xView1 Adapted for YOLOv5 in Colab

Overview:

This dataset is a modified version of the xView1 dataset, specifically tailored for seamless integration with YOLOv5 in Google Colab. The xView1 dataset originally consists of high-resolution satellite imagery labeled for object detection tasks. In this adapted version, we have preprocessed the data and organized it to facilitate easy usage with YOLOv5, a popular deep learning framework for object detection.

Dataset Contents:

Images: The dataset includes a collection of high-resolution satellite images covering diverse geographic locations. These images have been resized and preprocessed to align with the requirements of YOLOv5, ensuring efficient training and testing.

Annotations:

Object annotations are provided for each image, specifying the bounding boxes and class labels of various objects present in the scenes. The annotations are formatted to match the YOLOv5 input specifications.

Usage Instructions:

1. Download the dataset files, including images and annotations.
2. Clone the YOLOv5 repository in Colab.
3. Move dataset files (train.txt and val.txt) to the yolov5 directory.
4. Use the provided .yaml for training.

Food Ingredient Recognition

## Overview

Food Ingredient Recognition is a dataset for object detection tasks - it contains Food Ingredients annotations for 5,205 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).

Preprocessed dataset for Tsinghua Dogs in YOLOv5 format.. Ground truth labels for head bounding boxes, body bounding boxes

Preprocessed dataset for Oxford-IIIT Pet in YOLOv5 format.. Ground truth labels for head bounding boxes, body bounding boxes (derived from segmentation mask).

Yolov5 predicted images with 3-channel windowing technique: 1. windowing: 1) window = 1800, level = 400 2) window = 2800, level = 600 3) window = 4000, level = 700

1. Yolov5 predicted images: 1) 'yolo_image' has Yolov5 preprocessed and cropped image in .jpg 2) 'yolo_seg' has cropped segmentation image in .npz

🩻 Scoliosis Spine Detection Dataset (YOLOv5 Ready)

This dataset is a curated and preprocessed version of a Scoliosis Spine X-ray dataset, designed specifically for deep learning–based object detection and classification tasks using frameworks like YOLOv5, YOLOv8, and TensorFlow Object Detection API.

It contains annotated spinal X-ray images categorized into three classes, representing different spinal conditions.

🧩 Dataset Configuration

train: scoliosis2.v16i.tensorflow/images/train
val: scoliosis2.v16i.tensorflow/images/valid
test: scoliosis2.v16i.tensorflow/images/test

nc: 3
names: ['Vertebra', 'scoliosis spine', 'normal spine']

⚙️ Data Details

• Train Set: /images/train
• Validation Set: /images/valid
• Test Set: /images/test
• Total Classes: 3
• Annotations: YOLO format (.txt files with class, x_center, y_center, width, height)
• Image Format: .jpg / .png

Classes Description:

1. Vertebra — Labeled vertebral regions used for bone localization.
2. Scoliosis Spine — X-rays showing curvature or deformity in the spinal structure.
3. Normal Spine — Healthy, straight spinal alignment without scoliosis signs.

🧠 Augmentations Applied

To enhance diversity and model robustness, the dataset was augmented using:

• Rotation
• Brightness and contrast adjustment
• Horizontal flip
• Random zoom and cropping
• Gaussian noise

🎯 Use Cases

This dataset is ideal for:

• Scoliosis detection and classification research
• Vertebra localization and spine anomaly detection
• Medical object detection experiments (YOLOv5, YOLOv8, EfficientDet)
• Transfer learning on medical X-ray datasets
• Explainable AI and model comparison studies

📊 Source

The dataset was preprocessed and labeled using Roboflow, then manually refined and balanced for research use. Originally derived from a spinal X-ray dataset and adapted for deep learning object detection.

Roboflow Project Link: 🔗 View on Roboflow (add your Roboflow link here)

🧾 License

CC BY 4.0 — Free to use, modify, and share with attribution.

Would you like me to make a short summary version (under 1000 characters) for the “Short Description” field on Kaggle too? It’s required for the dataset card.

Why this dataset

Efficient detection of craters can be of vital significance in various space exploration missions. Previous researches have already made significant progress on this task, however the versatility and robustness of existing methods are still limited. While modern object detection methods using deep learning is gaining popularity and is probably a solution to aforementioned problems, public-accessible data for training is hard to find. This is the primary reason we propose this dataset.

What's in the dataset

The dataset mainly contains: * Image Data: Images of Mars and Moon surface which MAY contain craters. The data source is mixed. For Mars images, images are mainly from ASU and USGS; Currently all Moon images are from NASA Lunar Reconnaissance Orbiter mission. All images are preprocessed with RoboFlow to remove EXIF rotation and resize to 640*640. * Labels: Each image has its associated labelling file in YOLOv5 text format. The anotation work was performed by ourselves, and mainly serves the purpose of object detection. * Trained YOLOv5 model file: For each new version, we will upload our pretrained YOLOv5 model file using the latest version of data. The network strcture currently in use is YOLOv5m6.

Methods to use

This dataset is somewhat challenging compared to trivial object detection task: * Craters can greatly vary in size * The dataset combines Mars and Moon surface images, where craters can be different in shape/color etc. * Currently only around 100 images are available for training (if train-test-valid split is performed). However, please notice that more images will be added in the future.

In our own training with YOLOv5 framework using YOLOv5m6 pretrained model, we achieve a mAP_0.5 score of 0.6919. A sample notebook explaining the procedure is available in the Code section. Below are two sample detection results using our trained model (None of them are used in training process).

https://raw.githubusercontent.com/Lincoln-Zhou/Archived/master/015_png.rf.7d5b2091b6339c9480a171a59c52c3b9.jpg" alt="Mars surface detection sample">

https://raw.githubusercontent.com/Lincoln-Zhou/Archived/master/mars_crater--100-_jpg.rf.a2ad5867efb2d73e86d9d980ca40a9fe.jpg" alt="Moon surface detection sample">

This dataset is also available on the RoboFlow platform.

Credits

This dataset is a mixture of various data sources, we would like to thank each individual who participated. A detailed list of data source will be available soon.

Performance evaluation of YOLOv5 model with direct and indirect integration of traditional features.