Training Custom Dataset YOLOv8 OBB — Oriented Bounding Boxes

YOLOv8 Oriented Object Detection

What is Oriented Bounding Boxes Object Detection?

“Oriented Bounding Boxes Object Detection” refers to the process of identifying and localizing objects in images or videos while also estimating their orientation. This approach is particularly relevant when dealing with objects that exhibit a certain degree of rotation or orientation variation, such as cars, airplanes, or text.

The output of an oriented object detector is a set of rotated bounding boxes that exactly enclose the objects in the image, along with class labels and confidence scores for each box. Object detection is a good choice when you need to identify objects of interest in a scene, but don’t need to know exactly where the object is or its exact shape.

source: https://mediaan.com/mediaan-blog/oriented-object-detection

How to load model YOLOv8 OBB?

# install ultralytics

pip3 install ultralytics

from ultralytics import YOLO

# Load a model
model = YOLO('yolov8n-obb.pt')  # load an official model

# Predict with the model
results = model('https://miro.medium.com/v2/resize:fit:1400/1*BybWklt3t0M8zdSXtkipRg.png', save=True)  #…