cv2函数实践-图像处理（中心外扩的最佳RoI/根据两个坐标点求缩放+偏移后的RoI/滑窗切片/VOC的颜色+调色板）

中心外扩的最佳RoI（裁图）

指定中心点和裁图宽高，获得裁图位置xyxy坐标（最佳），便于在图像裁剪。

def get_best_crop_position_of_center(center_xy, img_w, img_h, crop_w, crop_h):
    pt = center_xy
    x0, y0 = max(0, pt[0] - crop_w // 2), max(0, pt[1] - crop_h // 2)  # 左上角 >= (0,0)
    x1, y1 = min(x0 + crop_w, img_w), min(y0 + crop_h, img_h)  # 右下角
    return [int(x1-crop_w), int(y1-crop_h), int(x1), int(y1)]

根据两个坐标点求缩放+偏移后的RoI

def get_xyxy_scale_shift(pt1, pt2, scale_xy=1.0, shift=0, imgW=0, imgH=0):
    """
    给定两个坐标点，返回缩放+偏移后的RoI坐标
    :param pt1, pt2: 两个坐标点
    :param scale_xy: 缩放比例，还原到原图
    :param shift: 短边的放大偏移量(长边不变)
    :param imgW: RoI坐标限宽
    :param imgH: RoI坐标限高
    """
    x0, y0, x1, y1 = min(pt1[0], pt2[0]), min(pt1[1], pt2[1]), max(pt1[0], pt2[0]), max(pt1[1], pt2[1])  # 左上, 右下
    x0, y0, x1, y1 = round(x0 * scale_xy), round(y0 * scale_xy), round(x1 * scale_xy), round(y1 * scale_xy)  # 缩放，取整
    if x1 - x0 == y1 - y0:
        x0, x1 = x0 - shift, x1 + shift
        y0, y1 = y0 - shift, y1 + shift
    elif x1 - x0 < y1 - y0:
        x0, x1 = x0 - shift, x1 + shift
    else:
        y0, y1 = y0 - shift, y1 + shift
    if imgW > 0:
        x0 = min(max(0, x0), imgW)
        x1 = min(max(0, x1), imgW)
    if imgH > 0:
        y0 = min(max(0, y0), imgH)
        y1 = min(max(0, y1), imgH)
    return int(x0+0.5), int(y0+0.5), int(x1+0.5), int(y1+0.5)

上面函数可以应用在图像上画矩形框，

def draw_RoI(img: np.ndarray, pt1, pt2, scale_xy=1.0, shift=0, color=None, thickness=None):
    if color is None: color = (0,255,0)
    imgH, imgW = img.shape[:2]
    x0, y0, x1, y1 = get_xyxy_scale_shift(pt1, pt2, scale_xy, shift, imgW, imgH)
    cv2.rectangle(img, (x0, y0), (x1, y1), color, thickness)
    return x0, y0, x1, y1

自定义RGB2BGR颜色解析小函数

def rgb2bgr(rgb):
    if isinstance(rgb, (list, tuple)):
        rgb_list = []
        for val in rgb:
            if isinstance(val, str) and val.strip() != '':
                rgb_list.append(int(val.strip()))
            elif isinstance(val, int):
                rgb_list.append(val)
        return rgb_list[::-1]
    elif isinstance(rgb, str):
        bgr = [int(val.strip()) for val in rgb.split(',') if val.strip() != ''][::-1]
        return bgr
    else:
        raise ValueError("error in converting RGB[" + str(rgb) + "] to BGR")

滑窗切片（sliding window crops）

指定横向和纵向的Windows数，自适应计算每个Window的宽和高，以及滑窗步长，居中对齐，返回每个Window的坐标。

def make_grids(img, grid_x, grid_y, dx=0, dy=0):
    """
    make grids in x-axis and y-axis
    指定横向和纵向的Windows数，自适应计算每个Window的宽和高，居中对齐，返回每个Window的坐标
    Args:
        img: ndarray
        grid_x: number of grids in x-axis，指定横向窗口数
        grid_y: number of grids in y-axis，指定纵向窗口数
        dx: shrinking size in x-axis，横向窗口间隔的一半
        dy: shrinking size in y-axis，纵向窗口间隔的一半

