Bird Vs Drone Bird and Drone Image Classification Dataset

Unmanned aerial vehicles (UAVs), or drones, have seen dramatic growth in both commercial and recreational use, but this proliferation has created serious safety concerns. Drones can pose risks to people, infrastructure, and air traffic if they are misidentified or undetected, especially when they are confused with other aerial objects, such as birds. To overcome this challenge, accurate detection systems are critical.

This dataset aims to fill this gap and enable the development and fine-tuning of models to better identify drones and birds in various environments. The dataset contains a diverse collection of images from the Pexel website, representing birds and drones in motion. These images are captured from video frames, segmented, enhanced, and pre-processed to simulate different environmental conditions, thereby enhancing the model training process.

The Bird vs Drone dataset is formatted according to the YOLOv7 PyTorch specification and is divided into three folders: Test, Train, and Valid. Each folder contains two subfolders – Images and Labels – the Labels folder contains relevant metadata in plain text format. These metadata provide valuable information about the objects detected in each image, enabling the model to accurately learn and detect drones and birds in different situations. The dataset contains a total of 20,925 images, all with a resolution of 640 x 640 pixels and JPEG format, providing comprehensive training and validation opportunities for machine learning models.

• Test Folder: Contains 889 images (drone and bird images). This folder has subcategories labeled BT (bird test images) and DT (drone test images).
• Train Folder: This folder has a total of 18,323 images, including drone and bird images, also divided into BT and DT categories.
• Valid folders: Contains 1,740 images. The images in this folder are also divided into BT and DT.