Welcome to ROSMASTER M3 repository

Oriented object detection.md

Note: Using the Docker container in the factory image does not require re-setting up the environment. The environment is already set up. Simply enter Docker and run the corresponding function commands according to the previous tutorial.

1. Orienting Objects: Images

Use yolo11n-obb.pt to predict images provided with the Ultralytics project.

Go to the code folder:

cd /root/ultralytics/ultralytics/yahboom_demo

Run the code:

xxxxxxxxxx
python3 05.obb_image.py

Preview

Yolo recognition output image location: /root/ultralytics/ultralytics/output/

Sample code:

​x
from ultralytics import YOLO
​
# Load a model
model = YOLO("/root/ultralytics/ultralytics/yolo11n-obb.pt")
# model = YOLO("/root/ultralytics/ultralytics/yolo11n-obb.onnx")
# model = YOLO("/root/ultralytics/ultralytics/yolo11n-obb_ncnn_model")
​
# Run batched inference on a list of images
results = model("/root/ultralytics/ultralytics/assets/car.jpg")  # return a list of Results objects
​
# Process results list
for result in results:
    boxes = result.boxes  # Boxes object for bounding box outputs
    # masks = result.masks  # Masks object for segmentation masks outputs
    # keypoints = result.keypoints  # Keypoints object for pose outputs
    # probs = result.probs  # Probs object for classification outputs
    obb = result.obb  # Oriented boxes object for OBB outputs
    result.show()  # display to screen
    result.save(filename="/root/ultralytics/ultralytics/output/car_output.jpg")  # save to disk
​

2. Oriented Object Detection: Video

Use yolo11n-obb.pt to predict videos in the Ultralytics project (not included with Ultralytics).

Go to the code folder:

xxxxxxxxxx
cd /root/ultralytics/ultralytics/yahboom_demo

Run the code:

xxxxxxxxxx
python3 02.segmentation_video.py

Preview

Yolo recognition output video location: /root/ultralytics/ultralytics/output/

Sample code:

 Image classification
Model conversion