blocks are further analyzed by global analysis to extract flame texture and flame reflection in surrounding blocks. Sequences of successful detections are buffered by a decision alarm system to reduce errors due to external camera influences. Research algorithms have low computation time. Through a sequence of experiments, the result is consistent with the empirical evidence and shows that the detection rate of the proposed system exceeds previous studies and reduces false alarm rates under various environments.

show abstract

“…[20] nominated Local Binary Pattern (LBP) [21] for analyzing videos in two ways: VLBP patterns, which are structured from three consecutive frames of a sequence, and LBP-TOP patterns from three orthogonal planes. After that, some works proposed various schemes to enhance the distinguishing power by dealing with limitations of the typical LBPs in DT encoding such as problems of rotation-invariant [22], near-uniform regions, and sensitivity to noise [23,24,25,26].…”

Section: Introductionmentioning

confidence: 99%

Rubik Gaussian-based patterns for dynamic texture classification

Nguyen

Nguyễn

Bouchara

2020

Pattern Recognition Letters

Self Cite

View full text Add to dashboard Cite

Illumination, noise, and changes of environments, scales negatively impact on encoding chaotic motions for dynamic texture (DT) representation. This paper proposes a new method to overcome those issues by addressing the following novel concepts. First, different Gaussian-based kernels are taken into account as an effective filtered pre-processing with low computational cost to point out robust and invariant features. Second, a discriminative operator, named Local Rubik-based Pattern (LRP), is introduced to adequately capture both shape and motion cues of DTs by proposing a new concept of complemented components together with an effective encoding method. In addition, it also addresses a novel thresholding to take into account rich spatio-temporal relationships extracted from a new model of neighborhood supporting region. Finally, an efficient framework for DT description is presented by exploiting operator LRP for encoding various instances of Gaussian-based volumes in order to form a robust descriptor against noise, changes of illumination, scale, and environment. Experiments for DT classification on benchmark datasets have authenticated the interest of our proposal.

show abstract

Dynamic Texture Representation Based on Hierarchical Local Patterns

Cited by 12 publications

References 42 publications

Dynamic Texture Classification Using Directional Binarized Random Features

Dynamic Texture Classification Using Directional Binarized Random Features

An Early Flame Detection System Based on Image Block Threshold Selection Using Knowledge of Local and Global Feature Analysis

Rubik Gaussian-based patterns for dynamic texture classification

Contact Info

Product

Resources

About