task2：图像储存、色彩空间、图像的算数运算。
笔记:
使用managers.WindowManager抽象窗口和键盘:
main.py:
import cv2
from manager import WindowManager, CaptureManager
class Cameo(object):
def init (self):
self._windowManager = WindowManager('Cameo', self.onKeypress)
self._captureManager = CaptureManager(cv2.VideoCapture(0), self._windowManager, True)
def run(self):
self._windowManager.createWindow()
while self._windowManager.isWindowCreated:
self._captureManager.enterFrame()
frame = self._captureManager.frame
# TODO: Filter the frame (Chapter 3).
self._captureManager.exitFrame()
self._windowManager.processEvents()
def onKeypress (self,keycode):
if keycode == 32: # space
self._captureManager.writelmage('me1.jpg')
elif keycode == 9: # tab
if not self._captureManager.isWritingVideo:
self._captureManager.startwritingvideo('output.avi')
else:
self._captureManager.stopWritingVideo()
elif keycode == 27: # escape
self._windowManager.destroyWindow()
if __name__ == '__main__':
Cameo().run()
manager.py:
import cv2
class CaptureManager(object):
def init (self, capture, previewWindowManager = None,shouldMirrorPreview = False):
self.previewWindowManager = previewWindowManager
self.shouldMirrorPreview = shouldMirrorPreview
self._capture = capture
self._channel = 0
self. enteredFrame = False
self._frame = None
self._imageFilename = None
self._videoFilename = None
self._videoEncoding = None
self._videoWriter = None
self._startTime = None
self._framesElapsed = int(0)
self._fpsEstimate = None
@property
def channel(self):
return self._channel
@channel.setter
def channel(self, value):
if self._channel != value:
self._channel = value
self._frame = None
@property
def frame(self):
if self._enteredFrame and self._frame is None:
self._frame = self._capture.retrieve()
return self._frame
@property
def isWritinglmage (self):
return self._imageFilename is not None
@property
def isWritingVideo(self):
return self._videoFilename is not None
class WindowManager(object):
def init (self, windowName,keypressCallback = None):
self.keypressCallback = keypressCallback
self._windowName = windowName
self._isWindowCreated = False
@property
def isWindowCreated(self):
return self._isWindowCreated
def createWindow (self):
cv2.namedWindow(self._windowName)
self._isWindowCreated = True
def show(self, frame):
cv2.imshow(self._windowName, frame)
def destroyWindow (self):
cv2.destroyWindow(self._windowName)
self._isWindowCreated = False
def processEvents (self):
keycode = cv2.waitKey(1)
if self.keypressCallback is not None and keycode != -1:
