检测不同颜色的blob opencv [英] Detect different color blob opencv
问题描述
我是opencv的新手,对于一个学校项目,我需要用相机检测一个红色和绿色的圆圈,所以我使用了blobdetection,但是它可以检测到我的两种颜色,我认为我的口罩很差,每种颜色都链接到特定的动作.
I'm new to opencv and for a school project i need to detect a red and a green circle with a camera, so i've use blobdetection, but it detect me the two colors, i think that my mask is bad, each color is linked to a specific action.
此刻,我的代码在同一页面上检测到了很好的红色和绿色圆圈,但我希望它在白色页面上仅检测到红色圆圈.
At the moment my code detect well red and green circle on the same page but i want it to detect only red circle on a white page.
感谢您的帮助
# Standard imports
import cv2
import numpy as np;
# Read image
im = cv2.VideoCapture(0)
# Setup SimpleBlobDetector parameters.
params = cv2.SimpleBlobDetector_Params()
# Change thresholds
params.minThreshold = 100;
params.maxThreshold = 200;
# Filter by Area.
params.filterByArea = True
params.minArea = 200
params.maxArea = 20000
# Filter by Circularity
params.filterByCircularity = True
params.minCircularity = 0.1
# Filter by Convexity
params.filterByConvexity = True
params.minConvexity = 0.1
# Filter by Inertia
params.filterByInertia = True
params.minInertiaRatio = 0.1
blueLower = (0,85,170) #100,130,50
blueUpper = (140,110,255) #200,200,130
while(1):
ret, frame=im.read()
mask = cv2.inRange(frame, blueLower, blueUpper)
mask = cv2.erode(mask, None, iterations=0)
mask = cv2.dilate(mask, None, iterations=0)
frame = cv2.bitwise_and(frame,frame,mask = mask)
# Set up the detector with default parameters.
detector = cv2.SimpleBlobDetector_create(params)
# Detect blobs.
keypoints = detector.detect(mask)
# Draw detected blobs as red circles.
# cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS ensures the size of the circle corresponds to the size of blob
im_with_keypoints = cv2.drawKeypoints(mask, keypoints, np.array([]), (0,0,255), cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
# Display the resulting frame
frame = cv2.bitwise_and(frame,im_with_keypoints,mask = mask)
cv2.imshow('frame',frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
# When everything done, release the capture
im.release()
cv2.destroyAllWindows()
代码更新
现在我遇到一个问题,就是我的整个圈子都没有被检测到.
Now i got a issue where my full circle isn't detected.
# Standard imports
import cv2
import numpy as np;
# Read image
im = cv2.VideoCapture(0)
while(1):
ret, frame=im.read()
lower = (130,150,80) #130,150,80
upper = (250,250,120) #250,250,120
mask = cv2.inRange(frame, lower, upper)
lower, contours, upper = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
blob = max(contours, key=lambda el: cv2.contourArea(el))
M = cv2.moments(blob)
center = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))
canvas = im.copy()
cv2.circle(canvas, center, 2, (0,0,255), -1)
cv2.imshow('frame',frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
im.release()
cv2.destroyAllWindows()
推荐答案
您需要计算出绿色的BGR编号是什么(假设参数[0, 255, 0]
假设是这样),然后创建一个忽略外部任何颜色的遮罩果岭周围的公差:
You need to work out what the BGR numbers for your green are (let's say for arguments sake [0, 255, 0]
), then create a mask that ignores any colours outside a tolerance around your green:
mask = cv2.inRange(image, lower, upper)
看看此教程一步一步来.
上下左右玩耍以获得正确的行为.然后,您可以在遮罩中找到轮廓:
Play around with lower and upper to get the right behaviour. Then you can find the contours in the mask:
_, contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_NONE)
然后在contours
列表中查找最大的列表(过滤掉所有可能的噪音):
Then go through the contours
list to find the biggest one (filter out any possible noise):
blob = max(contours, key=lambda el: cv2.contourArea(el))
这是您最后的斑点".您可以通过以下方法找到中心:
And that's your final 'blob'. You can find the center by doing:
M = cv2.moments(blob)
center = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))
您可以将此中心绘制到图像的副本上,以进行检查:
You can draw this center onto a copy of your image, for checking:
canvas = im.copy()
cv2.circle(canvas, center, 2, (0,0,255), -1)
显然,这是假设图像中只有一个绿色的球,而没有其他绿色.但这是一个开始.
Obviously, this makes the assumption that there's only one green ball and nothing else green in the image. But it's a start.
编辑-响应第二个帖子
我认为以下应该可行.我还没有测试过,但是您应该至少可以使用显示的画布和蒙版进行更多的调试:
I think the following should work. I haven't tested it, but you should be able to at least do a bit more debugging with the canvas and mask displayed:
# Standard imports
import cv2
import numpy as np;
# Read image
cam = cv2.VideoCapture(0)
while(1):
ret, frame = cam.read()
if not ret:
break
canvas = frame.copy()
lower = (130,150,80) #130,150,80
upper = (250,250,120) #250,250,120
mask = cv2.inRange(frame, lower, upper)
try:
# NB: using _ as the variable name for two of the outputs, as they're not used
_, contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
blob = max(contours, key=lambda el: cv2.contourArea(el))
M = cv2.moments(blob)
center = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))
cv2.circle(canvas, center, 2, (0,0,255), -1)
except (ValueError, ZeroDivisionError):
pass
cv2.imshow('frame',frame)
cv2.imshow('canvas',canvas)
cv2.imshow('mask',mask)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
im.release()
cv2.destroyAllWindows()
这篇关于检测不同颜色的blob opencv的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!