Opencv：检测点击图片的鼠标位置
Opencv: detect mouse position clicking over a picture
我有这段代码，其中我使用 OpenCV 简单地显示图像：
import numpy as np
import cv2
class LoadImage:
def loadImage(self):
self.img=cv2.imread('photo.png')
cv2.imshow('Test',self.img)
self.pressedkey=cv2.waitKey(0)
# Wait for ESC key to exit
if self.pressedkey==27:
cv2.destroyAllWindows()
# Start of the main program here
if __name__=="__main__":
LI=LoadImage()
LI.loadImage()
一旦 window 显示其中的照片，我想在控制台（终端）上显示单击图片时鼠标的位置。我不知道如何执行此操作。有什么帮助吗？
这里是一个鼠标回调函数的例子，捕获左键双击
def draw_circle(event,x,y,flags,param):
global mouseX,mouseY
if event == cv2.EVENT_LBUTTONDBLCLK:
cv2.circle(img,(x,y),100,(255,0,0),-1)
mouseX,mouseY = x,y
然后您需要将该函数绑定到 window 以捕获鼠标点击
img = np.zeros((512,512,3), np.uint8)
cv2.namedWindow('image')
cv2.setMouseCallback('image',draw_circle)
然后，在无限处理循环中（或任何你想要的）
while(1):
cv2.imshow('image',img)
k = cv2.waitKey(20) & 0xFF
if k == 27:
break
elif k == ord('a'):
print mouseX,mouseY
这段代码有什么作用？
它在全局变量mouseX & mouseY 中存储鼠标位置，每次在黑色内部双击window 并按下a 键 将被创建。
elif k == ord('a'):
print mouseX,mouseY
每次按下 a 按钮时都会打印当前存储的鼠标点击位置。
代码 "Borrowed" 来自 here.
下面是我的实现：
无需存储点击位置，仅显示：
def onMouse(event, x, y, flags, param):
if event == cv2.EVENT_LBUTTONDOWN:
# draw circle here (etc...)
print('x = %d, y = %d'%(x, y))
cv2.setMouseCallback('WindowName', onMouse)
如果你想在你的代码的其他地方使用位置，你可以使用以下方式获取坐标：
posList = []
def onMouse(event, x, y, flags, param):
global posList
if event == cv2.EVENT_LBUTTONDOWN:
posList.append((x, y))
cv2.setMouseCallback('WindowName', onMouse)
posNp = np.array(posList) # convert to NumPy for later use
我已将 PyIgnition 库从 Pygame 移植到 opencv2。在 https://github.com/bunkahle/particlescv2 找到代码
还有几个关于如何使用粒子引擎的示例 Python。
import cv2
cv2.imshow("image", img)
cv2.namedWindow('image')
cv2.setMouseCallback('image', on_click)
def on_click(event, x, y, p1, p2):
if event == cv2.EVENT_LBUTTONDOWN:
cv2.circle(lastImage, (x, y), 3, (255, 0, 0), -1)
您可以通过执行各种鼠标单击事件来检测鼠标在图片上的位置。
你只需要记住一件事，当执行鼠标点击事件时，你应该在任何地方使用相同的 window 名称，无论你使用 cv2.imshow 或 cv2.namedWindow
我在下面的 Whosebug post 中给出了使用 python 3.x 和 opencv 的工作代码：
你可以参考上面的link以获得更好的解释。
代码：
import cv2
import numpy as np
#This will display all the available mouse click events
events = [i for i in dir(cv2) if 'EVENT' in i]
print(events)
#This variable we use to store the pixel location
refPt = []
#click event function
def click_event(event, x, y, flags, param):
if event == cv2.EVENT_LBUTTONDOWN:
print(x,",",y)
refPt.append([x,y])
font = cv2.FONT_HERSHEY_SIMPLEX
strXY = str(x)+", "+str(y)
cv2.putText(img, strXY, (x,y), font, 0.5, (255,255,0), 2)
cv2.imshow("image", img)
if event == cv2.EVENT_RBUTTONDOWN:
blue = img[y, x, 0]
green = img[y, x, 1]
red = img[y, x, 2]
font = cv2.FONT_HERSHEY_SIMPLEX
strBGR = str(blue)+", "+str(green)+","+str(red)
cv2.putText(img, strBGR, (x,y), font, 0.5, (0,255,255), 2)
cv2.imshow("image", img)
#Here, you need to change the image name and it's path according to your directory
img = cv2.imread("D:/pictures/abc.jpg")
cv2.imshow("image", img)
#calling the mouse click event
cv2.setMouseCallback("image", click_event)
cv2.waitKey(0)
cv2.destroyAllWindows()
这是基于 class 的 OpenCV 鼠标回调实现，用于获取图像上的点，
import cv2
import numpy as np