# Discard any non-ASCII info encoded by GTK.
self.keypressCallback(keycode)
ps:这个代码运行以后显示：
File “C:\Users\14172\PycharmProjects\pythonProject3\main.py”, line
25, in run
self._windowManager.createWindow() AttributeError: ‘Cameo’ object has no attribute ‘_windowManager’
还没找出问题。
HSV和RGB
OpenCV中有数百种关于在不同色彩空间之间转换的方法。当前，在计算机视觉中有三 种常用的色彩空间：灰度、BGR以及HSV (Hue, Saturation, Value)o
□灰度色彩空间是通过去除彩色信息来将其转换成灰阶，灰度色彩空间对中间处理特 别有效，比如人脸检测。
□ BGR,即蓝-绿-红色彩空间，每一个像素点都由一个三元数组来表示，分别代表 蓝、绿、红三种颜色。网页开发者可能熟悉另一个与之相似的颜色空间：RGB,它 们只是在颜色的顺序上不同。
□ HSV, H ( Hue)是色调，S ( Saturation)是饱和度，V (Value)表示黑暗的程度(或 光谱另一端的明亮程度)。
BGR图像中像素B，G和R的取值与落在物体上的光相关，因此这些值也彼此相关，无法准确描述像素。相反，HSV空间中，三者相对独立，可以准确描述像素的亮度，饱和度和色度。
RGB色彩空间是一种被广泛接受的色彩空间，但是它过于抽象，我们不能直接通过其值感知具体的色彩，HSV色彩空间我们可以更加方便地通过色调 饱和度 亮度来感知颜色。
H色调 S饱和度 V亮度 色调0为红色，300为品红色
亮度为0时图像是纯黑色
img[0,0,0]=255将该像素点第0个通道（即B通道）设置为255，即该点指定为蓝色。
绿色的色调为60 蓝色为120
示例:
blue = np.zeros([1,1,3],dtype=np.uint8)
blue[0,0,0] = 255
bluet0 = cv2.cvtColor(blue,cv2.COLOR_BGR2HSV)
print(blue)
print(bluet0)
结果:
HSV模式中各种颜色的范围：
蓝色-[110,100,100]到[130,255,255]之间
绿色-值在[50,100,100]和,[70,255,255]之间
红色-[0,100,100]， [10,255,255]之间
通过掩码的按位与运算，锁定颜色区域：
img = cv2.imread("me1.jpg")
img2 = cv2.cvtColor(img,cv2.COLOR_BGR2HSV)
minred =np.array( [0,50,50])
maxred = np.array([30,255,255])
#确定红色区域
mask = cv2.inRange(img2,minred,maxred)
#按位与运算 提取蓝色区域
img3 = cv2.bitwise_and(img,img,mask=mask)
cv2.imshow("img",img3)
结果:=
傅里叶变换
在OpenCV中，对图像和视频的大多数处理都或多或少会涉及傅里叶变换的概念。
也就是说，人们所看到的波形都是由其他波形叠加得到的。这个概念对操作图像非常 有帮助，因为这样我们可以区分图像里哪些区域的信号（比如图像像素）变化特别强，哪些区域的信号变化不那么强，从而可以任意地标记噪声区域、感兴趣区域、前景和背景等。 原始图像由许多频率组成，人们能够分离这些频率来理解图像和提取感兴趣的数据。
傅里叶变换的概念是许多常见的图像处理操作的基础，比如边缘检测或线段和形状 检测。
下面先介绍两个概念：高通滤波器和低通滤波器，上面提到的那些操作都是以这两个 概念和傅里叶变换为基础。
3.2.1高通滤波器
高通滤波器（HPF）是检测图像的某个区域，然后根据像素与周围像素的亮度差值来提 升（boost）该像素的亮度的滤波器。
边缘检测
OpenCV提供了许多边缘检测滤波函数，包括Laplacian、Sobel()以及Scharr()这些滤波函数都会将非边缘区域转为黑色，将边缘区域转为白色或其他饱和的颜色。但是， 这些函数都很容易将噪声错误地识别为边缘。缓解这个问题的方法是在找到边缘之前对图 像进行模糊处理。OpenCV也提供了许多模糊滤波函数，包括blur()(简单的算术平均)、 medianBlur()以及GaussianBlur()。边缘检测滤波函数和模糊滤波函数的参数有很多，但总会有一个ksize参数，它是一个奇数，表示滤波核的宽和高(以像素为单位)。
这里使用medianBlur()作为模糊函数，它对去除数字化的视频噪声•非常有效，特别是去除彩色图像的噪声；使用Laplacian()作为边缘检测函数，它会产生明显的边缘线条，灰度图像更是如此。在使用medianBlur()函数之后，将要使用L aplacian ()函数之前，需要将 图像从BGR色彩空间转为灰度色彩空间。
在得到Laplacian()函数的结果之后，需要将其转换成黑色边缘和白色背景的图像。然 后将其归一化(使它的像素值在0到1之间)，并乘以源图像以便能将边缘变黑。
代码测试
flags = [i for i in dir(cv) if i.startswith('COLOR_')]
print(flags)
输出:
C:\Users\14172\PycharmProjects\pythonProject3\venv\Scripts\python.exe C:/Users/14172/PycharmProjects/pythonProject3/main.py
