对齐和裁剪相同的场景图像

Question

您好，我有不同的图像采取使用曝光括号（同一场景不同的曝光），我需要对齐的图像，并裁剪每一个，以使他们能够完全匹配。（因为拍摄这些图像时相机会抖动）

我不想合并它们，我只想剪切、旋转或缩放…等等，使它们精确对齐，然后保存它们。如果我知道如何做到这一点，我会添加一个代码示例。但我不知道。我是opencv的新手

下面是一个例子：

这是一个样本的真实例子：（这个样本有一个巨大的偏差，大多数样本只需要小的调整，因为与这个样本不同的是震动）

我需要的是裁剪每个图像，使它们完全相同（只保留共享区域）

谢谢大家!

Answer 1

在这个回答中，我描述了一种实现图像对齐的方法，该方法包括使用欧几里德模型根据中心图像图像2变换图像1（左侧）和图像3（右侧）

但是，我想很快指出，共享的图像非常具有挑战性：不仅对比度有很大差异，而且它们在平移、缩放、旋转，甚至可能有一点剪切方面也有显著差异。事实上，他们被张贴为非常低的分辨率也没有帮助

无论如何，我指出了它们在2D变换方面的差异，因为在选择适当的模型执行图像对齐时，您需要始终牢记这一点This nice picture is from a tutorial that describes the models in greater detail：

该方法包括以下步骤：

• 使用增强相关系数（ECC）算法在图像2和1之间使用欧几里德模型执行图像对齐
• 然后使用返回的变换矩阵借助cv2.warpAffine()变换图像1，并计算图像1中变换的近似矩形面积
• 重复相同的步骤变换图像3：使用增强相关系数（ECC）算法在图像2和图像3之间使用欧几里德模型执行图像对齐
• 然后使用返回的变换矩阵在cv2.warpAffine()的帮助下变换图像3，并计算变换的近似矩形面积
• 这些操作的结果是对齐的图像，可以在下图中看到。绿色矩形显示变换区域：

• 中间图像中的红色矩形（用于创建变换模型的参考图像）是图像1和3上区域之间的交点，可以视为所有3个图像之间的公共区域

• 然后可以使用红色矩形裁剪图像1、2和3，并提供图像对齐的良好外观。请注意，所有这些图像上的地形和天空看起来是如何完美地相互对齐的：

有趣的是，注意到这种方法的成本：因为图像1没有捕获图像2和3上可以很容易看到的所有地形特征，最终的结果是图像2和3最终失去了该部分地形。因此，所有图像显示的都是照片中完全相同的区域

Python源代码：

###
# reference:
#   https://www.learnopencv.com/image-alignment-ecc-in-opencv-c-python/
###
import numpy as np
import cv2

# internalRect: returns the intersection between two rectangles
#
#  p1          p2
#   |                  |
#   |                  |
#   |                  |
#  p4          p3
def internalRect(r1, r2):
    x = 0
    y = 1
    w = 2
    h = 3

    rect1_pt1 = [       r1[x], r1[y]       ]
    rect1_pt2 = [ r1[x]+r1[w], r1[y]       ]
    rect1_pt3 = [ r1[x]+r1[w], r1[y]+r1[h] ]
    rect1_pt4 = [       r1[x], r1[y]+r1[h] ]

    rect2_pt1 = [       r2[x], r2[y]       ]
    rect2_pt2 = [ r2[x]+r2[w], r2[y]       ]
    rect2_pt3 = [ r2[x]+r2[w], r2[y]+r2[h] ]
    rect2_pt4 = [       r2[x], r2[y]+r2[h] ]

    int_pt1   = [ max(rect1_pt1[x], rect2_pt1[x]), max(rect1_pt1[y], rect2_pt1[y]) ]
    int_pt2   = [ min(rect1_pt2[x], rect2_pt2[x]), max(rect1_pt2[y], rect2_pt2[y]) ]
    int_pt3   = [ min(rect1_pt3[x], rect2_pt3[x]), min(rect1_pt3[y], rect2_pt3[y]) ]
    int_pt4   = [ max(rect1_pt4[x], rect2_pt4[x]), min(rect1_pt4[y], rect2_pt4[y]) ]

    rect =  [ int_pt1[x], int_pt1[y], int_pt2[x]-int_pt1[x], int_pt4[y]-int_pt1[y] ]
    return rect


