Questions about the Affine Transformation Part

[ddk1246]

The following section is the selection of affine transformation source and target points in the mmpose

def get_warp_matrix(center: np.ndarray,
                    scale: np.ndarray,
                    rot: float,
                    output_size: Tuple[int, int],
                    shift: Tuple[float, float] = (0., 0.),
                    inv: bool = False) -> np.ndarray:
    """Calculate the affine transformation matrix that can warp the bbox area
    in the input image to the output size.

    Args:
        center (np.ndarray[2, ]): Center of the bounding box (x, y).
        scale (np.ndarray[2, ]): Scale of the bounding box
            wrt [width, height].
        rot (float): Rotation angle (degree).
        output_size (np.ndarray[2, ] | list(2,)): Size of the
            destination heatmaps.
        shift (0-100%): Shift translation ratio wrt the width/height.
            Default (0., 0.).
        inv (bool): Option to inverse the affine transform direction.
            (inv=False: src->dst or inv=True: dst->src)

    Returns:
        np.ndarray: A 2x3 transformation matrix
    """
    assert len(center) == 2
    assert len(scale) == 2
    assert len(output_size) == 2
    assert len(shift) == 2

    shift = np.array(shift)
    src_w = scale[0]
    dst_w = output_size[0]
    dst_h = output_size[1]

    rot_rad = np.deg2rad(rot)
    src_dir = _rotate_point(np.array([0., src_w * -0.5]), rot_rad)
    dst_dir = np.array([0., dst_w * -0.5])

    src = np.zeros((3, 2), dtype=np.float32)
    src[0, :] = center + scale * shift
    src[1, :] = center + src_dir + scale * shift
    src[2, :] = _get_3rd_point(src[0, :], src[1, :])

    dst = np.zeros((3, 2), dtype=np.float32)
    dst[0, :] = [dst_w * 0.5, dst_h * 0.5]
    dst[1, :] = np.array([dst_w * 0.5, dst_h * 0.5]) + dst_dir
    dst[2, :] = _get_3rd_point(dst[0, :], dst[1, :])

    if inv:
        warp_mat = cv2.getAffineTransform(np.float32(dst), np.float32(src))
    else:
        warp_mat = cv2.getAffineTransform(np.float32(src), np.float32(dst))
    return warp_mat

我的问题是，为什么目标点 dst[1, :] = np.array([dst_w * 0.5, dst_h * 0.5]) + dst_dir 的定义中， 添加的偏置是 dst_dir = np.array([0., dst_w * -0.5]) 。上述运算将宽度信息加在了高度信息中。 我认为应该是 dst_dir = np.array([dst_w * -0.5, 0])。 对于256*256的目标尺寸w和h是相同的可能不会有问题，但是其他的呢？

[Ben-Louis]

这个主要是为了和 src_dir 对应