Depth order estimation for video frames using motion occlusions
This study proposes a system to estimate the depth order of regions belonging to a monocular image sequence. For each frame, the regions are ordered according to their relative depth using information from the previous and following frames. The algorithm estimates occlusions relying on a hierarchica...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2014-04-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2012.0287 |
| _version_ | 1797685261648265216 |
|---|---|
| author | Guillem Palou Philippe Salembier |
| author_facet | Guillem Palou Philippe Salembier |
| author_sort | Guillem Palou |
| collection | DOAJ |
| description | This study proposes a system to estimate the depth order of regions belonging to a monocular image sequence. For each frame, the regions are ordered according to their relative depth using information from the previous and following frames. The algorithm estimates occlusions relying on a hierarchical region‐based representation of the image by means of a binary tree. This representation is used to define the final depth order partition which is obtained through an energy minimisation process. Finally, to achieve a global and consistent depth ordering, a depth order graph is constructed and used to eliminate contradictory local cues. The system is evaluated and compared with the state‐of‐the‐art figure/ground labelling systems showing very good results. |
| first_indexed | 2024-03-12T00:41:37Z |
| format | Article |
| id | doaj.art-d2ea9998a382481db2c7b407daea9c68 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:41:37Z |
| publishDate | 2014-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-d2ea9998a382481db2c7b407daea9c682023-09-15T07:13:11ZengWileyIET Computer Vision1751-96321751-96402014-04-018215216010.1049/iet-cvi.2012.0287Depth order estimation for video frames using motion occlusionsGuillem Palou0Philippe Salembier1Department of Signal Theory and CommunicationsTechnical University of Catalonia (UPC)BarcelonaSpainDepartment of Signal Theory and CommunicationsTechnical University of Catalonia (UPC)BarcelonaSpainThis study proposes a system to estimate the depth order of regions belonging to a monocular image sequence. For each frame, the regions are ordered according to their relative depth using information from the previous and following frames. The algorithm estimates occlusions relying on a hierarchical region‐based representation of the image by means of a binary tree. This representation is used to define the final depth order partition which is obtained through an energy minimisation process. Finally, to achieve a global and consistent depth ordering, a depth order graph is constructed and used to eliminate contradictory local cues. The system is evaluated and compared with the state‐of‐the‐art figure/ground labelling systems showing very good results.https://doi.org/10.1049/iet-cvi.2012.0287video framesmotion occlusionsmonocular image sequencerelative depthhierarchical region-based representationbinary tree |
| spellingShingle | Guillem Palou Philippe Salembier Depth order estimation for video frames using motion occlusions IET Computer Vision video frames motion occlusions monocular image sequence relative depth hierarchical region-based representation binary tree |
| title | Depth order estimation for video frames using motion occlusions |
| title_full | Depth order estimation for video frames using motion occlusions |
| title_fullStr | Depth order estimation for video frames using motion occlusions |
| title_full_unstemmed | Depth order estimation for video frames using motion occlusions |
| title_short | Depth order estimation for video frames using motion occlusions |
| title_sort | depth order estimation for video frames using motion occlusions |
| topic | video frames motion occlusions monocular image sequence relative depth hierarchical region-based representation binary tree |
| url | https://doi.org/10.1049/iet-cvi.2012.0287 |
| work_keys_str_mv | AT guillempalou depthorderestimationforvideoframesusingmotionocclusions AT philippesalembier depthorderestimationforvideoframesusingmotionocclusions |