cv2.warpPerspective调用异常：透视变换白屏及maxWidth为0问题

按左上角、左下角、右下角、右上角顺序标记四点后，Warped窗口仅显示白屏，无法得到预期变换图像。此外，four_point_transform函数中maxWidth变量值几乎始终为0，不清楚诱因。

环境配置 #

• Windows 11 64位
• Python 3.10.7
• opencv-contrib-python 4.5.5.62

相关截图 #

问题代码 #

import numpy
import cv2
import numpy as np


def on_click(event, x, y, flags, param):
    global a_, b_, c_, d_, to_set
    if event == cv2.EVENT_LBUTTONDOWN:
        print("click")
        if to_set == 0:
            to_set = 1
            a_ = [x, y]
        elif to_set == 1:
            to_set = 2
            b_ = [x, y]
        elif to_set == 2:
            to_set = 3
            c_ = [x, y]
        elif to_set == 3:
            to_set = 0
            d_ = [x, y]


def order_points(pts):
    # initialzie a list of coordinates that will be ordered
    # such that the first entry in the list is the top-left,
    # the second entry is the top-right, the third is the
    # bottom-right, and the fourth is the bottom-left
    rect = np.zeros((4, 2), dtype="float32")

    # the top-left point will have the smallest sum, whereas
    # the bottom-right point will have the largest sum
    s = pts.sum(axis=1)
    rect[0] = pts[np.argmin(s)]
    rect[2] = pts[np.argmax(s)]

    # now, compute the difference between the points, the
    # top-right point will have the smallest difference,
    # whereas the bottom-left will have the largest difference
    diff = np.diff(pts, axis=1)
    rect[1] = pts[np.argmin(diff)]
    rect[3] = pts[np.argmax(diff)]

    # return the ordered coordinates
    return rect


def four_point_transform(image, pts):
    # obtain a consistent order of the points and unpack them
    # individually
    rect = order_points(pts)
    (tl, tr, br, bl) = rect

    # compute the width of the new image, which will be the
    # maximum distance between bottom-right and bottom-left
    # x-coordiates or the top-right and top-left x-coordinates
    widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
    widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
    maxWidth = max(int(widthA), int(widthB))

    # compute the height of the new image, which will be the
    # maximum distance between the top-right and bottom-right
    # y-coordinates or the top-left and bottom-left y-coordinates
    heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
    heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
    maxHeight = max(int(heightA), int(heightB))

    # now that we have the dimensions of the new image, construct
    # the set of destination points to obtain a "birds eye view",
    # (i.e. top-down view) of the image, again specifying points
    # in the top-left, top-right, bottom-right, and bottom-left
    # order
    dst = np.array([
        [0, 0],
        [maxWidth - 1, 0],
        [maxWidth - 1, maxHeight - 1],
        [0, maxHeight - 1]], dtype="float32")

    # compute the perspective transform matrix and then apply it
    M = cv2.getPerspectiveTransform(rect, dst)
    warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))

    # return the warped image
    return warped


#cap = cv2.VideoCapture(1, cv2.CAP_DSHOW)
cv2.namedWindow("Corner points")
cv2.setMouseCallback("Corner points", on_click)
to_set = 0
a_ = b_ = c_ = d_ = [0, 0]
while True:
    big_img = cv2.imread("Test.png")
    #_, big_img = cap.read()
    ratio = big_img.shape[0] / 500.0
    org = big_img.copy()
    img = imutils.resize(big_img, height=500)
    cv2.putText(img, f"{to_set}", (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0))
    values = numpy.array([a_,
                          b_,
                          c_,
                          d_], dtype="float32")
    warped = four_point_transform(org, values * ratio)
    cv2.circle(img, a_, 5, (0, 0, 255))
    cv2.circle(img, b_, 5, (0, 0, 255))
    cv2.circle(img, c_, 5, (0, 0, 255))
    cv2.circle(img, d_, 5, (0, 0, 255))
    cv2.imshow("Warped", warped)
    cv2.imshow('Corner points', img)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break
cv2.destroyAllWindows()

