DSA-SOLO: Double Split Attention SOLO for Side-Scan Sonar Target Segmentation
Side-scan sonar systems play an important role in tasks such as marine terrain exploration and underwater target identification. Target segmentation of side-scan sonar images is an effective method of underwater target detection. However, the principle of side-scan sonar systems leads to high noise...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/18/9365 |
| _version_ | 1797491392068452352 |
|---|---|
| author | Honghe Huang Zhen Zuo Bei Sun Peng Wu Jiaju Zhang |
| author_facet | Honghe Huang Zhen Zuo Bei Sun Peng Wu Jiaju Zhang |
| author_sort | Honghe Huang |
| collection | DOAJ |
| description | Side-scan sonar systems play an important role in tasks such as marine terrain exploration and underwater target identification. Target segmentation of side-scan sonar images is an effective method of underwater target detection. However, the principle of side-scan sonar systems leads to high noise interference, weak boundary information, and difficult target feature extraction of sonar images. To solve these problems, we propose a Double Split Attention (DSA) SOLO. Specially, we present an efficient attention module called DSA which fuses spatial attention and channel attention together effectively. DSA first splits feature maps into two parts along channel dimensions before processing them in parallel. Next, DSA utilizes C-S Unit and S-C Unit to describe relevant features in the spatial and channel dimensions, respectively. After that, the results of the two parts are aggregated to improve feature representation. We embedded the proposed DSA module after the FPN network of SOLOv2, and this approach improves the instance segmentation accuracy to a great extent. Experimental results show that our proposed DSA-SOLO on SCTD dataset achieves 78.4% mAP.5, which is 5.1% higher than SOLOv2. |
| first_indexed | 2024-03-10T00:46:47Z |
| format | Article |
| id | doaj.art-24d85a955ffb44d799c977d601b06e2d |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T00:46:47Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-24d85a955ffb44d799c977d601b06e2d2023-11-23T14:57:27ZengMDPI AGApplied Sciences2076-34172022-09-011218936510.3390/app12189365DSA-SOLO: Double Split Attention SOLO for Side-Scan Sonar Target SegmentationHonghe Huang0Zhen Zuo1Bei Sun2Peng Wu3Jiaju Zhang4College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, ChinaSide-scan sonar systems play an important role in tasks such as marine terrain exploration and underwater target identification. Target segmentation of side-scan sonar images is an effective method of underwater target detection. However, the principle of side-scan sonar systems leads to high noise interference, weak boundary information, and difficult target feature extraction of sonar images. To solve these problems, we propose a Double Split Attention (DSA) SOLO. Specially, we present an efficient attention module called DSA which fuses spatial attention and channel attention together effectively. DSA first splits feature maps into two parts along channel dimensions before processing them in parallel. Next, DSA utilizes C-S Unit and S-C Unit to describe relevant features in the spatial and channel dimensions, respectively. After that, the results of the two parts are aggregated to improve feature representation. We embedded the proposed DSA module after the FPN network of SOLOv2, and this approach improves the instance segmentation accuracy to a great extent. Experimental results show that our proposed DSA-SOLO on SCTD dataset achieves 78.4% mAP.5, which is 5.1% higher than SOLOv2.https://www.mdpi.com/2076-3417/12/18/9365side-scan sonar imageinstance segmentationattention mechanismdeep learning |
| spellingShingle | Honghe Huang Zhen Zuo Bei Sun Peng Wu Jiaju Zhang DSA-SOLO: Double Split Attention SOLO for Side-Scan Sonar Target Segmentation Applied Sciences side-scan sonar image instance segmentation attention mechanism deep learning |
| title | DSA-SOLO: Double Split Attention SOLO for Side-Scan Sonar Target Segmentation |
| title_full | DSA-SOLO: Double Split Attention SOLO for Side-Scan Sonar Target Segmentation |
| title_fullStr | DSA-SOLO: Double Split Attention SOLO for Side-Scan Sonar Target Segmentation |
| title_full_unstemmed | DSA-SOLO: Double Split Attention SOLO for Side-Scan Sonar Target Segmentation |
| title_short | DSA-SOLO: Double Split Attention SOLO for Side-Scan Sonar Target Segmentation |
| title_sort | dsa solo double split attention solo for side scan sonar target segmentation |
| topic | side-scan sonar image instance segmentation attention mechanism deep learning |
| url | https://www.mdpi.com/2076-3417/12/18/9365 |
| work_keys_str_mv | AT honghehuang dsasolodoublesplitattentionsoloforsidescansonartargetsegmentation AT zhenzuo dsasolodoublesplitattentionsoloforsidescansonartargetsegmentation AT beisun dsasolodoublesplitattentionsoloforsidescansonartargetsegmentation AT pengwu dsasolodoublesplitattentionsoloforsidescansonartargetsegmentation AT jiajuzhang dsasolodoublesplitattentionsoloforsidescansonartargetsegmentation |