Multi-Scale Feature Enhancement for Saliency Object Detection Algorithm
Aimed at existing saliency object detection models with problems of front and back view misclassification and edge blur, this study proposes an algorithm with multi-scale feature enhancement. In this algorithm, the feature maps of salient objects are extracted using VGG16. Multi-scale Feature Fusion...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10258301/ |
| _version_ | 1797668041684680704 |
|---|---|
| author | Su Li Rugang Wang Feng Zhou Yuanyuan Wang Naihong Guo |
| author_facet | Su Li Rugang Wang Feng Zhou Yuanyuan Wang Naihong Guo |
| author_sort | Su Li |
| collection | DOAJ |
| description | Aimed at existing saliency object detection models with problems of front and back view misclassification and edge blur, this study proposes an algorithm with multi-scale feature enhancement. In this algorithm, the feature maps of salient objects are extracted using VGG16. Multi-scale Feature Fusion Module is added to enhance the detailed information of the second feature layer and the semantic information of the fifth feature layer, which effectively improves the characterization ability of the second feature layer on the edges of salient objects and the fifth feature layer on salient objects. Simultaneously, Feature Enhancement Fusion Module is added to achieve the full fusion of local detail information and global semantic information through layer-by-layer fusion from deep to shallow, which is used to obtain a feature map with complete feature information. Finally, a complete prediction map with clear edges is obtained by training the network model. The performance of the proposed algorithm is compared with six algorithms, Amulet, R3Net, PoolNet, MINet, PurNet, and NSAL, on the HKU-IS, ECSSD, DUT-OMRON, and DUTS-TE datasets. MAE (Mean Absolute Error) values were decreased by 0.011, 0.009, 0, −0.001, 0.001, 0.003. F-measure were improved by 0.037, 0.019, 0.013, 0.017, 0.015, 0.09. E-measure were improved by: null, −0.008, 0.003, 0.005, −0.014, 0.047. S-measure were improved by: 0.073, 0.041, 0.016, 0.021, 0.016, 0.101. Compared with existing algorithms, the proposed algorithm can obtain better detection results and accurately identify all regions of significant objects. |
| first_indexed | 2024-03-11T20:22:20Z |
| format | Article |
| id | doaj.art-658fae80e6f54335805d7b9faaa6a146 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-11T20:22:20Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-658fae80e6f54335805d7b9faaa6a1462023-10-02T23:01:40ZengIEEEIEEE Access2169-35362023-01-011110351110352010.1109/ACCESS.2023.331790110258301Multi-Scale Feature Enhancement for Saliency Object Detection AlgorithmSu Li0https://orcid.org/0009-0007-7183-8432Rugang Wang1https://orcid.org/0000-0001-7617-9607Feng Zhou2https://orcid.org/0000-0002-2906-8127Yuanyuan Wang3Naihong Guo4School of Information Technology, Yancheng Institute of Technology, Yancheng, ChinaSchool of Information Technology, Yancheng Institute of Technology, Yancheng, ChinaSchool of Information Technology, Yancheng Institute of Technology, Yancheng, ChinaSchool of Information Technology, Yancheng Institute of Technology, Yancheng, ChinaYancheng XiongYing Precision Machinery Company Ltd., Yancheng, ChinaAimed at existing saliency object detection models with problems of front and back view misclassification and edge blur, this study proposes an algorithm with multi-scale feature enhancement. In this algorithm, the feature maps of salient objects are extracted using VGG16. Multi-scale Feature Fusion Module is added to enhance the detailed information of the second feature layer and the semantic information of the fifth feature layer, which effectively improves the characterization ability of the second feature layer on the edges of salient objects and the fifth feature layer on salient objects. Simultaneously, Feature Enhancement Fusion Module is added to achieve the full fusion of local detail information and global semantic information through layer-by-layer fusion from deep to shallow, which is used to obtain a feature map with complete feature information. Finally, a complete prediction map with clear edges is obtained by training the network model. The performance of the proposed algorithm is compared with six algorithms, Amulet, R3Net, PoolNet, MINet, PurNet, and NSAL, on the HKU-IS, ECSSD, DUT-OMRON, and DUTS-TE datasets. MAE (Mean Absolute Error) values were decreased by 0.011, 0.009, 0, −0.001, 0.001, 0.003. F-measure were improved by 0.037, 0.019, 0.013, 0.017, 0.015, 0.09. E-measure were improved by: null, −0.008, 0.003, 0.005, −0.014, 0.047. S-measure were improved by: 0.073, 0.041, 0.016, 0.021, 0.016, 0.101. Compared with existing algorithms, the proposed algorithm can obtain better detection results and accurately identify all regions of significant objects.https://ieeexplore.ieee.org/document/10258301/Salient object detectionmulti-scale feature fusionfeature-enhancedlocal and global information |
| spellingShingle | Su Li Rugang Wang Feng Zhou Yuanyuan Wang Naihong Guo Multi-Scale Feature Enhancement for Saliency Object Detection Algorithm IEEE Access Salient object detection multi-scale feature fusion feature-enhanced local and global information |
| title | Multi-Scale Feature Enhancement for Saliency Object Detection Algorithm |
| title_full | Multi-Scale Feature Enhancement for Saliency Object Detection Algorithm |
| title_fullStr | Multi-Scale Feature Enhancement for Saliency Object Detection Algorithm |
| title_full_unstemmed | Multi-Scale Feature Enhancement for Saliency Object Detection Algorithm |
| title_short | Multi-Scale Feature Enhancement for Saliency Object Detection Algorithm |
| title_sort | multi scale feature enhancement for saliency object detection algorithm |
| topic | Salient object detection multi-scale feature fusion feature-enhanced local and global information |
| url | https://ieeexplore.ieee.org/document/10258301/ |
| work_keys_str_mv | AT suli multiscalefeatureenhancementforsaliencyobjectdetectionalgorithm AT rugangwang multiscalefeatureenhancementforsaliencyobjectdetectionalgorithm AT fengzhou multiscalefeatureenhancementforsaliencyobjectdetectionalgorithm AT yuanyuanwang multiscalefeatureenhancementforsaliencyobjectdetectionalgorithm AT naihongguo multiscalefeatureenhancementforsaliencyobjectdetectionalgorithm |