can’t send the bounding boxes of the objects I detect to the function

Question

I am doing object detection using yolov8 and sahi algorithms. I am writing a function to test whether some of the objects I detect are round or not, but I can’t send the bounding boxes of the objects I detect to the function.

def is_circle(image, bbox):
    img = cv.cvtColor(image, cv.COLOR_BGR2GRAY)
    x, y, w, h = bbox
    roi = img[y:y + h, x:x + w]
    edges = cv.Canny(roi, 50, 150, apertureSize=3)
    circles = cv.HoughCircles(edges, cv.HOUGH_GRADIENT, 1, 20, param1=50, param2=30, minRadius=0, maxRadius=0)
    return circles is not None



detection_model = AutoDetectionModel.from_pretrained(
    model_type='yolov8',
    model_path="C:/Users/UGURHANDASDEMIR/PycharmProjects/pythonProject1/best.pt",
    confidence_threshold=0.5,
    device="cuda:0", # or 'cuda:0'
)


image_dir = "img"
image_paths = [os.path.join(image_dir, image_name) for image_name in os.listdir(image_dir) if image_name.endswith(('.png', '.jpg', '.jpeg'))]


for image_path in image_paths:
    image = read_image(image_path)

    result = get_sliced_prediction(
        image,
        detection_model,
        slice_height = 1920,
        slice_width =1080 ,
        overlap_height_ratio = 0.5,
        overlap_width_ratio = 0.5
    )


    for prediction in result.object_prediction_list:
        print(prediction.category.name)

        if prediction.category.name == 'uap' or prediction.category.name == 'uai' :
            bbox = prediction.bbox
            is_circle(image,bbox)
        else:
            inis_durumu=-1



I am getting the following error from this code:

Traceback (most recent call last):
  File "C:\Users\UGURHANDASDEMIR\PycharmProjects\pythonProject1\dene.py", line 52, in <module>
    is_circle(image,bbox)
  File "C:\Users\UGURHANDASDEMIR\PycharmProjects\pythonProject1\dene.py", line 14, in is_circle
    x, y, w, h = bbox
    ^^^^^^^^^^
TypeError: cannot unpack non-iterable BoundingBox object

Please help