# align_image: use src1 as the reference image to transform src2
def align_image(src1, src2, warp_mode=cv2.MOTION_TRANSLATION):
    # convert images to grayscale
    img1_gray = cv2.cvtColor(src1, cv2.COLOR_BGR2GRAY)
    img2_gray = cv2.cvtColor(src2, cv2.COLOR_BGR2GRAY)

    # define 2x3 or 3x3 matrices and initialize it to a identity matrix
    if warp_mode == cv2.MOTION_HOMOGRAPHY:
        warp_matrix = np.eye(3, 3, dtype=np.float32)
    else:
        warp_matrix = np.eye(2, 3, dtype=np.float32)

    # number of iterations:
    num_iters = 1000

    # specify the threshold of the increment in the correlation coefficient between two iterations
    termination_eps = 1e-8    

    # Define termination criteria
    criteria = (cv2.TERM_CRITERIA_EPS | cv2.TERM_CRITERIA_COUNT, num_iters,  termination_eps)

    print('findTransformECC() may take a while...')

    # perform ECC: use the selected model to calculate the transformation required to align src2 with src1. The resulting transformation matrix is stored in warp_matrix:
    (cc, warp_matrix) = cv2.findTransformECC(img1_gray, img2_gray, warp_matrix, warp_mode, criteria, inputMask=None, gaussFiltSize=1)

    if (warp_mode == cv2.MOTION_HOMOGRAPHY):
        img2_aligned = cv2.warpPerspective(src2, warp_matrix, (src1.shape[1], src1.shape[0]), flags=cv2.INTER_LINEAR + cv2.WARP_INVERSE_MAP)
    else :
        # use warpAffine() for: translation, euclidean and affine models
        img2_aligned = cv2.warpAffine(src2, warp_matrix, (src1.shape[1], src1.shape[0]), flags=cv2.INTER_LINEAR + cv2.WARP_INVERSE_MAP, borderMode=cv2.BORDER_CONSTANT, borderValue=0)

    #print('warp_matrix shape', warp_matrix.shape, 'data=\n', warp_matrix)
    #print(warp_matrix, warp_matrix)

    # compute the cropping area to remove the black bars from the transformed image
    x = 0
    y = 0
    w = src1.shape[1]
    h = src1.shape[0]

    if (warp_matrix[0][2] < 0):
        x = warp_matrix[0][2] * -1
        w -= x

    if (warp_matrix[1][2] < 0):
        y = warp_matrix[1][2] * -1
        h -= y

    if (warp_matrix[1][2] > 0):
        h -= warp_matrix[1][2]
    
    matchArea = [ int(x), int(y), int(w), int(h) ]
  
    #print('src1 w=', src1.shape[1], 'h=', src1.shape[0])
    #print('matchedRect=', matchArea[0], ',', matchArea[1], '@', matchArea[2], 'x', matchArea[3], '\n')
    return img2_aligned, matchArea


##########################################################################################


img1 = cv2.imread("img1.png")
img2 = cv2.imread("img2.png")
img3 = cv2.imread("img3.png")

# TODO: adjust contrast on all input images

###
# resize images to be the same size as the smallest image for debug purposes
###
max_h = img1.shape[0]
max_h = max(max_h, img2.shape[0])
max_h = max(max_h, img3.shape[0])
max_w = img1.shape[1]
max_w = max(max_w, img2.shape[1])
max_w = max(max_w, img3.shape[1])
img1_padded = cv2.resize(img1, (max_w, max_h), interpolation=cv2.INTER_AREA)
img2_padded = cv2.resize(img2, (max_w, max_h), interpolation=cv2.INTER_AREA)
img3_padded = cv2.resize(img3, (max_w, max_h), interpolation=cv2.INTER_AREA)

