3.6

缩放盒

当向上或向下缩放图像时，可以使用 ultralytics.utils.ops.scale_boxes.

import cv2 as cv
import numpy as np

from ultralytics.utils.ops import scale_boxes

image = cv.imread("ultralytics/assets/bus.jpg")
h, w, c = image.shape
resized = cv.resize(image, None, (), fx=1.2, fy=1.2)
new_h, new_w, _ = resized.shape

xyxy_boxes = np.array(
    [
        [22.878, 231.27, 804.98, 756.83],
        [48.552, 398.56, 245.35, 902.71],
        [669.47, 392.19, 809.72, 877.04],
        [221.52, 405.8, 344.98, 857.54],
        [0, 550.53, 63.01, 873.44],
        [0.0584, 254.46, 32.561, 324.87],
    ]
)

new_boxes = scale_boxes(
    img1_shape=(h, w),  # original image dimensions
    boxes=xyxy_boxes,  # boxes from original image
    img0_shape=(new_h, new_w),  # resized image dimensions (scale to)
    ratio_pad=None,
    padding=False,
    xywh=False,
)

print(new_boxes)  
# >>> array(
#     [[  27.454,  277.52,  965.98,   908.2],
#     [   58.262,  478.27,  294.42,  1083.3],
#     [   803.36,  470.63,  971.66,  1052.4],
#     [   265.82,  486.96,  413.98,    1029],
#     [        0,  660.64,  75.612,  1048.1],
#     [   0.0701,  305.35,  39.073,  389.84]]
# )

边框格式转换

XYXY → XYWH

将边界框坐标从 (x1, y1, x2, y2) 格式转换为 (x, y, width, height) 格式，其中 (x1, y1) 为左上角，(x2, y2) 为右下角。

import numpy as np

from ultralytics.utils.ops import xyxy2xywh

xyxy_boxes = np.array(
    [
        [22.878, 231.27, 804.98, 756.83],
        [48.552, 398.56, 245.35, 902.71],
        [669.47, 392.19, 809.72, 877.04],
        [221.52, 405.8, 344.98, 857.54],
        [0, 550.53, 63.01, 873.44],
        [0.0584, 254.46, 32.561, 324.87],
    ]
)
xywh = xyxy2xywh(xyxy_boxes)

print(xywh)
# >>> array(
#     [[ 413.93,  494.05,   782.1, 525.56],
#     [  146.95,  650.63,   196.8, 504.15],
#     [   739.6,  634.62,  140.25, 484.85],
#     [  283.25,  631.67,  123.46, 451.74],
#     [  31.505,  711.99,   63.01, 322.91],
#     [   16.31,  289.67,  32.503,  70.41]]
# )

所有边框转换

from ultralytics.utils.ops import (
    ltwh2xywh,
    ltwh2xyxy,
    xywh2ltwh,  # xywh → top-left corner, w, h
    xywh2xyxy,
    xywhn2xyxy,  # normalized → pixel
    xyxy2ltwh,  # xyxy → top-left corner, w, h
    xyxy2xywhn,  # pixel → normalized
)

for func in (ltwh2xywh, ltwh2xyxy, xywh2ltwh, xywh2xyxy, xywhn2xyxy, xyxy2ltwh, xyxy2xywhn):
    print(help(func))  # print function docstrings