使用 Python 测量 OpenCv 上像素之间的距离
Measuring the distance between pixels on OpenCv with Python
我是Open CV和计算机视觉方面的新手，所以我虚心请教。我用 pi 相机录制了一段视频，我可以实时从其他颜色中识别出蓝色（我看到蓝色是白色，其他颜色是黑色）。
我想测量区域底部的长度（因为我有一个白色矩形和一个黑色矩形）。这两个矩形一起创建正方形框架。
代码摘录：
# Take each frame
_, frame = cap.read(0)
# Convert BGR to HSV
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
# define range of blue color in HSV
lower_blue = np.array([80,30,30])
upper_blue = np.array([130,150,210])
# Threshold the HSV image to get only blue colors
mask = cv2.inRange(hsv, lower_blue, upper_blue)
# applica filtri morfologici
mask = cv2.erode(mask, spotFilter)
mask = cv2.dilate(mask, maskMorph)
# ^Now the mask is a black and white image.
# ^Get height of the black region in this image
# Bitwise-AND mask and original image
res = cv2.bitwise_and(frame,frame, mask= mask)
cv2.imshow('frame',frame)
cv2.imshow('mask',mask)
cv2.imshow('res',res)
假设输入帧将具有 "close to rectangle" 形状（以下代码最有效），您必须使用 findContours 函数来获取黑色区域的边界，并使用 boundingRect 函数来得到它的尺寸。
mask = cv2.imread('mask.png') #The mask variable in your code
# plt.imshow(mask)
thresh_min,thresh_max = 127,255
ret,thresh = cv2.threshold(mask,thresh_min,thresh_max,0)
# findContours requires a monochrome image.
thresh_bw = cv2.cvtColor(thresh, cv2.COLOR_BGR2GRAY)
# findContours will find contours on bright areas (i.e. white areas), hence we'll need to invert the image first
thresh_bw_inv = cv2.bitwise_not(thresh_bw)
_, contours, hierarchy = cv2.findContours(thresh_bw_inv,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
# ^Gets all white contours
# Find the index of the largest contour
areas = [cv2.contourArea(c) for c in contours]
max_index = np.argmax(areas)
cnt=contours[max_index]
x,y,w,h = cv2.boundingRect(cnt)
#Draw the rectangle on original image here.
cv2.rectangle(mask,(x,y),(x+w,y+h),(0,255,0),2)
plt.imshow(mask)
print("Distances: vertical: %d, horizontal: %d" % (h,w))
我是Open CV和计算机视觉方面的新手，所以我虚心请教。我用 pi 相机录制了一段视频，我可以实时从其他颜色中识别出蓝色（我看到蓝色是白色，其他颜色是黑色）。
我想测量区域底部的长度（因为我有一个白色矩形和一个黑色矩形）。这两个矩形一起创建正方形框架。
代码摘录：
# Take each frame
_, frame = cap.read(0)
# Convert BGR to HSV
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
# define range of blue color in HSV
lower_blue = np.array([80,30,30])
upper_blue = np.array([130,150,210])
# Threshold the HSV image to get only blue colors
mask = cv2.inRange(hsv, lower_blue, upper_blue)
# applica filtri morfologici
mask = cv2.erode(mask, spotFilter)
mask = cv2.dilate(mask, maskMorph)
# ^Now the mask is a black and white image.
# ^Get height of the black region in this image
# Bitwise-AND mask and original image
res = cv2.bitwise_and(frame,frame, mask= mask)
cv2.imshow('frame',frame)
cv2.imshow('mask',mask)
cv2.imshow('res',res)
假设输入帧将具有 "close to rectangle" 形状（以下代码最有效），您必须使用 findContours 函数来获取黑色区域的边界，并使用 boundingRect 函数来得到它的尺寸。
mask = cv2.imread('mask.png') #The mask variable in your code
# plt.imshow(mask)
thresh_min,thresh_max = 127,255
ret,thresh = cv2.threshold(mask,thresh_min,thresh_max,0)
# findContours requires a monochrome image.
thresh_bw = cv2.cvtColor(thresh, cv2.COLOR_BGR2GRAY)
# findContours will find contours on bright areas (i.e. white areas), hence we'll need to invert the image first
thresh_bw_inv = cv2.bitwise_not(thresh_bw)
_, contours, hierarchy = cv2.findContours(thresh_bw_inv,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
# ^Gets all white contours
# Find the index of the largest contour
areas = [cv2.contourArea(c) for c in contours]
max_index = np.argmax(areas)
cnt=contours[max_index]
x,y,w,h = cv2.boundingRect(cnt)
#Draw the rectangle on original image here.
cv2.rectangle(mask,(x,y),(x+w,y+h),(0,255,0),2)
plt.imshow(mask)
print("Distances: vertical: %d, horizontal: %d" % (h,w))