A Precise Semantic Segmentation Model for Seabed Sediment Detection Using YOLO-C
Semantic segmentation methods have been successfully applied in seabed sediment detection. However, fast models like YOLO only produce rough segmentation boundaries (rectangles), while precise models like U-Net require too much time. In order to achieve fast and precise semantic segmentation results...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/11/7/1475 |
| _version_ | 1827732805171281920 |
|---|---|
| author | Xin Chen Peng Shi Yi Hu |
| author_facet | Xin Chen Peng Shi Yi Hu |
| author_sort | Xin Chen |
| collection | DOAJ |
| description | Semantic segmentation methods have been successfully applied in seabed sediment detection. However, fast models like YOLO only produce rough segmentation boundaries (rectangles), while precise models like U-Net require too much time. In order to achieve fast and precise semantic segmentation results, this paper introduces a novel model called YOLO-C. It utilizes the full-resolution classification features of the semantic segmentation algorithm to generate more accurate regions of interest, enabling rapid separation of potential targets and achieving region-based partitioning and precise object boundaries. YOLO-C surpasses existing methods in terms of accuracy and detection scope. Compared to U-Net, it achieves an impressive 15.17% improvement in mean pixel accuracy (mPA). With a processing speed of 98 frames per second, YOLO-C meets the requirements of real-time detection and provides accurate size estimation through segmentation. Furthermore, it achieves a mean average precision (mAP) of 58.94% and a mean intersection over union (mIoU) of 70.36%, outperforming industry-standard algorithms such as YOLOX. Because of the good performance in both rapid processing and high precision, YOLO-C can be effectively utilized in real-time seabed exploration tasks. |
| first_indexed | 2024-03-11T00:56:13Z |
| format | Article |
| id | doaj.art-ed2c80cffdc642bfbe473c2d9f2bb7a2 |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-11T00:56:13Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-ed2c80cffdc642bfbe473c2d9f2bb7a22023-11-18T20:00:55ZengMDPI AGJournal of Marine Science and Engineering2077-13122023-07-01117147510.3390/jmse11071475A Precise Semantic Segmentation Model for Seabed Sediment Detection Using YOLO-CXin Chen0Peng Shi1Yi Hu2National Center for Materials Service Safety, University of Science and Technology Beijing, Beijing 100083, ChinaNational Center for Materials Service Safety, University of Science and Technology Beijing, Beijing 100083, ChinaLaboratory of Coast and Marine Geology, Third Institute of Oceanography, Minister of Natural Resources (MNR), Xiamen 361005, ChinaSemantic segmentation methods have been successfully applied in seabed sediment detection. However, fast models like YOLO only produce rough segmentation boundaries (rectangles), while precise models like U-Net require too much time. In order to achieve fast and precise semantic segmentation results, this paper introduces a novel model called YOLO-C. It utilizes the full-resolution classification features of the semantic segmentation algorithm to generate more accurate regions of interest, enabling rapid separation of potential targets and achieving region-based partitioning and precise object boundaries. YOLO-C surpasses existing methods in terms of accuracy and detection scope. Compared to U-Net, it achieves an impressive 15.17% improvement in mean pixel accuracy (mPA). With a processing speed of 98 frames per second, YOLO-C meets the requirements of real-time detection and provides accurate size estimation through segmentation. Furthermore, it achieves a mean average precision (mAP) of 58.94% and a mean intersection over union (mIoU) of 70.36%, outperforming industry-standard algorithms such as YOLOX. Because of the good performance in both rapid processing and high precision, YOLO-C can be effectively utilized in real-time seabed exploration tasks.https://www.mdpi.com/2077-1312/11/7/1475feature extraction and fusionobject detectionsemantic segmentationseabed sedimentYOLO-C |
| spellingShingle | Xin Chen Peng Shi Yi Hu A Precise Semantic Segmentation Model for Seabed Sediment Detection Using YOLO-C Journal of Marine Science and Engineering feature extraction and fusion object detection semantic segmentation seabed sediment YOLO-C |
| title | A Precise Semantic Segmentation Model for Seabed Sediment Detection Using YOLO-C |
| title_full | A Precise Semantic Segmentation Model for Seabed Sediment Detection Using YOLO-C |
| title_fullStr | A Precise Semantic Segmentation Model for Seabed Sediment Detection Using YOLO-C |
| title_full_unstemmed | A Precise Semantic Segmentation Model for Seabed Sediment Detection Using YOLO-C |
| title_short | A Precise Semantic Segmentation Model for Seabed Sediment Detection Using YOLO-C |
| title_sort | precise semantic segmentation model for seabed sediment detection using yolo c |
| topic | feature extraction and fusion object detection semantic segmentation seabed sediment YOLO-C |
| url | https://www.mdpi.com/2077-1312/11/7/1475 |
| work_keys_str_mv | AT xinchen aprecisesemanticsegmentationmodelforseabedsedimentdetectionusingyoloc AT pengshi aprecisesemanticsegmentationmodelforseabedsedimentdetectionusingyoloc AT yihu aprecisesemanticsegmentationmodelforseabedsedimentdetectionusingyoloc AT xinchen precisesemanticsegmentationmodelforseabedsedimentdetectionusingyoloc AT pengshi precisesemanticsegmentationmodelforseabedsedimentdetectionusingyoloc AT yihu precisesemanticsegmentationmodelforseabedsedimentdetectionusingyoloc |