回答此问题可获得 20 贡献值,回答如果被采纳可获得 50 分。
<p>我想检测图像中的物体并测量它们之间的距离。只要物体不是靠得太近就行了。不幸的是,图像的光照不是最佳的,所以看起来像是物体在触摸,尽管它们不是。我试图用一条代表物体的线来确定距离。问题是,一旦物体轮廓连接起来,我就无法确定代表物体的直线,因此无法计算距离。在</p>
<p>输入图像:</p>
<p><a href="https://i.stack.imgur.com/cDxYY.png" rel="nofollow noreferrer"><img src="https://i.stack.imgur.com/cDxYY.png" alt="enter image description here"/></a></p>
<p>代码:</p>
<pre><code>import cv2
import numpy as np
#import image
img = cv2.imread('img.png', 0)
#Thresh
_, thresh = cv2.threshold(img, 200, 255, cv2.THRESH_BINARY)
#Finding the contours in the image
_, contours, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
#Convert img to RGB and draw contour
img = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB)
cv2.drawContours(img, contours, -1, (0,0,255), 2)
#Object1
v = np.matrix([[0], [1]])
rect = cv2.minAreaRect(contours[0])
#determine angle
if rect[1][0] > rect[1][1]:
ang = (rect[2] + 90)* np.pi / 180
else:
ang = rect[2]* np.pi / 180
rot = np.matrix([[np.cos(ang), -np.sin(ang)],[np.sin(ang), np.cos(ang)]])
rv = rot*v
#draw angle line
lineSize = max(rect[1])*0.45 #length of line
p1 = tuple(np.array(rect[0] - lineSize*rv.T)[0].astype(int))
p2 = tuple(np.array(rect[0] + lineSize*rv.T)[0].astype(int))
cv2.line(img, p1, p2, (255,0,0), 2)
#Object2
if len(contours) > 1:
rect = cv2.minAreaRect(contours[1])
#determine angle
if rect[1][0] > rect[1][1]:
ang = (rect[2] + 90)* np.pi / 180
else:
ang = rect[2]* np.pi / 180
rot = np.matrix([[np.cos(ang), -np.sin(ang)],[np.sin(ang), np.cos(ang)]])
rv = rot*v
#draw angle line
lineSize = max(rect[1])*0.45 #length of line
p1 = tuple(np.array(rect[0] - lineSize*rv.T)[0].astype(int))
p2 = tuple(np.array(rect[0] + lineSize*rv.T)[0].astype(int))
cv2.line(img, p1, p2, (255,0,0), 2)
#save output img
cv2.imwrite('output_img.png', img)
</code></pre>
<p>输出图像:</p>
<p><a href="https://i.stack.imgur.com/Le4MO.png" rel="nofollow noreferrer"><img src="https://i.stack.imgur.com/Le4MO.png" alt="enter image description here"/></a></p>
<p>这很好,但只要我使用一个带有连接轮廓的图像,就会发生这种情况:</p>
<p><a href="https://i.stack.imgur.com/r1BCC.png" rel="nofollow noreferrer"><img src="https://i.stack.imgur.com/r1BCC.png" alt="enter image description here"/></a>
<a href="https://i.stack.imgur.com/h9dmT.png" rel="nofollow noreferrer"><img src="https://i.stack.imgur.com/h9dmT.png" alt="enter image description here"/></a></p>
<p>有没有一种方法来划分轮廓或是一个变通方法?在</p>
<p><strong>编辑</strong></p>
<p>多亏了B.M.的建议,我试过是否可以解决侵蚀问题,但不幸的是,新的问题出现了。似乎不可能在侵蚀和阈值/轮廓之间找到平衡。在</p>
<p>示例:</p>
<p><a href="https://i.stack.imgur.com/pW7zk.png" rel="nofollow noreferrer"><img src="https://i.stack.imgur.com/pW7zk.png" alt="enter image description here"/></a>
<a href="https://i.stack.imgur.com/a3Mp3.png" rel="nofollow noreferrer"><img src="https://i.stack.imgur.com/a3Mp3.png" alt="enter image description here"/></a>
<a href="https://i.stack.imgur.com/tSkP8.png" rel="nofollow noreferrer"><img src="https://i.stack.imgur.com/tSkP8.png" alt="enter image description here"/></a>
<a href="https://i.stack.imgur.com/0Eaz4.png" rel="nofollow noreferrer"><img src="https://i.stack.imgur.com/0Eaz4.png" alt="enter image description here"/></a></p>