Directional dense‐trajectory‐based patterns for dynamic texture recognition
Representation of dynamic textures (DTs), well‐known as a sequence of moving textures, is a challenging problem in video analysis due to the disorientation of motion features. Analysing DTs to make them ‘understandable’ plays an important role in different applications of computer vision. In this st...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-06-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2019.0455 |
| _version_ | 1797684631813750784 |
|---|---|
| author | Thanh Tuan Nguyen Thanh Phuong Nguyen Frédéric Bouchara |
| author_facet | Thanh Tuan Nguyen Thanh Phuong Nguyen Frédéric Bouchara |
| author_sort | Thanh Tuan Nguyen |
| collection | DOAJ |
| description | Representation of dynamic textures (DTs), well‐known as a sequence of moving textures, is a challenging problem in video analysis due to the disorientation of motion features. Analysing DTs to make them ‘understandable’ plays an important role in different applications of computer vision. In this study, an efficient approach for DT description is proposed by addressing the following novel concepts. First, the beneficial properties of dense trajectories are exploited for the first time to efficiently describe DTs instead of the whole video. Second, two substantial extensions of local vector pattern operator are introduced to form a completed model which is based on complemented components to enhance its performance in encoding directional features of motion points in a trajectory. Finally, the authors present a new framework, called directional dense trajectory patterns, which takes advantage of directional beams of dense trajectories along with spatio‐temporal features of their motion points in order to construct dense‐trajectory‐based descriptors with more robustness. Evaluations of DT recognition on different benchmark datasets (i.e. UCLA, DynTex, and DynTex++) have verified the interest of the authors’ proposal. |
| first_indexed | 2024-03-12T00:32:31Z |
| format | Article |
| id | doaj.art-c7d2e6e652b34c23a8722b1bf3e2ae7f |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:32:31Z |
| publishDate | 2020-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-c7d2e6e652b34c23a8722b1bf3e2ae7f2023-09-15T10:11:45ZengWileyIET Computer Vision1751-96321751-96402020-06-0114416217610.1049/iet-cvi.2019.0455Directional dense‐trajectory‐based patterns for dynamic texture recognitionThanh Tuan Nguyen0Thanh Phuong Nguyen1Frédéric Bouchara2CNRS, LIS, Aix Marseille Université, Université de ToulonMarseilleFranceCNRS, LIS, Aix Marseille Université, Université de ToulonMarseilleFranceCNRS, LIS, Aix Marseille Université, Université de ToulonMarseilleFranceRepresentation of dynamic textures (DTs), well‐known as a sequence of moving textures, is a challenging problem in video analysis due to the disorientation of motion features. Analysing DTs to make them ‘understandable’ plays an important role in different applications of computer vision. In this study, an efficient approach for DT description is proposed by addressing the following novel concepts. First, the beneficial properties of dense trajectories are exploited for the first time to efficiently describe DTs instead of the whole video. Second, two substantial extensions of local vector pattern operator are introduced to form a completed model which is based on complemented components to enhance its performance in encoding directional features of motion points in a trajectory. Finally, the authors present a new framework, called directional dense trajectory patterns, which takes advantage of directional beams of dense trajectories along with spatio‐temporal features of their motion points in order to construct dense‐trajectory‐based descriptors with more robustness. Evaluations of DT recognition on different benchmark datasets (i.e. UCLA, DynTex, and DynTex++) have verified the interest of the authors’ proposal.https://doi.org/10.1049/iet-cvi.2019.0455dense trajectoriesspatio-temporal featuresmotion pointsdense-trajectory-based descriptorsDT recognitiondirectional dense-trajectory-based patterns |
| spellingShingle | Thanh Tuan Nguyen Thanh Phuong Nguyen Frédéric Bouchara Directional dense‐trajectory‐based patterns for dynamic texture recognition IET Computer Vision dense trajectories spatio-temporal features motion points dense-trajectory-based descriptors DT recognition directional dense-trajectory-based patterns |
| title | Directional dense‐trajectory‐based patterns for dynamic texture recognition |
| title_full | Directional dense‐trajectory‐based patterns for dynamic texture recognition |
| title_fullStr | Directional dense‐trajectory‐based patterns for dynamic texture recognition |
| title_full_unstemmed | Directional dense‐trajectory‐based patterns for dynamic texture recognition |
| title_short | Directional dense‐trajectory‐based patterns for dynamic texture recognition |
| title_sort | directional dense trajectory based patterns for dynamic texture recognition |
| topic | dense trajectories spatio-temporal features motion points dense-trajectory-based descriptors DT recognition directional dense-trajectory-based patterns |
| url | https://doi.org/10.1049/iet-cvi.2019.0455 |
| work_keys_str_mv | AT thanhtuannguyen directionaldensetrajectorybasedpatternsfordynamictexturerecognition AT thanhphuongnguyen directionaldensetrajectorybasedpatternsfordynamictexturerecognition AT fredericbouchara directionaldensetrajectorybasedpatternsfordynamictexturerecognition |