Enhancing Aquaculture Net Pen Inspection: A Benchmark Study on Detection and Semantic Segmentation
The aquaculture industry is critical in global food production, with net pens being a vital component in fish farming operations. Regular inspection of these net pens is essential to ensure their structural integrity, prevent fish escapes, and monitor biofouling. However, manual inspections are time...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10819379/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554066281332736 |
|---|---|
| author | Waseem Akram Ahsan Baidar Bakht Muhayy Ud Din Lakmal Seneviratne Irfan Hussain |
| author_facet | Waseem Akram Ahsan Baidar Bakht Muhayy Ud Din Lakmal Seneviratne Irfan Hussain |
| author_sort | Waseem Akram |
| collection | DOAJ |
| description | The aquaculture industry is critical in global food production, with net pens being a vital component in fish farming operations. Regular inspection of these net pens is essential to ensure their structural integrity, prevent fish escapes, and monitor biofouling. However, manual inspections are time-consuming, labor-intensive, and subject to human error, driving the need for automated solutions. Detection and segmentation are computer vision techniques that offer a promising approach to automating these inspections by enabling precise identification and classification of various components within underwater images. This paper presents a novel dataset designed specifically for detection and semantic segmentation in the context of aquaculture net-pen inspections. The dataset comprises diverse high-resolution underwater images and annotated with multiple classes, including net holes, biofouling, and vegetation. We also provide a benchmark evaluation of state-of-the-art detection and semantic segmentation models using standard performance metrics. We evaluate their benefits both qualitatively and quantitatively in aquaculture inspection. As a result, we recommend using the YOLOV8 model for the detection and segmentation task, as it offers an optimal balance between performance and computational efficiency, making it well-suited for real-time inspection. The dataset and the detection pipeline provide promising opportunities for further research in aquaculture net-pen inspection tasks. |
| format | Article |
| id | doaj-art-c77ee7de62904abcaacbe5bad2013342 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-c77ee7de62904abcaacbe5bad20133422025-01-09T00:01:26ZengIEEEIEEE Access2169-35362025-01-01133453347410.1109/ACCESS.2024.352463510819379Enhancing Aquaculture Net Pen Inspection: A Benchmark Study on Detection and Semantic SegmentationWaseem Akram0https://orcid.org/0000-0002-7401-5120Ahsan Baidar Bakht1Muhayy Ud Din2https://orcid.org/0000-0001-6214-1077Lakmal Seneviratne3https://orcid.org/0000-0001-6405-8402Irfan Hussain4https://orcid.org/0000-0003-2759-0306Khalifa University Center for Autonomous Robotic Systems (KUCARS), Khalifa University, Abu Dhabi, United Arab EmiratesKhalifa University Center for Autonomous Robotic Systems (KUCARS), Khalifa University, Abu Dhabi, United Arab EmiratesKhalifa University Center for Autonomous Robotic Systems (KUCARS), Khalifa University, Abu Dhabi, United Arab EmiratesKhalifa University Center for Autonomous Robotic Systems (KUCARS), Khalifa University, Abu Dhabi, United Arab EmiratesKhalifa University Center for Autonomous Robotic Systems (KUCARS), Khalifa University, Abu Dhabi, United Arab EmiratesThe aquaculture industry is critical in global food production, with net pens being a vital component in fish farming operations. Regular inspection of these net pens is essential to ensure their structural integrity, prevent fish escapes, and monitor biofouling. However, manual inspections are time-consuming, labor-intensive, and subject to human error, driving the need for automated solutions. Detection and segmentation are computer vision techniques that offer a promising approach to automating these inspections by enabling precise identification and classification of various components within underwater images. This paper presents a novel dataset designed specifically for detection and semantic segmentation in the context of aquaculture net-pen inspections. The dataset comprises diverse high-resolution underwater images and annotated with multiple classes, including net holes, biofouling, and vegetation. We also provide a benchmark evaluation of state-of-the-art detection and semantic segmentation models using standard performance metrics. We evaluate their benefits both qualitatively and quantitatively in aquaculture inspection. As a result, we recommend using the YOLOV8 model for the detection and segmentation task, as it offers an optimal balance between performance and computational efficiency, making it well-suited for real-time inspection. The dataset and the detection pipeline provide promising opportunities for further research in aquaculture net-pen inspection tasks.https://ieeexplore.ieee.org/document/10819379/Aquacultureaquatic robotsdeep learningimage segmentationunderwater structures |
| spellingShingle | Waseem Akram Ahsan Baidar Bakht Muhayy Ud Din Lakmal Seneviratne Irfan Hussain Enhancing Aquaculture Net Pen Inspection: A Benchmark Study on Detection and Semantic Segmentation IEEE Access Aquaculture aquatic robots deep learning image segmentation underwater structures |
| title | Enhancing Aquaculture Net Pen Inspection: A Benchmark Study on Detection and Semantic Segmentation |
| title_full | Enhancing Aquaculture Net Pen Inspection: A Benchmark Study on Detection and Semantic Segmentation |
| title_fullStr | Enhancing Aquaculture Net Pen Inspection: A Benchmark Study on Detection and Semantic Segmentation |
| title_full_unstemmed | Enhancing Aquaculture Net Pen Inspection: A Benchmark Study on Detection and Semantic Segmentation |
| title_short | Enhancing Aquaculture Net Pen Inspection: A Benchmark Study on Detection and Semantic Segmentation |
| title_sort | enhancing aquaculture net pen inspection a benchmark study on detection and semantic segmentation |
| topic | Aquaculture aquatic robots deep learning image segmentation underwater structures |
| url | https://ieeexplore.ieee.org/document/10819379/ |
| work_keys_str_mv | AT waseemakram enhancingaquaculturenetpeninspectionabenchmarkstudyondetectionandsemanticsegmentation AT ahsanbaidarbakht enhancingaquaculturenetpeninspectionabenchmarkstudyondetectionandsemanticsegmentation AT muhayyuddin enhancingaquaculturenetpeninspectionabenchmarkstudyondetectionandsemanticsegmentation AT lakmalseneviratne enhancingaquaculturenetpeninspectionabenchmarkstudyondetectionandsemanticsegmentation AT irfanhussain enhancingaquaculturenetpeninspectionabenchmarkstudyondetectionandsemanticsegmentation |