#events = [i for i in dir(cv2) if 'EVENT' in i]
#print (events)
class MousePts:
def __init__(self,windowname,img):
self.windowname = windowname
self.img1 = img.copy()
self.img = self.img1.copy()
cv2.namedWindow(windowname,cv2.WINDOW_NORMAL)
cv2.imshow(windowname,img)
self.curr_pt = []
self.point = []
def select_point(self,event,x,y,flags,param):
if event == cv2.EVENT_LBUTTONDOWN:
self.point.append([x,y])
#print(self.point)
cv2.circle(self.img,(x,y),5,(0,255,0),-1)
elif event == cv2.EVENT_MOUSEMOVE:
self.curr_pt = [x,y]
#print(self.point)
def getpt(self,count=1,img=None):
if img is not None:
self.img = img
else:
self.img = self.img1.copy()
cv2.namedWindow(self.windowname,cv2.WINDOW_NORMAL)
cv2.imshow(self.windowname,self.img)
cv2.setMouseCallback(self.windowname,self.select_point)
self.point = []
while(1):
cv2.imshow(self.windowname,self.img)
k = cv2.waitKey(20) & 0xFF
if k == 27 or len(self.point)>=count:
break
#print(self.point)
cv2.setMouseCallback(self.windowname, lambda *args : None)
#cv2.destroyAllWindows()
return self.point, self.img
if __name__=='__main__':
img = np.zeros((512,512,3), np.uint8)
windowname = 'image'
coordinateStore = MousePts(windowname,img)
pts,img = coordinateStore.getpt(3)
print(pts)
pts,img = coordinateStore.getpt(3,img)
print(pts)
cv2.imshow(windowname,img)
cv2.waitKey(0)
如果您想通过将鼠标悬停在 Python 3 中的图像上来获取坐标，您可以试试这个：
import numpy as np
import cv2 as cv
import os
import sys
# Reduce the size of image by this number to show completely in screen
descalingFactor = 2
# mouse callback function, which will print the coordinates in console
def print_coord(event,x,y,flags,param):
if event == cv.EVENT_MOUSEMOVE:
print(f'{x*descalingFactor, y*descalingFactor}\r', end="")
img = cv.imread(cv.samples.findFile('TestImage.png'))
imgheight, imgwidth = img.shape[:2]
resizedImg = cv.resize(img,(int(imgwidth/descalingFactor), int(imgheight/descalingFactor)), interpolation = cv.INTER_AREA)
cv.namedWindow('Get Coordinates')
cv.setMouseCallback('Get Coordinates',print_coord)
cv.imshow('Get Coordinates',resizedImg)
cv.waitKey(0)
如果有人想要一个 multi-process-based GUI 来绘制点并拖动以移动它们，这里有一个 single file script 同样的。
我有这段代码，其中我使用 OpenCV 简单地显示图像：
import numpy as np
import cv2
class LoadImage:
def loadImage(self):
self.img=cv2.imread('photo.png')
cv2.imshow('Test',self.img)
self.pressedkey=cv2.waitKey(0)
# Wait for ESC key to exit
if self.pressedkey==27:
cv2.destroyAllWindows()
# Start of the main program here
if __name__=="__main__":
LI=LoadImage()
LI.loadImage()
一旦 window 显示其中的照片，我想在控制台（终端）上显示单击图片时鼠标的位置。我不知道如何执行此操作。有什么帮助吗？
这里是一个鼠标回调函数的例子，捕获左键双击
def draw_circle(event,x,y,flags,param):
global mouseX,mouseY
if event == cv2.EVENT_LBUTTONDBLCLK:
cv2.circle(img,(x,y),100,(255,0,0),-1)
mouseX,mouseY = x,y
然后您需要将该函数绑定到 window 以捕获鼠标点击
img = np.zeros((512,512,3), np.uint8)
cv2.namedWindow('image')
cv2.setMouseCallback('image',draw_circle)
然后，在无限处理循环中（或任何你想要的）
while(1):
cv2.imshow('image',img)
k = cv2.waitKey(20) & 0xFF
if k == 27:
break
elif k == ord('a'):
print mouseX,mouseY
这段代码有什么作用？
它在全局变量mouseX & mouseY 中存储鼠标位置，每次在黑色内部双击window 并按下a 键 将被创建。
elif k == ord('a'):
print mouseX,mouseY
每次按下 a 按钮时都会打印当前存储的鼠标点击位置。
代码 "Borrowed" 来自 here.
