Saliency density maximization for efficient visual objects discovery
Detection of salient objects in an image remains a challenging problem despite extensive studies in visual saliency, as the generated saliency map is usually noisy and incomplete. In this paper, we propose a new method to discover the salient object without prior knowledge on its shape and size. By...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/100801 http://hdl.handle.net/10220/18222 |
| _version_ | 1811691533162774528 |
|---|---|
| author | Luo, Ye Yuan, Junsong Xue, Ping Tian, Qi |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Luo, Ye Yuan, Junsong Xue, Ping Tian, Qi |
| author_sort | Luo, Ye |
| collection | NTU |
| description | Detection of salient objects in an image remains a
challenging problem despite extensive studies in visual saliency, as the generated saliency map is usually noisy and incomplete. In this paper, we propose a new method to discover the salient object without prior knowledge on its shape and size. By searching the sub-image, i.e., a bounding box of maximum saliency density, the new formulation can automatically crop the salient objects of various sizes in spite of the cluttered background, and is capable to handle different types of saliency maps. A global optimal solution is obtained by the proposed density-based branch-and-bound search. The proposed method can apply to both images and videos. Experimental results on a public dataset of five thousand images show that our unsupervised detection approach
is comparable to the state-of-the-art learning based methods.
Promising results are also observed in the salient object detection for videos with a good potential in video retargeting. |
| first_indexed | 2024-10-01T06:21:24Z |
| format | Journal Article |
| id | ntu-10356/100801 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:21:24Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/1008012020-03-07T14:00:32Z Saliency density maximization for efficient visual objects discovery Luo, Ye Yuan, Junsong Xue, Ping Tian, Qi School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering Detection of salient objects in an image remains a challenging problem despite extensive studies in visual saliency, as the generated saliency map is usually noisy and incomplete. In this paper, we propose a new method to discover the salient object without prior knowledge on its shape and size. By searching the sub-image, i.e., a bounding box of maximum saliency density, the new formulation can automatically crop the salient objects of various sizes in spite of the cluttered background, and is capable to handle different types of saliency maps. A global optimal solution is obtained by the proposed density-based branch-and-bound search. The proposed method can apply to both images and videos. Experimental results on a public dataset of five thousand images show that our unsupervised detection approach is comparable to the state-of-the-art learning based methods. Promising results are also observed in the salient object detection for videos with a good potential in video retargeting. Accepted version 2013-12-12T02:56:12Z 2019-12-06T20:28:31Z 2013-12-12T02:56:12Z 2019-12-06T20:28:31Z 2011 2011 Journal Article Luo, Y., Yuan, J., Xue, P., & Tian, Q. (2011). Saliency density maximization for efficient visual objects discovery. IEEE transactions on circuits and systems for video technology, 21(12), 1822-1834. 1051-8215 https://hdl.handle.net/10356/100801 http://hdl.handle.net/10220/18222 10.1109/TCSVT.2011.2147230 en IEEE transactions on circuits and systems for video technology © 2011 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: http://dx.doi.org/10.1109/TCSVT.2011.2147230. 13 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering Luo, Ye Yuan, Junsong Xue, Ping Tian, Qi Saliency density maximization for efficient visual objects discovery |
| title | Saliency density maximization for efficient visual objects discovery |
| title_full | Saliency density maximization for efficient visual objects discovery |
| title_fullStr | Saliency density maximization for efficient visual objects discovery |
| title_full_unstemmed | Saliency density maximization for efficient visual objects discovery |
| title_short | Saliency density maximization for efficient visual objects discovery |
| title_sort | saliency density maximization for efficient visual objects discovery |
| topic | DRNTU::Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/100801 http://hdl.handle.net/10220/18222 |
| work_keys_str_mv | AT luoye saliencydensitymaximizationforefficientvisualobjectsdiscovery AT yuanjunsong saliencydensitymaximizationforefficientvisualobjectsdiscovery AT xueping saliencydensitymaximizationforefficientvisualobjectsdiscovery AT tianqi saliencydensitymaximizationforefficientvisualobjectsdiscovery |