试试background subtraction。
使用cv2.subtract(img1,img2)代替算术运算，因为cv2会处理负值。

如果两张图片中的背景完全相同，您可以将它们减去，就像您在帖子中提到的那样。

image1 = imread("/path/to/image1")
image2 = imread("/path/to/image2")
image3 = image1 - image2

字符串

@dvigneshwr的答案做减法，其中得到的负值向上舍入为0。@Taha Anwar M-Holmes的答案保留了否定的结果，但改变了结果数组的数据类型，因此它不再是传统的图像类型。
对于那些希望根据 * 绝对值差 * 从背景图像中识别前景并返回与输入相同数据类型的数组的人（这就是我在这里结束的原因），使用absdiff。
假设数组的宽度和高度都一样……

import cv2 as cv

image3 = cv.absdiff(image1, image2)

字符串
值得注意的是，OP没有提供任何细节wrt的图像被减去在这里...根据图像的内容，所有这些方法都可以回答OP的问题。

cv2.subtract不工作，它只是绑定0-255之间的值，所以如果你想得到负值，只需将图像从unit 8转换为int 32或int 64。注意unint 8只能接受0-255的值，因此它不能处理负值。

image1= np.int32(image1)

image2= np.int32(image2)

image3 = image1 - image2

字符串

# find moving image.
#
# running the program pops up a window to watch the video.
# the program video window shows the first monitor,
# but watch the program video window on second extended monitor

import cv2
import numpy as np

# Path to video file
cap = cv2.VideoCapture(
    1,
    apiPreference=cv2.CAP_ANY,
    params=[cv2.CAP_PROP_FRAME_WIDTH, 1280, cv2.CAP_PROP_FRAME_HEIGHT, 720],
)  # I made cap = 1280, 720 resolution to speed the program up on my computer. I have a rtx 3060, obs studio at 60 fps

# Used as counter variable
count = 1

# checks whether frames were extracted
success = 1

# create frame_1 and frame_2 to be able to use the frames between if conditions
frame_1 = 0
frame_2 = 0

# get 2 frames to start with
count_subtraction = 0

while success:

    # function extract frames
    success, image = cap.read()

    if count_subtraction == 0:
        if count <= 2:
            # Saves the frames with frame-count
            cv2.imwrite("frame_%d.jpg" % count, image, [int(cv2.IMWRITE_JPEG_QUALITY), 100])  # jpg 100% quality

            count += 1

        if count == 3:

            frame_1 = cv2.imread("frame_1.jpg", 0)
            frame_2 = cv2.imread("frame_2.jpg", 0)

            # use the frames below

            # Create the sharpening kernel
            kernel = np.array([[0, -1, 0], [-1, 5, -1], [0, -1, 0]])

            # Sharpen the image
            frame_1 = cv2.filter2D(frame_1, -1, kernel)
            frame_2 = cv2.filter2D(frame_2, -1, kernel)

            # subtract the images
            subtracted = cv2.subtract(frame_2, frame_1)

            subtracted_sharpened = cv2.filter2D(subtracted, -1, kernel)

            # TO show the output
            cv2.imshow("image", subtracted_sharpened)

            # the else condition to count_subtraction needs a first frame
            frame_1 = frame_2

            count = 1
            count_subtraction = 1

    else:

        cv2.imwrite("frame_2.jpg", image, [int(cv2.IMWRITE_JPEG_QUALITY), 100])  # jpg 100% quality

        frame_2 = cv2.imread("frame_2.jpg", 0)

        # use the frames below

        # Create the sharpening kernel
        kernel = np.array([[0, -1, 0], [-1, 5, -1], [0, -1, 0]])

        # Sharpen the image
        frame_2 = cv2.filter2D(frame_2, -1, kernel)

        # subtract the images
        subtracted = cv2.subtract(frame_2, frame_1)

        subtracted_sharpened = cv2.filter2D(subtracted, -1, kernel)

        # TO show the output
        cv2.imshow("image", subtracted_sharpened)

        # the second frame becomes a first frame
        frame_1 = frame_2

    if cv2.waitKey(1) & 0xFF == ord("q"):
        break

# When everything done, release the capture
cap.release()
cv2.destroyAllWindows()

字符串