[‘COLOR_BAYER_BG2BGR’, ‘COLOR_BAYER_BG2BGRA’, ‘COLOR_BAYER_BG2BGR_EA’, ‘COLOR_BAYER_BG2BGR_VNG’, ‘COLOR_BAYER_BG2GRAY’, ‘COLOR_BAYER_BG2RGB’, ‘COLOR_BAYER_BG2RGBA’, ‘COLOR_BAYER_BG2RGB_EA’, ‘COLOR_BAYER_BG2RGB_VNG’, ‘COLOR_BAYER_GB2BGR’, ‘COLOR_BAYER_GB2BGRA’, ‘COLOR_BAYER_GB2BGR_EA’, ‘COLOR_BAYER_GB2BGR_VNG’, ‘COLOR_BAYER_GB2GRAY’, ‘COLOR_BAYER_GB2RGB’, ‘COLOR_BAYER_GB2RGBA’, ‘COLOR_BAYER_GB2RGB_EA’, ‘COLOR_BAYER_GB2RGB_VNG’, ‘COLOR_BAYER_GR2BGR’, ‘COLOR_BAYER_GR2BGRA’, ‘COLOR_BAYER_GR2BGR_EA’, ‘COLOR_BAYER_GR2BGR_VNG’, ‘COLOR_BAYER_GR2GRAY’, ‘COLOR_BAYER_GR2RGB’, ‘COLOR_BAYER_GR2RGBA’, ‘COLOR_BAYER_GR2RGB_EA’, ‘COLOR_BAYER_GR2RGB_VNG’, ‘COLOR_BAYER_RG2BGR’, ‘COLOR_BAYER_RG2BGRA’, ‘COLOR_BAYER_RG2BGR_EA’, ‘COLOR_BAYER_RG2BGR_VNG’, ‘COLOR_BAYER_RG2GRAY’, ‘COLOR_BAYER_RG2RGB’, ‘COLOR_BAYER_RG2RGBA’, ‘COLOR_BAYER_RG2RGB_EA’, ‘COLOR_BAYER_RG2RGB_VNG’, ‘COLOR_BGR2BGR555’, ‘COLOR_BGR2BGR565’, ‘COLOR_BGR2BGRA’, ‘COLOR_BGR2GRAY’, ‘COLOR_BGR2HLS’, ‘COLOR_BGR2HLS_FULL’, ‘COLOR_BGR2HSV’, ‘COLOR_BGR2HSV_FULL’, ‘COLOR_BGR2LAB’, ‘COLOR_BGR2LUV’, ‘COLOR_BGR2Lab’, ‘COLOR_BGR2Luv’, ‘COLOR_BGR2RGB’, ‘COLOR_BGR2RGBA’, ‘COLOR_BGR2XYZ’, ‘COLOR_BGR2YCR_CB’, ‘COLOR_BGR2YCrCb’, ‘COLOR_BGR2YUV’, ‘COLOR_BGR2YUV_I420’, ‘COLOR_BGR2YUV_IYUV’, ‘COLOR_BGR2YUV_YV12’, ‘COLOR_BGR5552BGR’, ‘COLOR_BGR5552BGRA’, ‘COLOR_BGR5552GRAY’, ‘COLOR_BGR5552RGB’, ‘COLOR_BGR5552RGBA’, ‘COLOR_BGR5652BGR’, ‘COLOR_BGR5652BGRA’, ‘COLOR_BGR5652GRAY’, ‘COLOR_BGR5652RGB’, ‘COLOR_BGR5652RGBA’, ‘COLOR_BGRA2BGR’, ‘COLOR_BGRA2BGR555’, ‘COLOR_BGRA2BGR565’, ‘COLOR_BGRA2GRAY’, ‘COLOR_BGRA2RGB’, ‘COLOR_BGRA2RGBA’, ‘COLOR_BGRA2YUV_I420’, ‘COLOR_BGRA2YUV_IYUV’, ‘COLOR_BGRA2YUV_YV12’, ‘COLOR_BayerBG2BGR’, ‘COLOR_BayerBG2BGRA’, ‘COLOR_BayerBG2BGR_EA’, ‘COLOR_BayerBG2BGR_VNG’, ‘COLOR_BayerBG2GRAY’, ‘COLOR_BayerBG2RGB’, ‘COLOR_BayerBG2RGBA’, ‘COLOR_BayerBG2RGB_EA’, ‘COLOR_BayerBG2RGB_VNG’, ‘COLOR_BayerGB2BGR’, ‘COLOR_BayerGB2BGRA’, ‘COLOR_BayerGB2BGR_EA’, ‘COLOR_BayerGB2BGR_VNG’, ‘COLOR_BayerGB2GRAY’, ‘COLOR_BayerGB2RGB’, ‘COLOR_BayerGB2RGBA’, ‘COLOR_BayerGB2RGB_EA’, ‘COLOR_BayerGB2RGB_VNG’, ‘COLOR_BayerGR2BGR’, ‘COLOR_BayerGR2BGRA’, ‘COLOR_BayerGR2BGR_EA’, ‘COLOR_BayerGR2BGR_VNG’, ‘COLOR_BayerGR2GRAY’, ‘COLOR_BayerGR2RGB’, ‘COLOR_BayerGR2RGBA’, ‘COLOR_BayerGR2RGB_EA’, ‘COLOR_BayerGR2RGB_VNG’, ‘COLOR_BayerRG2BGR’, ‘COLOR_BayerRG2BGRA’, ‘COLOR_BayerRG2BGR_EA’, ‘COLOR_BayerRG2BGR_VNG’, ‘COLOR_BayerRG2GRAY’, ‘COLOR_BayerRG2RGB’, ‘COLOR_BayerRG2RGBA’, ‘COLOR_BayerRG2RGB_EA’, ‘COLOR_BayerRG2RGB_VNG’, ‘COLOR_COLORCVT_MAX’, ‘COLOR_GRAY2BGR’, ‘COLOR_GRAY2BGR555’, ‘COLOR_GRAY2BGR565’, ‘COLOR_GRAY2BGRA’, ‘COLOR_GRAY2RGB’, ‘COLOR_GRAY2RGBA’, ‘COLOR_HLS2BGR’, ‘COLOR_HLS2BGR_FULL’, ‘COLOR_HLS2RGB’, ‘COLOR_HLS2RGB_FULL’, ‘COLOR_HSV2BGR’, ‘COLOR_HSV2BGR_FULL’, ‘COLOR_HSV2RGB’, ‘COLOR_HSV2RGB_FULL’, ‘COLOR_LAB2BGR’, ‘COLOR_LAB2LBGR’, ‘COLOR_LAB2LRGB’, ‘COLOR_LAB2RGB’, ‘COLOR_LBGR2LAB’, ‘COLOR_LBGR2LUV’, ‘COLOR_LBGR2Lab’, ‘COLOR_LBGR2Luv’, ‘COLOR_LRGB2LAB’, ‘COLOR_LRGB2LUV’, ‘COLOR_LRGB2Lab’, ‘COLOR_LRGB2Luv’, ‘COLOR_LUV2BGR’, ‘COLOR_LUV2LBGR’, ‘COLOR_LUV2LRGB’, ‘COLOR_LUV2RGB’, ‘COLOR_Lab2BGR’, ‘COLOR_Lab2LBGR’, ‘COLOR_Lab2LRGB’, ‘COLOR_Lab2RGB’, ‘COLOR_Luv2BGR’, ‘COLOR_Luv2LBGR’, ‘COLOR_Luv2LRGB’, ‘COLOR_Luv2RGB’, ‘COLOR_M_RGBA2RGBA’, ‘COLOR_RGB2BGR’, ‘COLOR_RGB2BGR555’, ‘COLOR_RGB2BGR565’, ‘COLOR_RGB2BGRA’, ‘COLOR_RGB2GRAY’, ‘COLOR_RGB2HLS’, ‘COLOR_RGB2HLS_FULL’, ‘COLOR_RGB2HSV’, ‘COLOR_RGB2HSV_FULL’, ‘COLOR_RGB2LAB’, ‘COLOR_RGB2LUV’, ‘COLOR_RGB2Lab’, ‘COLOR_RGB2Luv’, ‘COLOR_RGB2RGBA’, ‘COLOR_RGB2XYZ’, ‘COLOR_RGB2YCR_CB’, ‘COLOR_RGB2YCrCb’, ‘COLOR_RGB2YUV’, ‘COLOR_RGB2YUV_I420’, ‘COLOR_RGB2YUV_IYUV’, ‘COLOR_RGB2YUV_YV12’, ‘COLOR_RGBA2BGR’, ‘COLOR_RGBA2BGR555’, ‘COLOR_RGBA2BGR565’, ‘COLOR_RGBA2BGRA’, ‘COLOR_RGBA2GRAY’, ‘COLOR_RGBA2M_RGBA’, ‘COLOR_RGBA2RGB’, ‘COLOR_RGBA2YUV_I420’, ‘COLOR_RGBA2YUV_IYUV’, ‘COLOR_RGBA2YUV_YV12’, ‘COLOR_RGBA2mRGBA’, ‘COLOR_XYZ2BGR’, ‘COLOR_XYZ2RGB’, ‘COLOR_YCR_CB2BGR’, ‘COLOR_YCR_CB2RGB’, ‘COLOR_YCrCb2BGR’, ‘COLOR_YCrCb2RGB’, ‘COLOR_YUV2BGR’, ‘COLOR_YUV2BGRA_I420’, ‘COLOR_YUV2BGRA_IYUV’, ‘COLOR_YUV2BGRA_NV12’, ‘COLOR_YUV2BGRA_NV21’, ‘COLOR_YUV2BGRA_UYNV’, ‘COLOR_YUV2BGRA_UYVY’, ‘COLOR_YUV2BGRA_Y422’, ‘COLOR_YUV2BGRA_YUNV’, ‘COLOR_YUV2BGRA_YUY2’, ‘COLOR_YUV2BGRA_YUYV’, ‘COLOR_YUV2BGRA_YV12’, ‘COLOR_YUV2BGRA_YVYU’, ‘COLOR_YUV2BGR_I420’, ‘COLOR_YUV2BGR_IYUV’, ‘COLOR_YUV2BGR_NV12’, ‘COLOR_YUV2BGR_NV21’, ‘COLOR_YUV2BGR_UYNV’, ‘COLOR_YUV2BGR_UYVY’, ‘COLOR_YUV2BGR_Y422’, ‘COLOR_YUV2BGR_YUNV’, ‘COLOR_YUV2BGR_YUY2’, ‘COLOR_YUV2BGR_YUYV’, ‘COLOR_YUV2BGR_YV12’, ‘COLOR_YUV2BGR_YVYU’, ‘COLOR_YUV2GRAY_420’, ‘COLOR_YUV2GRAY_I420’, ‘COLOR_YUV2GRAY_IYUV’, ‘COLOR_YUV2GRAY_NV12’, ‘COLOR_YUV2GRAY_NV21’, ‘COLOR_YUV2GRAY_UYNV’, ‘COLOR_YUV2GRAY_UYVY’, ‘COLOR_YUV2GRAY_Y422’, ‘COLOR_YUV2GRAY_YUNV’, ‘COLOR_YUV2GRAY_YUY2’, ‘COLOR_YUV2GRAY_YUYV’, ‘COLOR_YUV2GRAY_YV12’, ‘COLOR_YUV2GRAY_YVYU’, ‘COLOR_YUV2RGB’, ‘COLOR_YUV2RGBA_I420’, ‘COLOR_YUV2RGBA_IYUV’, ‘COLOR_YUV2RGBA_NV12’, ‘COLOR_YUV2RGBA_NV21’, ‘COLOR_YUV2RGBA_UYNV’, ‘COLOR_YUV2RGBA_UYVY’, ‘COLOR_YUV2