Video Object Relevance Metrics for Overall Segmentation Quality Evaluation
<p/> <p>Video object segmentation is a task that humans perform efficiently and effectively, but which is difficult for a computer to perform. Since video segmentation plays an important role for many emerging applications, as those enabled by the MPEG-4 and MPEG-7 standards, the ability...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2006-01-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Online Access: | http://dx.doi.org/10.1155/ASP/2006/82195 |
| _version_ | 1811278539531485184 |
|---|---|
| author | Correia Paulo Pereira Fernando |
| author_facet | Correia Paulo Pereira Fernando |
| author_sort | Correia Paulo |
| collection | DOAJ |
| description | <p/> <p>Video object segmentation is a task that humans perform efficiently and effectively, but which is difficult for a computer to perform. Since video segmentation plays an important role for many emerging applications, as those enabled by the MPEG-4 and MPEG-7 standards, the ability to assess the segmentation quality in view of the application targets is a relevant task for which a standard, or even a consensual, solution is not available. This paper considers the evaluation of overall segmentation partitions quality, highlighting one of its major components: the contextual relevance of the segmented objects. Video object relevance metrics are presented taking into account the behaviour of the human visual system and the visual attention mechanisms. In particular, contextual relevance evaluation takes into account the context where an object is found, exploiting, for instance, the contrast to neighbours or the position in the image. Most of the relevance metrics proposed in this paper can also be used in contexts other than segmentation quality evaluation, such as object-based rate control algorithms, description creation, or image and video quality evaluation.</p> |
| first_indexed | 2024-04-13T00:36:23Z |
| format | Article |
| id | doaj.art-3ec37b4bb48b4398b08d328851455514 |
| institution | Directory Open Access Journal |
| issn | 1687-6172 1687-6180 |
| language | English |
| last_indexed | 2024-04-13T00:36:23Z |
| publishDate | 2006-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj.art-3ec37b4bb48b4398b08d3288514555142022-12-22T03:10:18ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61721687-61802006-01-0120061082195Video Object Relevance Metrics for Overall Segmentation Quality EvaluationCorreia PauloPereira Fernando<p/> <p>Video object segmentation is a task that humans perform efficiently and effectively, but which is difficult for a computer to perform. Since video segmentation plays an important role for many emerging applications, as those enabled by the MPEG-4 and MPEG-7 standards, the ability to assess the segmentation quality in view of the application targets is a relevant task for which a standard, or even a consensual, solution is not available. This paper considers the evaluation of overall segmentation partitions quality, highlighting one of its major components: the contextual relevance of the segmented objects. Video object relevance metrics are presented taking into account the behaviour of the human visual system and the visual attention mechanisms. In particular, contextual relevance evaluation takes into account the context where an object is found, exploiting, for instance, the contrast to neighbours or the position in the image. Most of the relevance metrics proposed in this paper can also be used in contexts other than segmentation quality evaluation, such as object-based rate control algorithms, description creation, or image and video quality evaluation.</p>http://dx.doi.org/10.1155/ASP/2006/82195 |
| spellingShingle | Correia Paulo Pereira Fernando Video Object Relevance Metrics for Overall Segmentation Quality Evaluation EURASIP Journal on Advances in Signal Processing |
| title | Video Object Relevance Metrics for Overall Segmentation Quality Evaluation |
| title_full | Video Object Relevance Metrics for Overall Segmentation Quality Evaluation |
| title_fullStr | Video Object Relevance Metrics for Overall Segmentation Quality Evaluation |
| title_full_unstemmed | Video Object Relevance Metrics for Overall Segmentation Quality Evaluation |
| title_short | Video Object Relevance Metrics for Overall Segmentation Quality Evaluation |
| title_sort | video object relevance metrics for overall segmentation quality evaluation |
| url | http://dx.doi.org/10.1155/ASP/2006/82195 |
| work_keys_str_mv | AT correiapaulo videoobjectrelevancemetricsforoverallsegmentationqualityevaluation AT pereirafernando videoobjectrelevancemetricsforoverallsegmentationqualityevaluation |