Hierarchical Deep Learning Framework for Automated Marine Vegetation and Fauna Analysis Using ROV Video Data

Experimental data for the paper "Hierarchical Deep Learning Framework for Automated Marine Vegetation and Fauna Analysis Using ROV Video Data."This dataset supports the study "Hierarchical Deep Learning Framework for Automated Marine Vegetation and Fauna Analysis Using ROV Video Data" by providing resources essential for reproducing and validating the research findings.Dataset Contents and Structure:<br><b>Hierarchical Model Weights:</b> - `.pth` files containing trained weights for all alpha regularization values used in hierarchical classification models.<b>MaskRCNN-Segmented Objects</b>: - `.jpg` files representing segmented objects detected by the MaskRCNN model. - Accompanied by `maskrcnn-segmented-objects-dataset.parquet`, which includes metadata and classifications: - <b>Columns</b>:masked_image: Path to the segmented image file.confidence: Confidence score for the prediction.predicted_species: Predicted species label.species: True species label.<b>MaskRCNN Weights</b>: - Trained MaskRCNN model weights, including hierarchical CNN models integrated with MaskRCNN in the processing pipeline.<b>Pre-Trained Models</b>:.pt files for all object detectors trained on the Esefjorden Marine Vegetation Segmentation Dataset (EMVSD) in YOLO txt format.<b>Segmented Object Outputs</b>: - Segmentation outputs and datasets for the following models: - RT-DETR: - Segmented objects: `rtdetr-segmented-objects/` - Dataset: `rtdetr-segmented-objects-dataset.parquet` - <b>YOLO-SAG</b>: - Segmented objects: `yolosag-segmented-objects/` - Dataset: `yolosag-segmented-objects-dataset.parquet` - <b>YOLOv11</b>: - Segmented objects: `yolov11-segmented-objects/` - Dataset: `yolov11-segmented-objects-dataset.parquet` - <b>YOLOv8</b>: - Segmented objects: `yolov8-segmented-objects/` - Dataset: `yolov8-segmented-objects-dataset.parquet` - <b>YOLOv9</b>: - Segmented objects: `yolov9-segmented-objects/` - Dataset: `yolov9-segmented-objects-dataset.parquet`<b>Usage Instructions</b>:1. Download and extract the dataset.2. Utilize the Python scripts provided in the associated GitHub repository for evaluation and inference: https://github.com/Ci2Lab/FjordVision<b>Reproducibility</b>:The dataset includes pre-trained weights, segmentation outputs, and experimental results to facilitate reproducibility. The `.parquet` files and segmented object directories follow a standardized format to ensure consistency.<b>Licensing</b>:This dataset is released under the CC-BY 4.0 license, permitting reuse with proper attribution.<b>Related Materials</b>:- GitHub Repository: https://github.com/Ci2Lab/FjordVision