RGBA_Y422’, ‘COLOR_YUV2RGBA_YUNV’, ‘COLOR_YUV2RGBA_YUY2’, ‘COLOR_YUV2RGBA_YUYV’, ‘COLOR_YUV2RGBA_YV12’, ‘COLOR_YUV2RGBA_YVYU’, ‘COLOR_YUV2RGB_I420’, ‘COLOR_YUV2RGB_IYUV’, ‘COLOR_YUV2RGB_NV12’, ‘COLOR_YUV2RGB_NV21’, ‘COLOR_YUV2RGB_UYNV’, ‘COLOR_YUV2RGB_UYVY’, ‘COLOR_YUV2RGB_Y422’, ‘COLOR_YUV2RGB_YUNV’, ‘COLOR_YUV2RGB_YUY2’, ‘COLOR_YUV2RGB_YUYV’, ‘COLOR_YUV2RGB_YV12’, ‘COLOR_YUV2RGB_YVYU’, ‘COLOR_YUV420P2BGR’, ‘COLOR_YUV420P2BGRA’, ‘COLOR_YUV420P2GRAY’, ‘COLOR_YUV420P2RGB’, ‘COLOR_YUV420P2RGBA’, ‘COLOR_YUV420SP2BGR’, ‘COLOR_YUV420SP2BGRA’, ‘COLOR_YUV420SP2GRAY’, ‘COLOR_YUV420SP2RGB’, ‘COLOR_YUV420SP2RGBA’, ‘COLOR_YUV420p2BGR’, ‘COLOR_YUV420p2BGRA’, ‘COLOR_YUV420p2GRAY’, ‘COLOR_YUV420p2RGB’, ‘COLOR_YUV420p2RGBA’, ‘COLOR_YUV420sp2BGR’, ‘COLOR_YUV420sp2BGRA’, ‘COLOR_YUV420sp2GRAY’, ‘COLOR_YUV420sp2RGB’, ‘COLOR_YUV420sp2RGBA’, ‘COLOR_mRGBA2RGBA’]
Process finished with exit code 0
在蓝色物体附件画圈：
import cv2 as cv
import numpy as np
if __name__ == '__main__':
cap = cv.VideoCapture(0)
while (1):
# Take each frame
_, frame = cap.read()
# Convert BGR to HSV
hsv = cv.cvtColor(frame, cv.COLOR_BGR2HSV)
# define range of blue color in HSV
lower_blue = np.array([110, 50, 50])
upper_blue = np.array([130, 255, 255])
# Threshold the HSV image to get only blue colors
mask = cv.inRange(hsv, lower_blue, upper_blue)
# Bitwise-AND mask and original image
res = cv.bitwise_and(frame, frame, mask=mask)
cv.imshow('frame', frame)
cv.imshow('mask', mask)
cv.imshow('res', res)
k = cv.waitKey(5) & 0xFF
if k == 27:
break
cv.destroyAllWindows()
效果：
将参数修改
lower_blue = np.array([100, 50, 50])
之后效果:
一份用c++画矩形的代码:
#include "opencv2/opencv.hpp"
using namespace cv;
void main()
{
Mat src = imread("bird.jpg");
Rect rect(230, 5, 280, 290);//左上坐标（x,y）和矩形的长(x)宽(y)
cv::rectangle(src, rect, Scalar(255, 0, 0),1, LINE_8,0);
//cv::rectangle(src, Point(230, 5), Point(510, 295), Scalar(255, 0, 0), 1, LINE_8, 0);//左上角点的(x,y)，右下角点的(x,y)
// cv::rectangle(src, rect, Scalar(255, 0, 0),-1, LINE_8,0);//绘制填充矩形
imwrite("src.png", src);
imshow("src", src);
waitKey(0);
}
习题
代码调用电脑摄像头，寻找视野中任意颜色（自定）并具有一定大小的物体，并用矩形框处，最后显示在图像上；
知道了怎么用圆形框住，还没有框矩形:
代码:
cap = cv.VideoCapture(0)
while True:
# 读取每一帧
_, frame = cap.read()
# 重设图片尺寸以提高计算速度
frame = imutils.resize(frame, width=600)
# 进行高斯模糊
blurred = cv.GaussianBlur(frame, (11, 11), 0)
# 转换颜色空间到HSV
hsv = cv.cvtColor(blurred, cv.COLOR_BGR2HSV)
# 定义蓝色阈值
lower_red = np.array([100, 100, 100])
upper_red = np.array([130, 255, 255])
# 对图片进行二值化处理
mask = cv.inRange(hsv, lower_red, upper_red)