问题排查与解决 #

1. 核心问题：初始点未赋值导致maxWidth为0 #

程序启动时a_、b_、c_、d_初始化为[0,0]，此时传入four_point_transform的四个点都是原点，计算出的widthA和widthB都是0，maxWidth自然为0，变换后得到1x1的白图（因为maxWidth-1=0）。

且循环中每次都会重新读取图片，未判断四个点是否全部标记完成，只要没完成四次点击，就会有部分点还是初始的[0,0]，依然会计算出错误尺寸。

2. 次要问题：缺失imutils导入 #

代码中使用imutils.resize但未导入库，需补上：

import imutils

3. 修正后的完整代码 #

import numpy
import cv2
import numpy as np
import imutils  # 补上缺失的导入


def on_click(event, x, y, flags, param):
    global a_, b_, c_, d_, to_set
    if event == cv2.EVENT_LBUTTONDOWN:
        print("click")
        if to_set == 0:
            to_set = 1
            a_ = [x, y]
        elif to_set == 1:
            to_set = 2
            b_ = [x, y]
        elif to_set == 2:
            to_set = 3
            c_ = [x, y]
        elif to_set == 3:
            to_set = 0
            d_ = [x, y]


def order_points(pts):
    rect = np.zeros((4, 2), dtype="float32")
    s = pts.sum(axis=1)
    rect[0] = pts[np.argmin(s)]
    rect[2] = pts[np.argmax(s)]
    diff = np.diff(pts, axis=1)
    rect[1] = pts[np.argmin(diff)]
    rect[3] = pts[np.argmax(diff)]
    return rect


def four_point_transform(image, pts):
    rect = order_points(pts)
    (tl, tr, br, bl) = rect

    widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
    widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
    maxWidth = max(int(widthA), int(widthB))

    heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
    heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
    maxHeight = max(int(heightA), int(heightB))

    dst = np.array([
        [0, 0],
        [maxWidth - 1, 0],
        [maxWidth - 1, maxHeight - 1],
        [0, maxHeight - 1]], dtype="float32")

    M = cv2.getPerspectiveTransform(rect, dst)
    warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))
    return warped


cv2.namedWindow("Corner points")
cv2.setMouseCallback("Corner points", on_click)
to_set = 0
a_ = b_ = c_ = d_ = [0, 0]
# 标记是否完成四个点的选择
points_selected = False

while True:
    big_img = cv2.imread("Test.png")
    ratio = big_img.shape[0] / 500.0
    org = big_img.copy()
    img = imutils.resize(big_img, height=500)
    cv2.putText(img, f"Current point to mark: {to_set+1}", (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0))
    
    # 绘制已标记的点
    if to_set >=1:
        cv2.circle(img, a_, 5, (0, 0, 255), -1)
    if to_set >=2:
        cv2.circle(img, b_, 5, (0, 0, 255), -1)
    if to_set >=3:
        cv2.circle(img, c_, 5, (0, 0, 255), -1)
    if to_set ==0 and a_ != [0,0]:  # 完成四个点标记
        cv2.circle(img, d_, 5, (0, 0, 255), -1)
        points_selected = True
    
    # 只有完成四个点标记后才执行变换
    if points_selected:
        values = numpy.array([a_, b_, c_, d_], dtype="float32")
        warped = four_point_transform(org, values * ratio)
        cv2.imshow("Warped", warped)
    else:
        # 未完成标记时显示提示图
        empty_img = np.zeros((500,500,3), dtype=np.uint8)
        cv2.putText(empty_img, "Please mark 4 points in order", (20,250), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (255,255,255))
        cv2.imshow("Warped", empty_img)

    cv2.imshow('Corner points', img)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break
cv2.destroyAllWindows()

4. 额外注意事项 #

• 标记点时尽量按照提示顺序（左上角→左下角→右下角→右上角），order_points函数会重新排序，但保证输入准确性能减少异常
• 确保Test.png与脚本在同一目录，或使用绝对路径避免读取失败
• 变换后的窗口尺寸由标记四点自动计算，适配目标区域大小

内容的提问来源于stack exchange，提问作者user19345539