填充 scipy affine_transform 输出以显示变换图像的非重叠区域

Question

我有源 ( src) 图像，我希望dst使用仿射变换对齐到目标 ( ) 图像，同时在对齐过程中保留两个图像的完整范围（甚至是非重叠区域）。

我已经能够计算仿射变换旋转和偏移矩阵，我将其提供给scipy.ndimage.interpolate.affine_transform恢复dst对齐的src图像。

问题在于，当图像未完全重叠时，生成的图像将被裁剪为仅两个图像的公共足迹。我需要的是放置在同一像素坐标系上的两个图像的完整范围。这个问题几乎是这个问题的重复- 那里的优秀答案和存储库为 OpenCV 转换提供了这一功能。不幸的是我需要这个来scipy实现。

太晚了，在多次碰壁试图将上述问题的答案翻译为 后scipy，我遇到了这个问题并随后遵循了这个问题。后一个问题确实让我们对仿射变换的奇妙世界有了一些了解scipy，但我还无法满足我的特殊需求。

src从到 的变换dst可以具有平移和旋转。我只能让翻译起作用（下面显示了一个示例），并且我只能让旋转起作用（主要是围绕下面的内容进行黑客攻击并从使用reshape中的参数中获取灵感scipy.ndimage.interpolation.rotate）。然而，将两者结合起来我彻底迷失了。我试图计算什么应该是正确的offset（再次参见这个问题的答案），但我无法让它在所有情况下工作。

填充仿射变换的仅翻译工作示例，主要遵循此存储库，在这个答案中进行了解释：

from scipy.ndimage import rotate, affine_transform
import numpy as np
import matplotlib.pyplot as plt

nblob = 50
shape = (200, 100)
buffered_shape = (300, 200)  # buffer for rotation and translation


def affine_test(angle=0, translate=(0, 0)):
    np.random.seed(42)
    # Maxiumum translation allowed is half difference between shape and buffered_shape

    # Generate a buffered_shape-sized base image with random blobs
    base = np.zeros(buffered_shape, dtype=np.float32)
    random_locs = np.random.choice(np.arange(2, buffered_shape[0] - 2), nblob * 2, replace=False)
    i = random_locs[:nblob]
    j = random_locs[nblob:]
    for k, (_i, _j) in enumerate(zip(i, j)):
        # Use different values, just to make it easier to distinguish blobs
        base[_i - 2 : _i + 2, _j - 2 : _j + 2] = k + 10

    # Impose a rotation and translation on source
    src = rotate(base, angle, reshape=False, order=1, mode="constant")
    bsc = (np.array(buffered_shape) / 2).astype(int)
    sc = (np.array(shape) / 2).astype(int)
    src = src[
        bsc[0] - sc[0] + translate[0] : bsc[0] + sc[0] + translate[0],
        bsc[1] - sc[1] + translate[1] : bsc[1] + sc[1] + translate[1],
    ]
    # Cut-out destination from the centre of the base image
    dst = base[bsc[0] - sc[0] : bsc[0] + sc[0], bsc[1] - sc[1] : bsc[1] + sc[1]]

    src_y, src_x = src.shape

    def get_matrix_offset(centre, angle, scale):
        """Follows OpenCV.getRotationMatrix2D"""
        angle = angle * np.pi / 180
        alpha = scale * np.cos(angle)
        beta = scale * np.sin(angle)
        return (
            np.array([[alpha, beta], [-beta, alpha]]),
            np.array(
                [
                    (1 - alpha) * centre[0] - beta * centre[1],
                    beta * centre[0] + (1 - alpha) * centre[1],
                ]
            ),
        )
    # Obtain the rotation matrix and offset that describes the transformation
    # between src and dst
    matrix, offset = get_matrix_offset(np.array([src_y / 2, src_x / 2]), angle, 1)
    offset = offset - translate

    # Determine the outer bounds of the new image
    lin_pts = np.array([[0, src_x, src_x, 0], [0, 0, src_y, src_y]])
    transf_lin_pts = np.dot(matrix.T, lin_pts) - offset[::-1].reshape(2, 1)

    # Find min and max bounds of the transformed image
    min_x = np.floor(np.min(transf_lin_pts[0])).astype(int)
    min_y = np.floor(np.min(transf_lin_pts[1])).astype(int)
    max_x = np.ceil(np.max(transf_lin_pts[0])).astype(int)
    max_y = np.ceil(np.max(transf_lin_pts[1])).astype(int)

    # Add translation to the transformation matrix to shift to positive values
    anchor_x, anchor_y = 0, 0
    if min_x < 0:
        anchor_x = -min_x
    if min_y < 0:
        anchor_y = -min_y
    shifted_offset = offset - np.dot(matrix, [anchor_y, anchor_x])

    # Create padded destination image
    dst_h, dst_w = dst.shape[:2]
    pad_widths = [anchor_y, max(max_y, dst_h) - dst_h, anchor_x, max(max_x, dst_w) - dst_w]
    dst_padded = np.pad(
        dst,
        ((pad_widths[0], pad_widths[1]), (pad_widths[2], pad_widths[3])),
        "constant",
        constant_values=-1,
    )
    dst_pad_h, dst_pad_w = dst_padded.shape

    # Create the aligned and padded source image
    source_aligned = affine_transform(
        src,
        matrix.T,
        offset=shifted_offset,
        output_shape=(dst_pad_h, dst_pad_w),
        order=3,
        mode="constant",
        cval=-1,
    )