# 腐蚀操作
mask = cv.erode(mask, None, iterations=2)
# 膨胀操作，先腐蚀后膨胀以滤除噪声
mask = cv.dilate(mask, None, iterations=2)
cv.imshow('mask', mask)
# 寻找图中轮廓
cnts = cv.findContours(mask.copy(), cv.RETR_EXTERNAL, cv.CHAIN_APPROX_SIMPLE)[-2]
# 如果存在至少一个轮廓则进行如下操作
if len(cnts) > 0:
# 找到面积最大的轮廓
c = max(cnts, key=cv.contourArea)
# 使用最小外接圆圈出面积最大的轮廓
((x, y), radius) = cv.minEnclosingCircle(c)
# 计算轮廓的矩
M = cv.moments(c)
# 计算轮廓的重心
center = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))
# 只处理尺寸足够大的轮廓
if radius > 5:
# 画出最小外接圆
cv.circle(frame, (int(x), int(y)), int(radius), (0, 255, 255), 2)
# 画出重心
cv.circle(frame, center, 5, (0, 0, 255), -1)
cv.imshow('frame', frame)
k = cv.waitKey(5) & 0xFF
if k == 27:
break
cap.release()
cv.destroyAllWindows()
效果：
框正矩形:
其余句子不变，if后面改成这个：
if len(cnts) > 0:
# 找到面积最大的轮廓
c = max(cnts, key=cv.contourArea)
# 使用最小外接圆圈出面积最大的轮廓
x,y,w,h = cv.boundingRect(c)
cv.rectangle(frame,(x,y), (x+w,y+h), (0, 255, 255), 2)
cv2.boundingRect(img)这个函数很简单，img是一个二值图，也就是它的参数；返回四个值，分别是x，y，w，h；
x，y是矩阵左上点的坐标，w，h是矩阵的宽和高
换一个颜色试试：
阈值设置要准确，才能正确框住。
还有一个框斜矩形的：
minAreaRect函数返回矩形的中心点坐标，长宽，旋转角度[-90,0)，当矩形水平或竖直时均返回-90
以rect作为它的返回值则有:
centar = rect[0] width,height = rect[1] （注意第二个返回值是一个数组）
if __name__ == '__main__':
img = cv2.imread("me1.jpg")
cv2.rectangle(img, (130, 250), (200,400), (0, 255, 0), 2)
cv2.imshow("nn",img)
cv2.waitKey()
提取轮廓:
import cv2
if __name__ == '__main__':
img = cv2.imread("me1.jpg")
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret, binary = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)
contours, hierarchy = cv2.findContours(binary, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours(img, contours, -1, (0, 0, 255), 3)
cv2.imshow("img", img)
cv2.waitKey(0)
效果：
框一定颜色的物块：（中间的绿线还不知道咋出来的。。。
img = cv2.imread('66.png')
# 颜色转换函数 转换为hsv cv2.COLOR_BGR2HSV
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
low_hsv = np.array([11, 43, 46])
high_hsv = np.array([100, 255, 255])
mask = cv2.inRange(hsv, lowerb=low_hsv, upperb=high_hsv)
# 中值滤波降噪
median = cv2.medianBlur(mask, 5)
# 进行边缘检测np.array([30, 43, 46])
# mask是只突出指定颜色的图片
cannyPic = cv2.Canny(median, 10, 200)
line = 50
minLineLength = 10
maxLineGap = 150
# 检测直线函数，能输出检测到的直线端点
lines = cv2.HoughLinesP(cannyPic, 1, np.pi / 180, 120, lines=line, minLineLength=minLineLength,
maxLineGap=maxLineGap)
lines1 = lines[:, 0, :]
# line()划线函数
for x1, y1, x2, y2 in lines1:
cv2.line(img, (x1, y1), (x2, y2), (0, 255, 0), 2)
contours, hierarchy = cv2.findContours(cannyPic, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