下面是我的实现：
无需存储点击位置，仅显示：
def onMouse(event, x, y, flags, param):
if event == cv2.EVENT_LBUTTONDOWN:
# draw circle here (etc...)
print('x = %d, y = %d'%(x, y))
cv2.setMouseCallback('WindowName', onMouse)
如果你想在你的代码的其他地方使用位置，你可以使用以下方式获取坐标：
posList = []
def onMouse(event, x, y, flags, param):
global posList
if event == cv2.EVENT_LBUTTONDOWN:
posList.append((x, y))
cv2.setMouseCallback('WindowName', onMouse)
posNp = np.array(posList) # convert to NumPy for later use
我已将 PyIgnition 库从 Pygame 移植到 opencv2。在 https://github.com/bunkahle/particlescv2 找到代码 还有几个关于如何使用粒子引擎的示例 Python。
import cv2
cv2.imshow("image", img)
cv2.namedWindow('image')
cv2.setMouseCallback('image', on_click)
def on_click(event, x, y, p1, p2):
if event == cv2.EVENT_LBUTTONDOWN:
cv2.circle(lastImage, (x, y), 3, (255, 0, 0), -1)
您可以通过执行各种鼠标单击事件来检测鼠标在图片上的位置。
你只需要记住一件事，当执行鼠标点击事件时，你应该在任何地方使用相同的 window 名称，无论你使用 cv2.imshow 或 cv2.namedWindow
我在下面的 Whosebug post 中给出了使用 python 3.x 和 opencv 的工作代码：
你可以参考上面的link以获得更好的解释。
代码：
import cv2
import numpy as np
#This will display all the available mouse click events
events = [i for i in dir(cv2) if 'EVENT' in i]
print(events)
#This variable we use to store the pixel location
refPt = []
#click event function
def click_event(event, x, y, flags, param):
if event == cv2.EVENT_LBUTTONDOWN:
print(x,",",y)
refPt.append([x,y])
font = cv2.FONT_HERSHEY_SIMPLEX
strXY = str(x)+", "+str(y)
cv2.putText(img, strXY, (x,y), font, 0.5, (255,255,0), 2)
cv2.imshow("image", img)
if event == cv2.EVENT_RBUTTONDOWN:
blue = img[y, x, 0]
green = img[y, x, 1]
red = img[y, x, 2]
font = cv2.FONT_HERSHEY_SIMPLEX
strBGR = str(blue)+", "+str(green)+","+str(red)
cv2.putText(img, strBGR, (x,y), font, 0.5, (0,255,255), 2)
cv2.imshow("image", img)
#Here, you need to change the image name and it's path according to your directory
img = cv2.imread("D:/pictures/abc.jpg")
cv2.imshow("image", img)
#calling the mouse click event
cv2.setMouseCallback("image", click_event)
cv2.waitKey(0)
cv2.destroyAllWindows()
这是基于 class 的 OpenCV 鼠标回调实现，用于获取图像上的点，
import cv2
import numpy as np
#events = [i for i in dir(cv2) if 'EVENT' in i]
#print (events)
class MousePts:
def __init__(self,windowname,img):
self.windowname = windowname
self.img1 = img.copy()
self.img = self.img1.copy()
cv2.namedWindow(windowname,cv2.WINDOW_NORMAL)
cv2.imshow(windowname,img)
self.curr_pt = []
self.point = []
def select_point(self,event,x,y,flags,param):
if event == cv2.EVENT_LBUTTONDOWN:
self.point.append([x,y])
#print(self.point)
cv2.circle(self.img,(x,y),5,(0,255,0),-1)
elif event == cv2.EVENT_MOUSEMOVE:
self.curr_pt = [x,y]
#print(self.point)
def getpt(self,count=1,img=None):
if img is not None:
self.img = img
else:
self.img = self.img1.copy()
cv2.namedWindow(self.windowname,cv2.WINDOW_NORMAL)
cv2.imshow(self.windowname,self.img)
cv2.setMouseCallback(self.windowname,self.select_point)
self.point = []
while(1):
cv2.imshow(self.windowname,self.img)
k = cv2.waitKey(20) & 0xFF
if k == 27 or len(self.point)>=count:
break
#print(self.point)
cv2.setMouseCallback(self.windowname, lambda *args : None)
#cv2.destroyAllWindows()
return self.point, self.img
if __name__=='__main__':
img = np.zeros((512,512,3), np.uint8)
windowname = 'image'
coordinateStore = MousePts(windowname,img)
pts,img = coordinateStore.getpt(3)
print(pts)
pts,img = coordinateStore.getpt(3,img)
print(pts)
cv2.imshow(windowname,img)
cv2.waitKey(0)
如果您想通过将鼠标悬停在 Python 3 中的图像上来获取坐标，您可以试试这个：
import numpy as np
import cv2 as cv
import os
import sys
# Reduce the size of image by this number to show completely in screen
descalingFactor = 2
# mouse callback function, which will print the coordinates in console
def print_coord(event,x,y,flags,param):
if event == cv.EVENT_MOUSEMOVE:
print(f'{x*descalingFactor, y*descalingFactor}\r', end="")
img = cv.imread(cv.samples.findFile('TestImage.png'))
imgheight, imgwidth = img.shape[:2]
resizedImg = cv.resize(img,(int(imgwidth/descalingFactor), int(imgheight/descalingFactor)), interpolation = cv.INTER_AREA)
cv.namedWindow('Get Coordinates')
cv.setMouseCallback('Get Coordinates',print_coord)
cv.imshow('Get Coordinates',resizedImg)
cv.waitKey(0)
如果有人想要一个 multi-process-based GUI 来绘制点并拖动以移动它们，这里有一个 single file script 同样的。