Underwater Drowning Detection Dataset
<p dir="ltr"><b>Underwater Drowning Detection Dataset</b><br>This dataset contains 5,613 manually annotated underwater images for drowning detection research, captured in controlled swimming pool environments. It provides a balanced distribution of three behavioral...
সংরক্ষণ করুন:
| প্রধান লেখক: | |
|---|---|
| অন্যান্য লেখক: | , |
| প্রকাশিত: |
2025
|
| বিষয়গুলি: | |
| ট্যাগগুলো: |
ট্যাগ যুক্ত করুন
কোনো ট্যাগ নেই, প্রথমজন হিসাবে ট্যাগ করুন!
|
| সংক্ষিপ্ত: | <p dir="ltr"><b>Underwater Drowning Detection Dataset</b><br>This dataset contains 5,613 manually annotated underwater images for drowning detection research, captured in controlled swimming pool environments. It provides a balanced distribution of three behavioral states:</p><p><br></p><ul><li><b>Swimming</b> (1,871 images)</li><li><b>Struggling</b> (1,871 images)</li><li><b>Drowning</b> (1,871 images)</li></ul><p dir="ltr">All images were collected under real underwater conditions and annotated for object detection tasks using the YOLO format.</p><p dir="ltr"><b>Key Features</b></p><ul><li>High-resolution underwater images (640×640 pixels, RGB)</li><li>YOLO <code>.txt</code> annotations with bounding boxes for three behavior classes</li><li>Balanced class distribution to minimize model bias</li><li>Data collected ethically with lifeguard supervision and participant consent</li><li>Includes realistic challenges such as water distortion and lighting variability</li></ul><p dir="ltr"><b>Technical Details</b></p><ul><li><b>Total Images:</b> 5,613</li><li><b>Training/Validation Split:</b> 4,488 / 1,125</li><li><b>Classes:</b> Swimming, Struggling, Drowning</li><li><b>Format:</b> JPEG + YOLO annotation files</li><li><b>Resolution:</b> 640×640 pixels</li><li><b>Baseline Performance:</b> YOLOv8n achieved 97.5% mAP@50 on this dataset</li></ul><p dir="ltr"><b>Annotation Format</b><br>Each image has a corresponding .txt file with annotations in YOLO format, where each line follows this structure:</p><p dir="ltr"> <br><br><b>Field Descriptions:</b><br><br></p><ul><li>class_id: Integer label for the class<br>0 = Swimming<br>1 = Struggling<br>2 = Drowning</li><li>x_center, y_center: Normalized center coordinates of the bounding box (values between 0.0 and 1.0)</li><li>width, height: Normalized width and height of the bounding box (values between 0.0 and 1.0)</li></ul><p dir="ltr"><b>Example Annotation:</b><br><br>0 0.509896 0.568519 0.453125 0.581481</p><p dir="ltr">This line indicates a “Swimming” detection (class_id = 0) with a bounding box centered at 50.99% (horizontal) and 56.85% (vertical) of the image dimensions, covering 45.31% of the width and 58.15% of the height.</p><p dir="ltr"><b>Dataset Folder Structure</b><br>datasets/<br>├── images/<br>│ ├── train/<br>│ │ ├── frame_00001.jpg<br>│ │ └── ...<br>│ └── val/<br>│ ├── frame_04489.jpg<br>│ └── ...<br>│<br>├── labels/<br>│ ├── train/<br>│ │ ├── frame_00001.txt<br>│ │ └── ...<br>│ └── val/<br>│ ├── frame_04489.txt<br>│ └── ...<br>│<br>├── classes.txt<br>├── README.md</p><p><br></p><p dir="ltr"><b>Use and Applications</b><br>This dataset is designed to support the development and evaluation of real-time AI systems for aquatic safety, including:</p><p><br></p><ul><li>Drowning detection models</li><li>Multi-class object detection in underwater environments</li><li>Research in underwater computer vision and human activity recognition</li></ul><p dir="ltr"><b>Citation</b><br>If you use this dataset, please cite:<br></p><pre>graphqlCopyEdit<pre>@dataset{underwater_drowning_detection_2025,<br> title = {Underwater Drowning Detection Dataset},<br> author = {Hamad Alzaabi and Saif Alzaabi and Sarah Kohail},<br> year = {2025},<br> publisher = {Figshare},<br> note = {Manually annotated underwater images for drowning detection research}<br>}<br></pre></pre><p dir="ltr">Please also cite the related publication:<br><br>mathematicaCopyEdit</p><pre>@inproceedings{Alzaabi2025,<br> author = {Hamad Alzaabi and Saif Alzaabi and Sarah Kohail},<br> title = {Multi‑Swimmer Drowning Detection Using a Custom Annotated Underwater Dataset and Real‑Time AI},<br> booktitle = {Proceedings of the International Conference on Image Analysis and Processing (ICIAP)},<br> year = {2025}<br>}</pre><p><br></p> |
|---|