for c in contours:
rect = cv2.minAreaRect(c)
box_ = cv2.boxPoints(rect)
h = abs(box_[3, 1] - box_[1, 1])
w = abs(box_[3, 0] - box_[1, 0])
box = cv2.boxPoints(rect) # 计算最小面积矩形的坐标
box = np.int0(box) # 将坐标规范化为整数
angle = rect[2]
if angle > 20:
continue
# 绘制矩形
cv2.drawContours(img, [box], 0, (255, 0, 0), 3)
cv2.namedWindow("img_3", 0)
cv2.imshow("img_3", img)
cv2.waitKey(0)
cv2.destroyAllWindows()
然后发现有的颜色还没有框住。。
一个框住一定物体的代码:
img = cv2.pyrDown(cv2.imread("hammer.png" ,cv2.IMREAD_UNCHANGED))
ret, thresh = cv2.threshold(cv2.cvtColor(img.copy(),cv2.COLOR_BGR2GRAY), 127, 255, cv2.THRESH_BINARY)
image,contours= cv2.findContours(thresh,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
for c in contours:
# find bounding box coordinates
x, y, w, h = cv2.boundingRect(c)
cv2.rectangle(img, (x, y), (x+w, y + h), (0, 255, 0), 2)
# find minimum area
rect = cv2.minAreaRect(c)
# calculate coordinates of the minimum area rectangle
box = cv2.boxPoints(rect)
# normalize coordinates to integers
box = np.into(box)
# draw contours
cv2.drawContours(img, [box], 0, (0, 0, 255), 3)
# calculate center and radius of minimum enclosing circle
(x, y),radius = cv2.minEnclosingCircle(c)
# cast to integers
center = (int(x), int(y))
radius = int(radius)
# draw the circle
img = cv2.circle(img, center, radius, (0, 255, 0),2)
cv2.drawContours(img, contours, -1, (255, 0, 0),1)
cv2.imshow("contoursn", img)
原图:
不知道代码是哪里出了bug 还没跑成功：
关键是好多函数还不知道是怎么用的。。。
追踪特定颜色:
import imutils
if __name__ == '__main__':
cap = cv.VideoCapture(0)
while True:
# 读取每一帧
_, frame = cap.read()
# 重设图片尺寸以提高计算速度
frame = imutils.resize(frame, width=600)
# 进行高斯模糊
blurred = cv.GaussianBlur(frame, (11, 11), 0)
# 转换颜色空间到HSV
hsv = cv.cvtColor(blurred, cv.COLOR_BGR2HSV)
# 定义红色无图的HSV阈值
lower_red = np.array([20, 100, 100])
upper_red = np.array([220, 255, 255])
# 对图片进行二值化处理
mask = cv.inRange(hsv, lower_red, upper_red)
# 腐蚀操作
mask = cv.erode(mask, None, iterations=2)
# 膨胀操作，先腐蚀后膨胀以滤除噪声
mask = cv.dilate(mask, None, iterations=2)
cv.imshow('mask', mask)
# 寻找图中轮廓
cnts = cv.findContours(mask.copy(), cv.RETR_EXTERNAL, cv.CHAIN_APPROX_SIMPLE)[-2]
# 如果存在至少一个轮廓则进行如下操作
if len(cnts) > 0:
# 找到面积最大的轮廓
c = max(cnts, key=cv.contourArea)
# 使用最小外接圆圈出面积最大的轮廓
((x, y), radius) = cv.minEnclosingCircle(c)
# 计算轮廓的矩
M = cv.moments(c)
# 计算轮廓的重心
center = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))
# 只处理尺寸足够大的轮廓
if radius > 5:
# 画出最小外接圆
cv.rectangle(frame, (int(x), int(y)), (int(x), int(y)), (0, 255, 255), 2)
