The YOLOv8 Oriented Bounding Boxes (OBB) format is used to train a YOLOv8-OBB model. This model can return angled bounding boxes that more precisely surround an object of interest.
YOLOv8-OBB coordinates are normalized between 0 and 1.
Below, learn the structure of YOLOv8 Oriented Bounding Boxes.
class_index, x1, y1, x2, y2, x3, y3, x4, y4
With Roboflow supervision, an open source Python package with utilities for completing computer vision tasks, you can merge and split detections in YOLOv8 Oriented Bounding Boxes. Read our dedicated guides to learn how to merge and split YOLOv8 Oriented Bounding Boxes detections.
Below, see model architectures that require data in the YOLOv8 Oriented Bounding Boxes format when training a new model.
On each page below, you can find links to our guides that show how to plot predictions from the model, and complete other common tasks like detecting small objects with the model.