YOLOv8-OBB

Real‑time oriented object detection optimized for mobile and edge by Ultralytics.

Ultralytics YOLOv8‑OBB is a machine learning model that predicts oriented bounding boxes (OBB) and classes of objects in an image. It is designed for detecting objects that are not axis‑aligned, such as aerial imagery or tilted text.

Note: YOLOv8-OBB cannot be downloaded directly due to licensing restrictions. You can export a model ready for on-device deployment using the AI Hub service.

Export with AI Hub

Not supported

This model is currently not supported on any Compute chipset.

To see performance metrics for this model on other chipsets, click the button below.

View for other chipsets

Model Repository Hugging Face Research Paper

Technical Details

Model checkpoint:YOLOv8-N-OBB

Input resolution:640*640

Model size (float):12.1 MB

Model size (w8a8):3.53 MB

Model size (w8a8_mixed_int16):3.62 MB

Model size (w8a16):3.55 MB

Applicable Scenarios

Aerial Imagery Analysis
Warehouse Logistics
Text Detection
Robotic Navigation

License

Tags

real-time

Supported Compute Devices

Snapdragon X Elite CRD
Snapdragon X Plus 8-Core CRD
Snapdragon X2 Elite CRD

Supported Compute Chipsets

Snapdragon® X Elite
Snapdragon® X Plus 8-Core
Snapdragon® X2 Elite

Related Models

YOLOv8-Detection

Real-time object detection optimized for mobile and edge by Ultralytics.

Yolo-v6

Real-time object detection optimized for mobile and edge.

Yolo-v7

Real-time object detection optimized for mobile and edge.

Looking for more? See models created by industry leaders.

Discover Model Makers