Welcome to RDK X5 Board repository
07.Oriented bounding box object detection
Oriented Bounding Box Object Detection
Oriented Bounding Box Object Detection1. Model Introduction2. Oriented Bounding Box Object Detection: ImagesEffect Preview3. Oriented Bounding Box Object Detection: VideosEffect Preview4. Oriented Bounding Box Object Detection: Real-time Detection4.1. USB CameraEffect Preview4.2. CSI CameraEffect PreviewReferences
Use Python to demonstrate Ultralytics: Oriented Bounding Boxes Object Detection effects on images, videos, and real-time detection.
1. Model Introduction
Oriented bounding box object detection, also called oriented object detection, goes a step further than standard object detection by introducing an additional angle to more accurately locate objects in images.
The output of an oriented object detector is a set of rotated bounding boxes that precisely surround objects in images, along with class labels and confidence scores for each bounding box. Oriented bounding boxes are particularly useful when objects appear at different angles, for example in aerial images, where traditional axis-aligned bounding boxes might contain unnecessary background.
Simply put, oriented object detection can use tilted boxes to precisely surround tilted objects, thereby reducing unnecessary background areas and improving detection accuracy.
2. Oriented Bounding Box Object Detection: Images
Use yolo26n-obb_ncnn_model to predict images in the ultralytics26 folder (not images that come with ultralytics).
Enter the code folder:
cd /home/sunrise/ultralytics26/yahboom_demo
Run the code:
xxxxxxxxxxpython3 05.obb_image.py
Effect Preview
yolo recognition output image location: /home/sunrise/ultralytics26/output/
Example code:
xfrom ultralytics import YOLO# Load a modelmodel = YOLO("/home/sunrise/ultralytics26/yolo26n-obb_ncnn_model")# model = YOLO("/home/sunrise/ultralytics26/yolo26n-obb.pt")# Run batched inference on a list of imagesresults = model("/home/sunrise/ultralytics26/assets/car.jpg") # return a list of Results objects# Process results listfor 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="/home/sunrise/ultralytics26/output/car_output.jpg") # save to disk3. Oriented Bounding Box Object Detection: Videos
Use yolo26n-obb_ncnn_model to predict videos in the ultralytics26 folder (not videos that come with ultralytics).
Enter the code folder:
xxxxxxxxxxcd /home/sunrise/ultralytics26/yahboom_demo
Run the code:
xxxxxxxxxxpython3 05.obb_video.py
Effect Preview
yolo recognition output video location: /home/sunrise/ultralytics26/output/
Example code:
xxxxxxxxxximport cv2from ultralytics import YOLO# Load the YOLO modelmodel = YOLO("/home/sunrise/ultralytics26/yolo26n-obb_ncnn_model")# model = YOLO("/home/sunrise/ultralytics26/yolo26n-obb.pt")# Open the video filevideo_path = "/home/sunrise/ultralytics26/videos/street.mp4"cap = cv2.VideoCapture(video_path)# Get the video frame size and frame rateframe_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))fps = int(cap.get(cv2.CAP_PROP_FPS))# Define the codec and create a VideoWriter object to output the processed videooutput_path = "/home/sunrise/ultralytics26/output/05.street_output.mp4"fourcc = cv2.VideoWriter_fourcc(*'mp4v') # You can use 'XVID' or 'mp4v' depending on your platformout = cv2.VideoWriter(output_path, fourcc, fps, (frame_width, frame_height))# Loop through the video frameswhile cap.isOpened(): # Read a frame from the video success, frame = cap.read() if success: # Run YOLO inference on the frame results = model(frame) # Visualize the results on the frame annotated_frame = results[0].plot() # Write the annotated frame to the output video file out.write(annotated_frame) # Display the annotated frame cv2.imshow("YOLO Inference", cv2.resize(annotated_frame, (640, 480))) # Break the loop if 'q' is pressed if cv2.waitKey(1) & 0xFF == ord("q"): break else: # Break the loop if the end of the video is reached break# Release the video capture and writer objects, and close the display windowcap.release()out.release()cv2.destroyAllWindows()4. Oriented Bounding Box Object Detection: Real-time Detection
4.1. USB Camera
Use yolo26n-obb_ncnn_model to predict USB camera footage.
Enter the code folder:
xxxxxxxxxxcd /home/sunrise/ultralytics26/yahboom_demo
Run the code: Click on the preview screen, press q key to terminate the program!
xxxxxxxxxxpython3 05.obb_camera_usb.py
Effect Preview
yolo recognition output video location: /home/sunrise/ultralytics26/output/
Example code:
xxxxxxxxxximport cv2from ultralytics import YOLO# Load the YOLO modelmodel = YOLO("/home/sunrise/ultralytics26/yolo26n-obb_ncnn_model")# model = YOLO("/home/sunrise/ultralytics26/yolo26n-obb.pt")# Open the cammeracap = cv2.VideoCapture(0)cap.set(6, cv2.VideoWriter.fourcc('M', 'J', 'P', 'G'))cap.set(cv2.CAP_PROP_FRAME_WIDTH, 640)cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 480)# Get the video frame size and frame rateframe_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))fps = int(cap.get(cv2.CAP_PROP_FPS))# Define the codec and create a VideoWriter object to output the processed videooutput_path = "/home/sunrise/ultralytics26/output/05.obb_camera_usb.mp4"fourcc = cv2.VideoWriter_fourcc(*'mp4v') # You can use 'XVID' or 'mp4v' depending on your platformout = cv2.VideoWriter(output_path, fourcc, fps, (frame_width, frame_height))# Loop through the video frameswhile cap.isOpened(): # Read a frame from the video success, frame = cap.read() if success: # Run YOLO inference on the frame results = model(frame) # Visualize the results on the frame annotated_frame = results[0].plot() # Write the annotated frame to the output video file out.write(annotated_frame) # Display the annotated frame cv2.imshow("YOLO Inference", cv2.resize(annotated_frame, (640, 480))) # Break the loop if 'q' is pressed if cv2.waitKey(1) & 0xFF == ord("q"): break else: # Break the loop if the end of the video is reached break# Release the video capture and writer objects, and close the display windowcap.release()out.release()cv2.destroyAllWindows()4.2. CSI Camera
Use yolo26n-obb_ncnn_model to predict CSI camera footage.
Enter the code folder:
xxxxxxxxxxcd /home/sunrise/ultralytics26/yahboom_demo
Run the code: Click on the preview screen, press q key to terminate the program!
xxxxxxxxxxpython3 05.obb_camera_csi.py
When this prompt appears in the running terminal, press 2, then press Enter,
Effect Preview
yolo recognition output video location: /home/sunrise/ultralytics26/output/
Example code:
xxxxxxxxxximport cv2from SunriseRobotLib import Mipi_Camerafrom ultralytics import YOLOwidth=640height=480g_camera = Mipi_Camera(width, height, debug=False)# Load the YOLO11 modelmodel = YOLO("/home/sunrise/ultralytics26/yolo26n-obb_ncnn_model")# model = YOLO("/home/sunrise/ultralytics26/yolo26n-obb.pt")# Set up video outputoutput_path = "/home/sunrise/ultralytics26/output/05.obb_camera_csi.mp4"fourcc = cv2.VideoWriter_fourcc(*'mp4v')out = cv2.VideoWriter(output_path, fourcc, 30, (640, 480))# Loop through the video frameswhile True: # Capture frame-by-frame ret, frame = g_camera.