Dronescape: A High-Resolution Drone Footage Dataset for Tree Region Segmentation

Dronescape presents a dataset comprising 25 drone videos showcasing vast areas filled with trees, rivers, and mountains. The dataset includes two subsets: 25 videos with tree segmentation and 25 videos without tree segmentation, offering diverse perspectives on the presence and absence of segmented tree regions. The dataset focuses on highlighting the regions containing trees using the SAM (Segment Anything Model) and Track Anything library. Video object tracking and segmentation techniques are utilized to track the regions of trees throughout the dataset. Each video offers diverse perspectives, camera angles, and lighting conditions, providing rich visual content for analysis and research. The dataset includes annotations in the form of masks, indicating the location and extent of tree regions within each frame. This dataset can be utilized for various applications such as object detection, segmentation, tracking algorithms, ecological studies, environmental monitoring, and urban planning projects. Researchers and developers may encounter challenges related to lighting variations, occlusions, camera motion, and accurate tracking of tree regions while working with this dataset