从图像标签创建边界框

Question

我有一张二维彩色图像和一张标签图像（标签的投影）

标签图片输出如下：

[[16 16 16 ... 16 16 16 ]
 [16 16 16 ... 16 16 16 ]
 [16 16 16 ... 16 16 16 ]
 ...
 [ 2  2  2 ...  2  2  2 ]
 [ 2  2  2 ...  2  2  2 ]
 [ 2  2  2 ...  2  2  2 ]]

如何在原始二维彩色图像中的所有对象（由标签表示）周围绘制边界框？

Answer 1

使用 NumPy 的 boolean array indexing and OpenCV's boundingRect 函数可以轻松完成此任务。

来自 here，我拍摄了这张照片

和这个分割掩码

掩码是索引图像，OpenCV 有问题，另请参阅 . That's why, we'll also use Pillow 了解此任务。

代码如下：

import cv2
import numpy as np
from PIL import Image

# Read color image
img = cv2.imread('0.jpg')

# Read mask; OpenCV can't handle indexed images, so we need Pillow here
# for that, see also: 
mask = np.array(Image.open('0_mask.png'))

# Iterate all colors in mask
for color in np.unique(mask):

    # Color 0 is assumed to be background or artifacts
    if color == 0:
        continue

    # Determine bounding rectangle w.r.t. all pixels of the mask with
    # the current color
    x, y, w, h = cv2.boundingRect(np.uint8(mask == color))

    # Draw bounding rectangle to color image
    out = cv2.rectangle(img.copy(), (x, y), (x+w, y+h), (0, int(color), 0), 2)

    # Show image with bounding box
    cv2.imshow('img_' + str(color), out)

# Show mask
cv2.imshow('mask', mask)
cv2.waitKey(0)
cv2.destroyAllWindows()

这些是输出：

我决定输出几张图片，因为对于给定的图片，边界框严重重叠。要将所有矩形绘制到同一个图像，只需将相应的 rectangle 命令替换为

img = cv2.rectangle(img, (x, y), (x+w, y+h), (0, int(color), 0), 2)

----------------------------------------
System information
----------------------------------------
Platform:    Windows-10-10.0.16299-SP0
Python:      3.8.5
NumPy:       1.19.2
OpenCV:      4.4.0
Pillow:      7.2.0
----------------------------------------

从图像标签创建边界框

Create Bounding Boxes from Image Labels

python

image-processing

bounding-box

image-segmentation