Road Crack Detection And Classification

## Overview

Road Crack Detection And Classification is a dataset for instance segmentation tasks - it contains Road Cracks annotations for 1,258 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Supplementary Data Protocol

This supplementary dataset includes all files necessary to reproduce and evaluate the training and validation of YOLOv8 and CNN models for detecting GUS-stained and haustoria-containing cells with the BluVision Haustoria software.

1. gus_training_set_yolo/
- Contains the complete YOLOv8-compatible training dataset for GUS classification.
- Format: PyTorch YOLOv5/8 structure from Roboflow export.
- Subfolders:
- train/, test/, val/: Image sets and corresponding label files.
- data.yaml: Configuration file specifying dataset structure and classes.

2. haustoria_training_set_yolo/
- Contains the complete YOLOv8-compatible training dataset for haustoria detection.
- Format identical to gus_training_set_yolo/.

3. haustoria_training_set_cnn/
- Dataset formatted for CNN-based classification.
- Structure:
- gus/: Images of cells without haustoria.
- hau/: Images of cells with haustoria.
- Suitable for binary classification pipelines (e.g., Keras, PyTorch).

4. yolo_models/
- Directory containing the final trained YOLOv8 model weights.
- Includes:
- gus.pt: YOLOv8 model trained on GUS data.
- haustoria.pt: YOLOv8 model trained on haustoria 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:Hierarchical Model Weights: - .pth files containing trained weights for all alpha regularization values used in hierarchical classification models.MaskRCNN-Segmented Objects: - .jpg files representing segmented objects detected by the MaskRCNN model. - Accompanied by maskrcnn-segmented-objects-dataset.parquet, which includes metadata and classifications: - Columns:masked_image: Path to the segmented image file.confidence: Confidence score for the prediction.predicted_species: Predicted species label.species: True species label.MaskRCNN Weights: - Trained MaskRCNN model weights, including hierarchical CNN models integrated with MaskRCNN in the processing pipeline.Pre-Trained Models:.pt files for all object detectors trained on the Esefjorden Marine Vegetation Segmentation Dataset (EMVSD) in YOLO txt format.Segmented Object Outputs: - Segmentation outputs and datasets for the following models: - RT-DETR: - Segmented objects: rtdetr-segmented-objects/ - Dataset: rtdetr-segmented-objects-dataset.parquet - YOLO-SAG: - Segmented objects: yolosag-segmented-objects/ - Dataset: yolosag-segmented-objects-dataset.parquet - YOLOv11: - Segmented objects: yolov11-segmented-objects/ - Dataset: yolov11-segmented-objects-dataset.parquet - YOLOv8: - Segmented objects: yolov8-segmented-objects/ - Dataset: yolov8-segmented-objects-dataset.parquet - YOLOv9: - Segmented objects: yolov9-segmented-objects/ - Dataset: yolov9-segmented-objects-dataset.parquetUsage Instructions: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/FjordVisionReproducibility: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.Licensing:This dataset is released under the CC-BY 4.0 license, permitting reuse with proper attribution.Related Materials:- GitHub Repository: https://github.com/Ci2Lab/FjordVision

BackgroundUrogenital schistosomiasis is considered a Neglected Tropical Disease (NTD) by the World Health Organization (WHO). It is estimated to affect 150 million people worldwide, with a high relevance in resource-poor settings of the African continent. The gold-standard diagnosis is still direct observation of Schistosoma haematobium eggs in urine samples by optical microscopy. Novel diagnostic techniques based on digital image analysis by Artificial Intelligence (AI) tools are a suitable alternative for schistosomiasis diagnosis.MethodologyDigital images of 24 urine sediment samples were acquired in non-endemic settings. S. haematobium eggs were manually labeled in digital images by laboratory professionals and used for training YOLOv5 and YOLOv8 models, which would achieve automatic detection and localization of the eggs. Urine sediment images were also employed to perform binary classification of images to detect erythrocytes/leukocytes with the MobileNetv3Large, EfficientNetv2, and NasNetLarge models. A robotized microscope system was employed to automatically move the slide through the X-Y axis and to auto-focus the sample.ResultsA total number of 1189 labels were annotated in 1017 digital images from urine sediment samples. YOLOv5x training demonstrated a 99.3% precision, 99.4% recall, 99.3% F-score, and 99.4% mAP0.5 for S. haematobium detection. NasNetLarge has an 85.6% accuracy for erythrocyte/leukocyte detection with the test dataset. Convolutional neural network training and comparison demonstrated that YOLOv5x for the detection of eggs and NasNetLarge for the binary image classification to detect erythrocytes/leukocytes were the best options for our digital image database.ConclusionsThe development of low-cost novel diagnostic techniques based on the detection and identification of S. haematobium eggs in urine by AI tools would be a suitable alternative to conventional microscopy in non-endemic settings. This technical proof-of-principle study allows laying the basis for improving the system, and optimizing its implementation in the laboratories.

Summary of the urine sediment sample image database.