Orthogonal object proposal and its application
In this study, the authors propose an object proposal algorithm that can accurately propose object candidate regions at each frame, despite noise in a video. Accordingly, they define three orthogonal planes, namely vertical–horizontal, temporal–vertical, and temporal–horizontal planes. As these plan...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-06-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2018.5346 |
| _version_ | 1827817480529117184 |
|---|---|
| author | Sung Woo Park Junseok Kwon |
| author_facet | Sung Woo Park Junseok Kwon |
| author_sort | Sung Woo Park |
| collection | DOAJ |
| description | In this study, the authors propose an object proposal algorithm that can accurately propose object candidate regions at each frame, despite noise in a video. Accordingly, they define three orthogonal planes, namely vertical–horizontal, temporal–vertical, and temporal–horizontal planes. As these planes are orthogonal, they are the most compact planes that can span the spatiotemporal space of a video. Their algorithm selects good object proposals for the vertical–horizontal plane with the help of the object proposal results of the other planes. Experimental results demonstrate that the proposed algorithm produces better object proposals than the baseline algorithm and other state‐of‐the‐art methods. In particular, their method provides more accurate object proposals in challenging environments with severe noise and background clutter. In addition, the object proposal results are utilised for visual tracking problems, and the experimental results show that their visual tracker outperforms recent deep‐learning‐based trackers. |
| first_indexed | 2024-03-12T00:34:49Z |
| format | Article |
| id | doaj.art-118f89f3d5a04dc39f347b2935879dd0 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:34:49Z |
| publishDate | 2019-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-118f89f3d5a04dc39f347b2935879dd02023-09-15T09:56:28ZengWileyIET Computer Vision1751-96321751-96402019-06-0113442042710.1049/iet-cvi.2018.5346Orthogonal object proposal and its applicationSung Woo Park0Junseok Kwon1School of Computer Science and EngineeringChung‐Ang UniversitySeoulRepublic of KoreaSchool of Computer Science and EngineeringChung‐Ang UniversitySeoulRepublic of KoreaIn this study, the authors propose an object proposal algorithm that can accurately propose object candidate regions at each frame, despite noise in a video. Accordingly, they define three orthogonal planes, namely vertical–horizontal, temporal–vertical, and temporal–horizontal planes. As these planes are orthogonal, they are the most compact planes that can span the spatiotemporal space of a video. Their algorithm selects good object proposals for the vertical–horizontal plane with the help of the object proposal results of the other planes. Experimental results demonstrate that the proposed algorithm produces better object proposals than the baseline algorithm and other state‐of‐the‐art methods. In particular, their method provides more accurate object proposals in challenging environments with severe noise and background clutter. In addition, the object proposal results are utilised for visual tracking problems, and the experimental results show that their visual tracker outperforms recent deep‐learning‐based trackers.https://doi.org/10.1049/iet-cvi.2018.5346orthogonal object proposalorthogonal planestemporal–horizontal planesvertical–horizontal planevideotemporal–vertical planes |
| spellingShingle | Sung Woo Park Junseok Kwon Orthogonal object proposal and its application IET Computer Vision orthogonal object proposal orthogonal planes temporal–horizontal planes vertical–horizontal plane video temporal–vertical planes |
| title | Orthogonal object proposal and its application |
| title_full | Orthogonal object proposal and its application |
| title_fullStr | Orthogonal object proposal and its application |
| title_full_unstemmed | Orthogonal object proposal and its application |
| title_short | Orthogonal object proposal and its application |
| title_sort | orthogonal object proposal and its application |
| topic | orthogonal object proposal orthogonal planes temporal–horizontal planes vertical–horizontal plane video temporal–vertical planes |
| url | https://doi.org/10.1049/iet-cvi.2018.5346 |
| work_keys_str_mv | AT sungwoopark orthogonalobjectproposalanditsapplication AT junseokkwon orthogonalobjectproposalanditsapplication |