# 画出重心
cv.imshow('frame', frame)
k = cv.waitKey(5) & 0xFF
if k == 27:
break
cap.release()
cv.destroyAllWindows()
不知道为什么只有试蓝色物体的时候才有阴影。。。然后圆形框也没出来。。。。。
追踪：
if __name__ == '__main__':
cap = cv2.VideoCapture(0) # 获取摄像头视频
while True:
ret, frame = cap.read() # 读取每一帧图片
hsv_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV) # 将每一帧图片转化HSV空间颜色
lower = np.array([0, 104, 205])
upper = np.array([15, 208, 255])
mask = cv2.inRange(hsv_frame, lower, upper)
img, conts = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) # 找出边界
cv2.drawContours(frame, conts, -1, (0, 255, 0), 3) # 画出边框
dst = cv2.bitwise_and(frame, frame, mask=mask) # 对每一帧进行位与操作，获取追踪图像的颜色
# cv2.imshow("mask",mask)
# cv2.imshow("dst",dst)
cv2.imshow("frame", frame)
if cv2.waitKey(1) & 0xff == 27:
break
cv2.destroyAllWindows()
动态识别物体:
import cv2
import numpy as np
camera = cv2.VideoCapture(0) # 参数0表示第一个摄像头
# 判断视频是否打开
if (camera.isOpened()):
print('Open')
else:
print('摄像头未打开')
# 测试用,查看视频size
size = (int(camera.get(cv2.CAP_PROP_FRAME_WIDTH)),
int(camera.get(cv2.CAP_PROP_FRAME_HEIGHT)))
print('size:' + repr(size))
es = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (9, 4))
kernel = np.ones((5, 5), np.uint8)
background = None
while True:
# 读取视频流
grabbed, frame_lwpCV = camera.read()
# 对帧进行预处理，先转灰度图，再进行高斯滤波。
# 用高斯滤波进行模糊处理，进行处理的原因：每个输入的视频都会因自然震动、光照变化或者摄像头本身等原因而产生噪声。对噪声进行平滑是为了避免在运动和跟踪时将其检测出来。
gray_lwpCV = cv2.cvtColor(frame_lwpCV, cv2.COLOR_BGR2GRAY)
gray_lwpCV = cv2.GaussianBlur(gray_lwpCV, (21, 21), 0)
# 将第一帧设置为整个输入的背景
if background is None:
background = gray_lwpCV
continue
# 对于每个从背景之后读取的帧都会计算其与北京之间的差异，并得到一个差分图（different map）。
# 还需要应用阈值来得到一幅黑白图像，并通过下面代码来膨胀（dilate）图像，从而对孔（hole）和缺陷（imperfection）进行归一化处理
diff = cv2.absdiff(background, gray_lwpCV)
diff = cv2.threshold(diff, 148, 255, cv2.THRESH_BINARY)[1] # 二值化阈值处理
diff = cv2.dilate(diff, es, iterations=2) # 形态学膨胀
# 显示矩形框
image, contours, hierarchy = cv2.findContours(diff.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE) # 该函数计算一幅图像中目标的轮廓
for c in contours:
if cv2.contourArea(c) < 1500: # 对于矩形区域，只显示大于给定阈值的轮廓，所以一些微小的变化不会显示。对于光照不变和噪声低的摄像头可不设定轮廓最小尺寸的阈值
continue
(x, y, w, h) = cv2.boundingRect(c) # 该函数计算矩形的边界框
cv2.rectangle(frame_lwpCV, (x, y), (x + w, y + h), (0, 255, 0), 2)
cv2.imshow('contours', frame_lwpCV)
cv2.imshow('dis', diff)
key = cv2.waitKey(1) & 0xFF
# 按'q'健退出循环
if key == ord('q'):
break
# When everything done, release the capture
camera.release()
cv2.destroyAllWindows()
感觉可能是opencv4发生了改动，这个代码在我的电脑上一直报错：
还没时间看官方文档，以后再看吧