    Returns:
        [[grid_box]], where
        grid_box = (upleft_pt, downright_pt) = ((x0, y0), (x1, y1))
    """
    grid_boxs = []
    h, w = img.shape[:2]
    left_pad, up_pad = (w % grid_x) // 2, (h % grid_y) // 2
    box_w, box_h = w // grid_x, h // grid_y
    for hi in range(grid_y):
        row_boxs = [((left_pad+wi*box_w+dx, up_pad+hi*box_h+dy),
                     (left_pad+(wi+1)*box_w-dx, up_pad+(hi+1)*box_h-dy))
                    for wi in range(grid_x)]
        grid_boxs.append(row_boxs)
    return grid_boxs


def make_grids_sliding(img, grid_x, grid_y, box_w, box_h):
    """
    指定横向和纵向的Windows数 以及窗口大小，有overlapping的滑窗，左右上下紧贴边
    Args:
        img: ndarray
        grid_x: number of grids in x-axis，指定横向窗口数
        grid_y: number of grids in y-axis，指定纵向窗口数
        box_w: width of each box，窗口横向宽度
        box_h: height of each box，窗口纵向高度

    Returns:
        [[grid_box]], where
        grid_box = (upleft_pt, downright_pt) = ((x0, y0), (x1, y1))

    Examples:
        [:append]
        grid_boxs = make_grids_sliding(srcImg, 4, 3, 1280, 1280)
        for idy, row_boxs in enumerate(grid_boxs):
            for idx, ((x0, y0), (x1, y1)) in enumerate(row_boxs):
                cv2.circle(srcImg, ((x0+x1)//2, (y0+y1)//2), 20, color, -1)
        [:extend]
        grid_boxs = make_grids_sliding(srcImg, 4, 3, 1280, 1280)
        for (x0, y0), (x1, y1) in grid_boxs:
            cv2.circle(srcImg, ((x0+x1)//2, (y0+y1)//2), 20, color, -1)
    """
    grid_boxs = []
    h, w = img.shape[:2]
    # box_h, box_w = min(h, box_h), min(w, box_w)  # 保证：窗口大小 <= 原图大小
    lt_x0y0, rd_x0y0 = (0, 0), (max(0, w-box_w), max(0, h-box_h))  # 左上角窗口、右下角窗口的左上角坐标
    x0linspace = [int(x0) for x0 in np.linspace(lt_x0y0[0], rd_x0y0[0], grid_x)]
    y0linspace = [int(y0) for y0 in np.linspace(lt_x0y0[1], rd_x0y0[1], grid_y)]
    for y0 in y0linspace:
        row_boxs = [((x0, y0), (x0+box_w, y0+box_h))
                    for x0 in x0linspace]  # 左上角、右下角
        grid_boxs.extend(row_boxs)  # .append
    return grid_boxs


if __name__ == '__main__':
    srcImg = np.zeros((2000, 2000, 3), dtype=np.uint8)
    grid_boxs = make_grids_sliding(srcImg, 2, 2, 1280, 1280)
    print(grid_boxs)
    # 在crop_srcImg上滑动窗口裁图，将grid_boxs从crop_srcImg映射回srcImg
    px0, py0 = 10, 10
    for idy, row_boxs in enumerate(grid_boxs):
        (x0, y0), (x1, y1) = row_boxs
        grid_boxs[idy] = ((x0 + px0, y0 + py0), (x1 + px0, y1 + py0))
    print(grid_boxs)

VOC的颜色+调色板

通过位运算，巧妙地生成有梯度（相差128个灰度值）的RGB颜色表，相比打表可快多了。

def create_pascal_label_colormap():
    """
    PASCAL VOC 分割数据集的类别标签颜色映射label colormap

    返回:
        可视化分割结果的颜色映射Colormap

    Examples:
        colormap = create_pascal_label_colormap()
        color = colormap[idx].tolist()  # [b, g, r]
        # 分割结果label.shape=(1024,1024)，渲染图vis.shape=(1024,1024,3)
        vis = colormap[label]
    """
    colormap = np.zeros((256, 3), dtype=int)
    ind = np.arange(256, dtype=int)

    for shift in reversed(range(8)):
        for channel in range(3):
            colormap[:, channel] |= ((ind >> channel) & 1) << shift
        ind >>= 3

    return colormap