Add to Favourites
To login click here
This article introduces the first dataset for goat detection, containing 6160 annotated images of goats captured under varying environmental conditions. The images were collected from field surveys and annotated with pixel-level bounding boxes around the goat’s body. The dataset is intended for use in developing machine learning algorithms for goat detection, with potential applications in precision agriculture, wildlife conservation, animal welfare, and animal husbandry. Additionally, the dataset can be used as a benchmark for evaluating existing detection methods. Microsoft COCO and PASCAL VOC are two widely used benchmark datasets for object detection and instance segmentation, but neither of them contain a goat class.