AquaYOLO: Enhancing YOLOv8 for Accurate Underwater Object Detection for Sonar Images
Object detection in underwater environments presents significant challenges due to the inherent limitations of sonar imaging, such as noise, low resolution, lack of texture, and color information. This paper introduces AquaYOLO, an enhanced YOLOv8 version specifically designed to improve object dete...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/13/1/73 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588235000250368 |
|---|---|
| author | Yanyang Lu Jingjing Zhang Qinglang Chen Chengjun Xu Muhammad Irfan Zhe Chen |
| author_facet | Yanyang Lu Jingjing Zhang Qinglang Chen Chengjun Xu Muhammad Irfan Zhe Chen |
| author_sort | Yanyang Lu |
| collection | DOAJ |
| description | Object detection in underwater environments presents significant challenges due to the inherent limitations of sonar imaging, such as noise, low resolution, lack of texture, and color information. This paper introduces AquaYOLO, an enhanced YOLOv8 version specifically designed to improve object detection accuracy in underwater sonar images. AquaYOLO replaces traditional convolutional layers with a residual block in the backbone network to enhance feature extraction. In addition, we introduce Dynamic Selection Aggregation Module (DSAM) and Context-Aware Feature Selection (CAFS) in the neck network. These modifications allow AquaYOLO to capture intricate details better and reduce feature redundancy, leading to improved performance in underwater object detection tasks. The model is evaluated on two standard underwater sonar datasets, UATD and Marine Debris, demonstrating superior accuracy and robustness compared to baseline models. |
| format | Article |
| id | doaj-art-d16b2a38f5bd40e9983eead1c71c8e2e |
| institution | Kabale University |
| issn | 2077-1312 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj-art-d16b2a38f5bd40e9983eead1c71c8e2e2025-01-24T13:36:46ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-01-011317310.3390/jmse13010073AquaYOLO: Enhancing YOLOv8 for Accurate Underwater Object Detection for Sonar ImagesYanyang Lu0Jingjing Zhang1Qinglang Chen2Chengjun Xu3Muhammad Irfan4Zhe Chen5Hangzhou Applied Acoustics Research Institute, Hangzhou 310023, ChinaHangzhou Applied Acoustics Research Institute, Hangzhou 310023, ChinaHangzhou Applied Acoustics Research Institute, Hangzhou 310023, ChinaHangzhou Applied Acoustics Research Institute, Hangzhou 310023, ChinaSchool of Software, Northwestern Polytechnical University, Xi’an 710129, ChinaSchool of Information and Communication, Guilin University of Electronic Technology, Guilin 541004, ChinaObject detection in underwater environments presents significant challenges due to the inherent limitations of sonar imaging, such as noise, low resolution, lack of texture, and color information. This paper introduces AquaYOLO, an enhanced YOLOv8 version specifically designed to improve object detection accuracy in underwater sonar images. AquaYOLO replaces traditional convolutional layers with a residual block in the backbone network to enhance feature extraction. In addition, we introduce Dynamic Selection Aggregation Module (DSAM) and Context-Aware Feature Selection (CAFS) in the neck network. These modifications allow AquaYOLO to capture intricate details better and reduce feature redundancy, leading to improved performance in underwater object detection tasks. The model is evaluated on two standard underwater sonar datasets, UATD and Marine Debris, demonstrating superior accuracy and robustness compared to baseline models.https://www.mdpi.com/2077-1312/13/1/73underwater object detectionunderwater sonar imagestrackingunderwater classificationmarine detectionmarine classification |
| spellingShingle | Yanyang Lu Jingjing Zhang Qinglang Chen Chengjun Xu Muhammad Irfan Zhe Chen AquaYOLO: Enhancing YOLOv8 for Accurate Underwater Object Detection for Sonar Images Journal of Marine Science and Engineering underwater object detection underwater sonar images tracking underwater classification marine detection marine classification |
| title | AquaYOLO: Enhancing YOLOv8 for Accurate Underwater Object Detection for Sonar Images |
| title_full | AquaYOLO: Enhancing YOLOv8 for Accurate Underwater Object Detection for Sonar Images |
| title_fullStr | AquaYOLO: Enhancing YOLOv8 for Accurate Underwater Object Detection for Sonar Images |
| title_full_unstemmed | AquaYOLO: Enhancing YOLOv8 for Accurate Underwater Object Detection for Sonar Images |
| title_short | AquaYOLO: Enhancing YOLOv8 for Accurate Underwater Object Detection for Sonar Images |
| title_sort | aquayolo enhancing yolov8 for accurate underwater object detection for sonar images |
| topic | underwater object detection underwater sonar images tracking underwater classification marine detection marine classification |
| url | https://www.mdpi.com/2077-1312/13/1/73 |
| work_keys_str_mv | AT yanyanglu aquayoloenhancingyolov8foraccurateunderwaterobjectdetectionforsonarimages AT jingjingzhang aquayoloenhancingyolov8foraccurateunderwaterobjectdetectionforsonarimages AT qinglangchen aquayoloenhancingyolov8foraccurateunderwaterobjectdetectionforsonarimages AT chengjunxu aquayoloenhancingyolov8foraccurateunderwaterobjectdetectionforsonarimages AT muhammadirfan aquayoloenhancingyolov8foraccurateunderwaterobjectdetectionforsonarimages AT zhechen aquayoloenhancingyolov8foraccurateunderwaterobjectdetectionforsonarimages |