    # Plot the images
    fig, axes = plt.subplots(1, 4, figsize=(10, 5), sharex=True, sharey=True)
    axes[0].imshow(src, cmap="viridis", vmin=-1, vmax=nblob)
    axes[0].set_title("Source")
    axes[1].imshow(dst, cmap="viridis", vmin=-1, vmax=nblob)
    axes[1].set_title("Dest")
    axes[2].imshow(source_aligned, cmap="viridis", vmin=-1, vmax=nblob)
    axes[2].set_title("Source aligned to Dest padded")
    axes[3].imshow(dst_padded, cmap="viridis", vmin=-1, vmax=nblob)
    axes[3].set_title("Dest padded")
    plt.show()

例如：

affine_test(0, (-20, 40))

给出：

放大显示填充图像中的对齐情况：

我需要在同一像素坐标上对齐src和图像的完整范围，同时进行旋转和平移。dst

任何帮助是极大的赞赏！

Answer 1

如果其他人有这种scipy仿射变换的需要，请使用下面的工作代码：

def affine_test(angle=0, translate=(0, 0), shape=(200, 100), buffered_shape=(300, 200), nblob=50):
    # Maxiumum translation allowed is half difference between shape and buffered_shape

    np.random.seed(42)

    # Generate a buffered_shape-sized base image
    base = np.zeros(buffered_shape, dtype=np.float32)
    random_locs = np.random.choice(np.arange(2, buffered_shape[0] - 2), nblob * 2, replace=False)
    i = random_locs[:nblob]
    j = random_locs[nblob:]
    for k, (_i, _j) in enumerate(zip(i, j)):
        base[_i - 2 : _i + 2, _j - 2 : _j + 2] = k + 10

    # Impose a rotation and translation on source
    src = rotate(base, angle, reshape=False, order=1, mode="constant")
    bsc = (np.array(buffered_shape) / 2).astype(int)
    sc = (np.array(shape) / 2).astype(int)
    src = src[
        bsc[0] - sc[0] + translate[0] : bsc[0] + sc[0] + translate[0],
        bsc[1] - sc[1] + translate[1] : bsc[1] + sc[1] + translate[1],
    ]
    # Cut-out destination from the centre of the base image
    dst = base[bsc[0] - sc[0] : bsc[0] + sc[0], bsc[1] - sc[1] : bsc[1] + sc[1]]

    src_y, src_x = src.shape

    def get_matrix_offset(centre, angle, scale):
        """Follows OpenCV.getRotationMatrix2D"""
        angle_rad = angle * np.pi / 180
        alpha = np.round(scale * np.cos(angle_rad), 8)
        beta = np.round(scale * np.sin(angle_rad), 8)
        return (
            np.array([[alpha, beta], [-beta, alpha]]),
            np.array(
                [
                    (1 - alpha) * centre[0] - beta * centre[1],
                    beta * centre[0] + (1 - alpha) * centre[1],
                ]
            ),
        )

    matrix, offset = get_matrix_offset(np.array([((src_y - 1) / 2) - translate[0], ((src_x - 1) / 2) - translate[
    1]]), angle, 1)

    offset += np.array(translate)

    M = np.column_stack((matrix, offset))
    M = np.vstack((M, [0, 0, 1]))
    iM = np.linalg.inv(M)
    imatrix = iM[:2, :2]
    ioffset = iM[:2, 2]

    # Determine the outer bounds of the new image
    lin_pts = np.array([[0, src_y-1, src_y-1, 0], [0, 0, src_x-1, src_x-1]])
    transf_lin_pts = np.dot(matrix, lin_pts) + offset.reshape(2, 1) # - np.array(translate).reshape(2, 1) # both?

    # Find min and max bounds of the transformed image
    min_x = np.floor(np.min(transf_lin_pts[1])).astype(int)
    min_y = np.floor(np.min(transf_lin_pts[0])).astype(int)
    max_x = np.ceil(np.max(transf_lin_pts[1])).astype(int)
    max_y = np.ceil(np.max(transf_lin_pts[0])).astype(int)

    # Add translation to the transformation matrix to shift to positive values
    anchor_x, anchor_y = 0, 0
    if min_x < 0:
        anchor_x = -min_x
    if min_y < 0:
        anchor_y = -min_y

    dot_anchor = np.dot(imatrix, [anchor_y, anchor_x])
    shifted_offset = ioffset - dot_anchor

    # Create padded destination image
    dst_y, dst_x = dst.shape[:2]
    pad_widths = [anchor_y, max(max_y, dst_y) - dst_y, anchor_x, max(max_x, dst_x) - dst_x]
    dst_padded = np.pad(
        dst,
        ((pad_widths[0], pad_widths[1]), (pad_widths[2], pad_widths[3])),
        "constant",
        constant_values=-10,
    )

    dst_pad_y, dst_pad_x = dst_padded.shape
    # Create the aligned and padded source image
    source_aligned = affine_transform(
        src,
        imatrix,
        offset=shifted_offset,
        output_shape=(dst_pad_y, dst_pad_x),
        order=3,
        mode="constant",
        cval=-10,
    )

例如运行：

affine_test(angle=-25, translate=(10, -40))

将会呈现：

并放大：

抱歉，代码写得不好。

请注意，在野外运行它时，我注意到它无法处理图像比例大小的任何变化，但我不确定这与我计算转换的方式无关 - 因此值得注意的警告，并检查，如果您要对齐不同比例的图像。