# stack them horizontally for display
hStack = np.hstack((img1_padded, img2_padded))  # stack images side-by-side
input_stacked = np.hstack((hStack, img3_padded))      # stack images side-by-side
cv2.imwrite("input_stacked.jpg", input_stacked)
cv2.imshow("input_stacked", input_stacked)
cv2.waitKey(0)

###
# perform image alignment
###

# specify the motion model
warp_mode = cv2.MOTION_EUCLIDEAN   # cv2.MOTION_TRANSLATION, cv2.MOTION_EUCLIDEAN, cv2.MOTION_AFFINE, cv2.MOTION_HOMOGRAPHY

# for testing purposes: img2 will be the reference image
img1_aligned, matchArea1 = align_image(img2, img1, warp_mode)
img1_aligned_cpy = img1_aligned.copy()
cv2.rectangle(img1_aligned_cpy, (matchArea1[0], matchArea1[1]),  (matchArea1[0]+matchArea1[2], matchArea1[1]+matchArea1[3]), (0, 255, 0), 2)
cv2.imwrite("img1_aligned.jpg", img1_aligned_cpy)

print('\n###############################################\n')

# for testing purposes: img2 will be the reference image again
img3_aligned, matchArea3 = align_image(img2, img3, warp_mode)
img3_aligned_cpy = img3_aligned.copy()
cv2.rectangle(img3_aligned_cpy, (matchArea3[0], matchArea3[1]),  (matchArea3[0]+matchArea3[2], matchArea3[1]+matchArea3[3]), (0, 255, 0), 2)
cv2.imwrite("img3_aligned.jpg", img3_aligned_cpy)

# compute the crop area in the reference image and draw a red rectangle
cropRect = internalRect(matchArea1, matchArea3)
print('cropRect=', cropRect[0], ',', cropRect[1], '@', cropRect[2], 'x', cropRect[3], '\n')

img2_eq_cpy = img2.copy()
cv2.rectangle(img2_eq_cpy, (cropRect[0], cropRect[1]),  (cropRect[0]+cropRect[2], cropRect[1]+cropRect[3]), (0, 0, 255), 2)
cv2.imwrite("img2_eq.jpg", img2_eq_cpy)

# stack results horizontally for display
res_hStack = np.hstack((img1_aligned_cpy, img2_eq_cpy))                 # stack images side-by-side
aligned_stacked = np.hstack((res_hStack, img3_aligned_cpy))             # stack images side-by-side
cv2.imwrite("aligned_stacked.jpg", aligned_stacked)
cv2.imshow("aligned_stacked", aligned_stacked)
cv2.waitKey(0)

print('\n###############################################\n')

# crop images to the smallest internal area between them
img1_aligned_cropped = img1_aligned[cropRect[1] : cropRect[1]+cropRect[3], cropRect[0] : cropRect[0]+cropRect[2]]
img3_aligned_cropped = img3_aligned[cropRect[1] : cropRect[1]+cropRect[3], cropRect[0] : cropRect[0]+cropRect[2]]
img2_eq_cropped      =         img2[cropRect[1] : cropRect[1]+cropRect[3], cropRect[0] : cropRect[0]+cropRect[2]]

cropped_hStack = np.hstack((img1_aligned_cropped, img2_eq_cropped))     # stack images side-by-side
cropped_stacked = np.hstack((cropped_hStack, img3_aligned_cropped))     # stack images side-by-side
cv2.imwrite("cropped_stacked.jpg", cropped_stacked)
cv2.imshow("cropped_stacked", cropped_stacked)
cv2.waitKey(0)