SCoralDet: Efficient real-time underwater soft coral detection with YOLO
In recent years, climate change and marine pollution have significantly degraded coral reefs, highlighting the urgent need for automated coral detection to monitor marine ecosystems. However, underwater coral detection presents unique challenges, including low image contrast, complex coral structure...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954124004795 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595370193977344 |
|---|---|
| author | Zhaoxuan Lu Lyuchao Liao Xingang Xie Hui Yuan |
| author_facet | Zhaoxuan Lu Lyuchao Liao Xingang Xie Hui Yuan |
| author_sort | Zhaoxuan Lu |
| collection | DOAJ |
| description | In recent years, climate change and marine pollution have significantly degraded coral reefs, highlighting the urgent need for automated coral detection to monitor marine ecosystems. However, underwater coral detection presents unique challenges, including low image contrast, complex coral structures, and dense coral growth, which limit the effectiveness of general object detection algorithms. To address these challenges, we propose SCoralDet, a soft coral detection model based on the YOLO architecture. First, we introduce a Multi-Path Fusion Block (MPFB) to capture coral features across multiple scales, enhancing the model’s robustness to uneven lighting and image blurring. We further improve inference efficiency by applying reparameterization. Second, we integrate lightweight components such as GSConv and VoV-GSCSP to reduce computational overhead without sacrificing performance. Additionally, we develop an Adaptive Power Transformation label assignment strategy, which dynamically adjusts anchor alignment metrics. By incorporating soft labels and soft central region loss, our model is guided to prioritize high-quality, well-aligned predictions. We evaluate SCoralDet on the Soft-Coral dataset, achieving an inference latency of 9.52 ms and an mAP50 of 81.9. This surpasses the performance of YOLOv5 (79.9), YOLOv6 (79.4), YOLOv8 (79.5), YOLOv9 (78.3), and YOLOv10 (79.5). These results demonstrate the effectiveness and practicality of SCoralDet in underwater coral detection tasks. |
| format | Article |
| id | doaj-art-00d9436dc47d4d55ad6886e1497c8c05 |
| institution | Kabale University |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-00d9436dc47d4d55ad6886e1497c8c052025-01-19T06:24:35ZengElsevierEcological Informatics1574-95412025-03-0185102937SCoralDet: Efficient real-time underwater soft coral detection with YOLOZhaoxuan Lu0Lyuchao Liao1Xingang Xie2Hui Yuan3School of Transportation, Fujian University of Technology, Fuzhou, 350118, ChinaSchool of Transportation, Fujian University of Technology, Fuzhou, 350118, China; Corresponding author.School of Marine Information Engineering, Hainan Tropical Ocean University, Sanya, 572022, ChinaSchool of Information Science and Technology, Beijing University of Technology, Beijing, 100124, China; NLPR & MAIS, Institute of Automation, Chinese Academy of Sciences, Beijing, 100191, ChinaIn recent years, climate change and marine pollution have significantly degraded coral reefs, highlighting the urgent need for automated coral detection to monitor marine ecosystems. However, underwater coral detection presents unique challenges, including low image contrast, complex coral structures, and dense coral growth, which limit the effectiveness of general object detection algorithms. To address these challenges, we propose SCoralDet, a soft coral detection model based on the YOLO architecture. First, we introduce a Multi-Path Fusion Block (MPFB) to capture coral features across multiple scales, enhancing the model’s robustness to uneven lighting and image blurring. We further improve inference efficiency by applying reparameterization. Second, we integrate lightweight components such as GSConv and VoV-GSCSP to reduce computational overhead without sacrificing performance. Additionally, we develop an Adaptive Power Transformation label assignment strategy, which dynamically adjusts anchor alignment metrics. By incorporating soft labels and soft central region loss, our model is guided to prioritize high-quality, well-aligned predictions. We evaluate SCoralDet on the Soft-Coral dataset, achieving an inference latency of 9.52 ms and an mAP50 of 81.9. This surpasses the performance of YOLOv5 (79.9), YOLOv6 (79.4), YOLOv8 (79.5), YOLOv9 (78.3), and YOLOv10 (79.5). These results demonstrate the effectiveness and practicality of SCoralDet in underwater coral detection tasks.http://www.sciencedirect.com/science/article/pii/S1574954124004795Object detectionUnderwater image analysisYOLOSoft coralSCoralDet |
| spellingShingle | Zhaoxuan Lu Lyuchao Liao Xingang Xie Hui Yuan SCoralDet: Efficient real-time underwater soft coral detection with YOLO Ecological Informatics Object detection Underwater image analysis YOLO Soft coral SCoralDet |
| title | SCoralDet: Efficient real-time underwater soft coral detection with YOLO |
| title_full | SCoralDet: Efficient real-time underwater soft coral detection with YOLO |
| title_fullStr | SCoralDet: Efficient real-time underwater soft coral detection with YOLO |
| title_full_unstemmed | SCoralDet: Efficient real-time underwater soft coral detection with YOLO |
| title_short | SCoralDet: Efficient real-time underwater soft coral detection with YOLO |
| title_sort | scoraldet efficient real time underwater soft coral detection with yolo |
| topic | Object detection Underwater image analysis YOLO Soft coral SCoralDet |
| url | http://www.sciencedirect.com/science/article/pii/S1574954124004795 |
| work_keys_str_mv | AT zhaoxuanlu scoraldetefficientrealtimeunderwatersoftcoraldetectionwithyolo AT lyuchaoliao scoraldetefficientrealtimeunderwatersoftcoraldetectionwithyolo AT xingangxie scoraldetefficientrealtimeunderwatersoftcoraldetectionwithyolo AT huiyuan scoraldetefficientrealtimeunderwatersoftcoraldetectionwithyolo |