根据图像调整边界框的大小

Question

我在Python中实现对象本地化。 我遇到的一个问题是，当我在采取行动时调整可观察区域的大小时，我不知道如何同时更改地面实况框。 因此，发生这种情况：

地面实况框不会调整大小以准确适应飞机。 因此，我无法正确本地化。 我当前格式化下一个状态的函数如下：

def next_state(init_input, b, b_prime, g, a):
    """ 
    Returns the observable region of the next state.

    Formats the next state's observable region, defined
    by b_prime, to be of dimension (224, 224, 3). Adding 16
    additional pixels of context around the original bounding box.
    The ground truth box must be reformatted according to the
    new observable region.

    :param init_input:
        The initial input volume of the current episode.

    :param b:
        The current state's bounding box.

    :param b_prime:
        The subsequent state's bounding box.

    :param g:
        The ground truth box of the target object.

    :param a:
        The action taken by the agent at the current step.
    """

    # Determine the pixel coordinates of the observable region for the following state
    context_pixels = 16
    x1 = max(b_prime[0] - context_pixels, 0)
    y1 = max(b_prime[1] - context_pixels, 0)
    x2 = min(b_prime[2] + context_pixels, IMG_SIZE)
    y2 = min(b_prime[3] + context_pixels, IMG_SIZE)

    # Determine observable region
    observable_region = cv2.resize(init_input[y1:y2, x1:x2], (224, 224))

    # Difference between crop region and image dimensions
    x1_diff = x1
    y1_diff = y1
    x2_diff = IMG_SIZE - x2
    y2_diff = IMG_SIZE - y2

    # Resize ground truth box
    g[0] = int(g[0] - 0.5 * x1_diff)  # x1
    g[1] = int(g[1] - 0.5 * y1_diff)  # y1
    g[2] = int(g[2] + 0.5 * x2_diff)  # x2
    g[3] = int(g[3] + 0.5 * y2_diff)  # y2

    return observable_region, g

我似乎无法正确地改变尺寸。 我按照这篇文章来初步调整边界框的大小。 然而，在这种情况下，该解决方案似乎并不起作用。

边界框/地面实况框的格式为： b = [x1, y1, x2, y2]

init_input具有维度(224, 224, 3) init_input (224, 224, 3) 。 IMG_SIZE = 224 ， context_pixels = 16

这是一个额外的例子：

似乎地面实况盒的大小是正确的，但位置是关闭的。

更新

我已经更新了上面的代码部分。 比例因子似乎是解决问题的错误方法。 通过添加/减去要放大的像素数量，我已经接近了很多。 我相信现在与插值有关，所以如果有人可以帮忙解决这个问题，那将是一个很大的帮助。

新例子：

更新2

提供了一种解决方案 。

Answer 1

我的问题在这篇文章中被名为@lenik的用户解决了。

在将比例因子应用于地面实况框g的像素坐标之前，必须首先减去零偏移，使x1, y1变为0, 0 。 这允许缩放工作正常。

因此，变换后任意随机点(x,y)的坐标可以计算为：

x_new = (x - x1) * IMG_SIZE / (x2 - x1)
y_new = (y - y1) * IMG_SIZE / (y2 - y1)

在代码中以及与我的问题相关的解决方案如下：

def next_state(init_input, b_prime, g):
    """
    Returns the observable region of the next state.

    Formats the next state's observable region, defined
    by b_prime, to be of dimension (224, 224, 3). Adding 16
    additional pixels of context around the original bounding box.
    The ground truth box must be reformatted according to the
    new observable region.

    :param init_input:
        The initial input volume of the current episode.

    :param b_prime:
        The subsequent state's bounding box.

    :param g:
        The ground truth box of the target object.
    """

    # Determine the pixel coordinates of the observable region for the following state
    context_pixels = 16
    x1 = max(b_prime[0] - context_pixels, 0)
    y1 = max(b_prime[1] - context_pixels, 0)
    x2 = min(b_prime[2] + context_pixels, IMG_SIZE)
    y2 = min(b_prime[3] + context_pixels, IMG_SIZE)

    # Determine observable region
    observable_region = cv2.resize(init_input[y1:y2, x1:x2], (224, 224), interpolation=cv2.INTER_AREA)

    # Resize ground truth box 
    g[0] = int((g[0] - x1) * IMG_SIZE / (x2 - x1))  # x1
    g[1] = int((g[1] - y1) * IMG_SIZE / (y2 - y1))  # y1
    g[2] = int((g[2] - x1) * IMG_SIZE / (x2 - x1))  # x2
    g[3] = int((g[3] - y1) * IMG_SIZE / (y2 - y1))  # y2

    return observable_region, g