How To Train YOLOv5-OBB (Oriented Bounding Boxes) custom object detection
Learn how to train your Roboflow Computer Vision dataset with YOLOv5-OBB.
✅ Subscribe: https://bit.ly/rf-yt-sub
Oriented bounding boxes are bounding boxes rotated to better fit the objects represented on an angle. Take a pill detection dataset for example. Using YOLOv5-obb we are able to detect objects that are rotated on a given frame or image more tightly and accurately, preventing capture of multiple objects or other objects in one bounding box.
Written guide: https://blog.roboflow.com/yolov5-for-...
Tools:
Colab notebook: https://colab.research.google.com/dri...
Roboflow - https://roboflow.com
GitHub repo - https://github.com/hukaixuan19970627/...
Free datasets - https://universe.roboflow.com/