Saliency Detection via Manifold Ranking on Multi-Layer Graph
Saliency detection is increasingly a crucial task in the computer vision area. In previous graph-based saliency detection, superpixels are usually regarded as the primary processing units to enhance computational efficiency. Nevertheless, most methods do not take into account the potential impact of...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10375386/ |
| _version_ | 1797243502960050176 |
|---|---|
| author | Suwei Wang Yang Ning Xuemei Li Caiming Zhang |
| author_facet | Suwei Wang Yang Ning Xuemei Li Caiming Zhang |
| author_sort | Suwei Wang |
| collection | DOAJ |
| description | Saliency detection is increasingly a crucial task in the computer vision area. In previous graph-based saliency detection, superpixels are usually regarded as the primary processing units to enhance computational efficiency. Nevertheless, most methods do not take into account the potential impact of errors in superpixel segmentation, which may result in incorrect saliency values. To address this issue, we propose a novel approach that leverages the diversity of superpixel algorithms and constructs a multi-layer graph. Specifically, we segment the input image into multiple sets by different superpixel algorithms. Through connections within and connections between these superpixel sets, we can mitigate the errors caused by individual algorithms through collaborative solutions. In addition to spatial proximity, we also consider feature similarity in the process of graph construction. Connecting superpixels that are similar in feature space can force them to obtain consistent saliency values, thus addressing challenges brought by the scattered spatial distribution and the uneven internal appearance of salient objects. Additionally, we use the two-stage manifold ranking to compute the saliency value of each superpixel, which includes a background-based ranking and a foreground-based ranking. Finally, we employ a mean-field-based propagation method to refine the saliency map iteratively and achieve smoother results. To evaluate the performance of our approach, we compare our work with multiple advanced methods in four datasets quantitatively and qualitatively. |
| first_indexed | 2024-04-24T18:56:09Z |
| format | Article |
| id | doaj.art-5b7b10d4fb3942e4bc8a218edec60b47 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T18:56:09Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5b7b10d4fb3942e4bc8a218edec60b472024-03-26T17:34:46ZengIEEEIEEE Access2169-35362024-01-01126615662710.1109/ACCESS.2023.334781210375386Saliency Detection via Manifold Ranking on Multi-Layer GraphSuwei Wang0https://orcid.org/0000-0002-0400-5269Yang Ning1Xuemei Li2https://orcid.org/0000-0001-5064-7425Caiming Zhang3https://orcid.org/0000-0003-0217-1543School of Software, Shandong University, Jinan, ChinaSchool of Computer Science and Technology, Shandong Jianzhu University, Jinan, ChinaSchool of Software, Shandong University, Jinan, ChinaSchool of Software, Shandong University, Jinan, ChinaSaliency detection is increasingly a crucial task in the computer vision area. In previous graph-based saliency detection, superpixels are usually regarded as the primary processing units to enhance computational efficiency. Nevertheless, most methods do not take into account the potential impact of errors in superpixel segmentation, which may result in incorrect saliency values. To address this issue, we propose a novel approach that leverages the diversity of superpixel algorithms and constructs a multi-layer graph. Specifically, we segment the input image into multiple sets by different superpixel algorithms. Through connections within and connections between these superpixel sets, we can mitigate the errors caused by individual algorithms through collaborative solutions. In addition to spatial proximity, we also consider feature similarity in the process of graph construction. Connecting superpixels that are similar in feature space can force them to obtain consistent saliency values, thus addressing challenges brought by the scattered spatial distribution and the uneven internal appearance of salient objects. Additionally, we use the two-stage manifold ranking to compute the saliency value of each superpixel, which includes a background-based ranking and a foreground-based ranking. Finally, we employ a mean-field-based propagation method to refine the saliency map iteratively and achieve smoother results. To evaluate the performance of our approach, we compare our work with multiple advanced methods in four datasets quantitatively and qualitatively.https://ieeexplore.ieee.org/document/10375386/Manifold rankingmulti-layer graphsuperpixel algorithmsaliency detection |
| spellingShingle | Suwei Wang Yang Ning Xuemei Li Caiming Zhang Saliency Detection via Manifold Ranking on Multi-Layer Graph IEEE Access Manifold ranking multi-layer graph superpixel algorithm saliency detection |
| title | Saliency Detection via Manifold Ranking on Multi-Layer Graph |
| title_full | Saliency Detection via Manifold Ranking on Multi-Layer Graph |
| title_fullStr | Saliency Detection via Manifold Ranking on Multi-Layer Graph |
| title_full_unstemmed | Saliency Detection via Manifold Ranking on Multi-Layer Graph |
| title_short | Saliency Detection via Manifold Ranking on Multi-Layer Graph |
| title_sort | saliency detection via manifold ranking on multi layer graph |
| topic | Manifold ranking multi-layer graph superpixel algorithm saliency detection |
| url | https://ieeexplore.ieee.org/document/10375386/ |
| work_keys_str_mv | AT suweiwang saliencydetectionviamanifoldrankingonmultilayergraph AT yangning saliencydetectionviamanifoldrankingonmultilayergraph AT xuemeili saliencydetectionviamanifoldrankingonmultilayergraph AT caimingzhang saliencydetectionviamanifoldrankingonmultilayergraph |