調(diào)取攝像頭的實(shí)現(xiàn)

import numpy as npimport cv2cap = cv2.VideoCapture(0)#參數(shù)為0時(shí)調(diào)用本地?cái)z像頭；url連接調(diào)取網(wǎng)絡(luò)攝像頭；文件地址獲取本地視頻while(True):ret,frame=cap.read()#灰度化gray=cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)cv2.imshow(’frame’,gray)#普通圖片cv2.imshow(’frame’,frame)if cv2.waitKey(1)&0xFF==ord(’q’):breakcap.release()cv2.destroyAllWindows()

opencv代碼

# -*- coding: utf-8 -*-'''Spyder EditorThis is a temporary script file.'''#設(shè)置工作路徑import osos.chdir(’E:0yflSH-spyder-workspace’)os.path.abspath(’.’)import numpy as npimport cv2#1.1讀取圖片imread；展示圖片imshow；導(dǎo)出圖片imwrite#只是灰度圖片img=cv2.imread(’Myhero.jpg’,cv2.IMREAD_GRAYSCALE)#彩色圖片img=cv2.imread(’Myhero.jpg’,cv2.IMREAD_COLOR)#彩色以及帶有透明度img=cv2.imread(’Myhero.jpg’,cv2.IMREAD_UNCHANGED)print(img)#設(shè)置窗口可自動(dòng)調(diào)節(jié)大小cv2.namedWindow(’image’,cv2.WINDOW_NORMAL)cv2.imshow(’image’,img)k=cv2.waitKey(0)#如果輸入escif k==27: #exit cv2.destroyAllWindows#如果輸入selif k==ord(’s’): #save picture and exit cv2.imwrite(’Myhero_out.png’,img) cv2.destroyAllWindows()#1.2視頻讀取#打開(kāi)內(nèi)置攝像頭cap=cv2.VideoCapture(0)#打開(kāi)視頻cap=cv2.VideoCapture(’why.mp4’)#或者視頻每秒多少幀的數(shù)據(jù)fps=cap.get(5)i=0while(True): #讀取一幀 ret,frame=cap.read() #轉(zhuǎn)化為灰圖 gray=cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY) #設(shè)置導(dǎo)出文件名編號(hào) i = i + 1 #每1s導(dǎo)出一張 if i/fps==int(i/fps): #導(dǎo)出文件名為why+編號(hào)+.png #若想要導(dǎo)出灰圖，則將下面frame改為gray即可 cv2.imwrite('why'+str(int(i/fps))+'.png',frame) #讀完之后結(jié)束退出 if cv2.waitKey(1)==ord(’q’): breakcap.release()cv2.destoryAllWindows()#1.3圖像像素修改rangexmin=100rangexmax=120rangeymin=90rangeymax=100img=cv2.imread(’Myhero.jpg’,0)img[rangexmin:rangexmax,rangeymin:rangeymax]=[[255]*(rangeymax-rangeymin)]*(rangexmax-rangexmin)cv2.imwrite(’Myhero_out2.png’,img)#拆分以及合并圖像通道1b,g,r=cv2.split(img)img=cv2.merge(b,g,r)#png轉(zhuǎn)eps，不過(guò)非常模糊from matplotlib import pyplot as pltimg=cv2.imread(’wechat1.png’,cv2.IMREAD_COLOR)plt.imsave(’wechat_out.eps’,img)#圖像按比例混合img1=cv2.imread(’Myhero.jpg’,cv2.IMREAD_COLOR)img2=cv2.imread(’Myhero_out.png’,cv2.IMREAD_COLOR)dst=cv2.addWeighted(img1,0.5,img2,0.5,0)cv2.imwrite('Myhero_combi.jpg',dst)#1.4按位運(yùn)算#加載圖像img1=cv2.imread('Myhero.jpg')img2=cv2.imread('why1.png')#后面那張圖更大rows,cols,channels=img1.shapeROI=img2[0:rows,0:cols]#做一個(gè)ROI為圖像的大小img2gray=cv2.cvtColor(img1,cv2.COLOR_BGR2GRAY)#小于175的改為0，大于175的賦值為255ret,mask=cv2.threshold(img2gray,175,255,cv2.THRESH_BINARY)cv2.imwrite('Myhero_mask.jpg',mask)#255-mask=mask_invmask_inv=cv2.bitwise_not(mask)cv2.imwrite('Myhero_mask_inv.jpg',mask_inv)#在mask白色區(qū)域顯示成ROI，背景圖片img2_bg=cv2.bitwise_and(ROI,ROI,mask=mask)cv2.imwrite('Myhero_pic2_backgroud.jpg',img2_bg)#除了mask以外的區(qū)域都顯示成img1，前景圖片img1_fg=cv2.bitwise_and(img1,img1,mask=mask_inv)cv2.imwrite('Myhero_pic2_frontgroud.jpg',img1_fg)#前景圖片加上背景圖片dst = cv2.add(img2_bg,img1_fg)img2[0:rows, 0:cols ] = dstcv2.imwrite('Myhero_pic2_addgroud.jpg',dst)#finished#構(gòu)建淹膜方法2#截取幀ret,frame=cap.read()#轉(zhuǎn)換到HSVhsv=cv2.cvtColor(frame,cv2.COLOR_BGR2HSV)#設(shè)定藍(lán)色的閾值lower_blue=np.array([110,50,50])upper_blue=np.array([130,255,255])#根據(jù)閾值構(gòu)建掩模mask=cv2.inRange(hsv,lower_blue,upper_blue)#對(duì)原圖像和掩模進(jìn)行位運(yùn)算res=cv2.bitwise_and(frame,frame,mask=mask)#圖片放縮，用的插值方法，所以不會(huì)損害清晰度res=cv2.resize(img1,None,fx=2,fy=2,interpolation=cv2.INTER_CUBIC)cv2.imwrite('Myhero_bigger.jpg',res)#第二種插值方法height,width=img.shape[:2]res=cv2.resize(img,(2*width,2*height),interpolation=cv2.INTER_CUBIC)#edge現(xiàn)實(shí)圖片中不好用，人工畫(huà)的圖片還可以img = cv2.imread(’why3.png’,0)edges = cv2.Canny(img,50,100)cv2.imwrite('why3_edge.png',edges)#識(shí)別輪廓，并保存輪廓點(diǎn)contoursimg=cv2.imread(’why129.png’)imgray=cv2.imread(’why129.png’,cv2.IMREAD_GRAYSCALE)ret,thresh = cv2.threshold(imgray,127,255,0)cv2.imwrite('2.jpg',thresh)image, contours, hierarchy = cv2.findContours(thresh,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)img = cv2.drawContours(img, contours, -1, (0,255,0), 3)cv2.imwrite('3.jpg',img)#輪廓img = cv2.imread(’why3.png’,0)ret,thresh = cv2.threshold(img,127,255,0)contours,hierarchy = cv2.findContours(thresh, 1, 2)cnt = contours[0] #近似輪廓epsilon = 0.1*cv2.arcLength(cnt,True)approx = cv2.approxPolyDP(cnt,epsilon,True)img = cv2.drawContours(img, approx, -1, (0,255,0), 3)cv2.imwrite('4.jpg',img)from matplotlib import pyplot as plt#圖像識(shí)別/匹配img_rgb = cv2.imread(’why174.png’)img_gray = cv2.cvtColor(img_rgb, cv2.COLOR_BGR2GRAY)img2=img_gray.copy()template = cv2.imread(’0temp.png’,0)w, h = template.shape[::-1]#共有六種識(shí)別方法methods = [’cv2.TM_CCOEFF’, ’cv2.TM_CCOEFF_NORMED’, ’cv2.TM_CCORR’, ’cv2.TM_CCORR_NORMED’, ’cv2.TM_SQDIFF’, ’cv2.TM_SQDIFF_NORMED’]for meth in methods: img = img2.copy() #eval返回某個(gè)式子的計(jì)算結(jié)果 method = eval(meth) #下面使用匹配方法 res = cv2.matchTemplate(img,template,method) min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(res) if method in [cv2.TM_SQDIFF, cv2.TM_SQDIFF_NORMED]: top_left = min_loc else: top_left = max_loc bottom_right = (top_left[0] + w, top_left[1] + h) #畫(huà)矩形把他框出來(lái) cv2.rectangle(img,top_left, bottom_right, 255, 2) plt.subplot(121),plt.imshow(res,cmap = ’gray’) plt.title(’Matching Result’), plt.xticks([]), plt.yticks([]) plt.subplot(122),plt.imshow(img,cmap = ’gray’) plt.title(’Detected Point’), plt.xticks([]), plt.yticks([]) plt.suptitle(meth) plt.show() #這個(gè)匹配結(jié)果太差#選取3，5，6的匹配方式會(huì)稍微好點(diǎn)：cv2.TM_CCORR；cv2.TM_SQDIFF，cv2.TM_SQDIFF_NORMED#視頻人臉識(shí)別#https://blog.csdn.net/wsywb111/article/details/79152425import cv2from PIL import Imagecap=cv2.VideoCapture('why.mp4')#告訴Opencv使用人臉識(shí)別分類(lèi)器classfier=cv2.CascadeClassifier('E:0yflopencv-masterdatahaarcascadeshaarcascade_frontalface_alt2.xml')count=0while cap.isOpened(): ret,frame=cap.read() if not ret: break grey=cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY) faceRect=classfier.detectMultiScale(grey,scaleFactor=1.2, minNeighbors=3, minSize=(32, 32)) if len(faceRect)>0: count=count+1print(count)#137這種程度可以識(shí)別，111沒(méi)有成功識(shí)別，大概是側(cè)臉的緣故#截出人臉image_name='why111.png'frame=cv2.imread(image_name,0)if not (frame is None): #導(dǎo)入測(cè)試集 classfier=cv2.CascadeClassifier('E:0yflopencv-masterdatahaarcascadeshaarcascade_frontalface_alt2.xml') #使用測(cè)試集導(dǎo)出人臉的位置，存在faceRect中，可以檢測(cè)多張人臉 faceRect=classfier.detectMultiScale(frame,scaleFactor=3.0, minNeighbors=3, minSize=(32, 32)) count=0 for (x1,y1,w,h) in faceRect: count=count+1 #截取上述圖片的人臉部分并保存每一張識(shí)別出的人臉 Image.open(image_name).crop((x1,y1,x1+w,y1+h)).save(image_name.split('.')[0]+'_face_'+str(count)+'.png') if count==0: print ('No face detected!')else: print ('Picture '+ image_name +' is not exist in '+os.path.abspath('.'))#人臉上畫(huà)出矩形from PIL import Image,ImageDrawimage_name='why111.png'frame=cv2.imread(image_name,0)if not (frame is None): classfier=cv2.CascadeClassifier('E:0yflopencv-masterdatahaarcascadeshaarcascade_frontalface_alt2.xml') faceRect=classfier.detectMultiScale(frame,scaleFactor=3.0, minNeighbors=3, minSize=(32, 32)) #畫(huà)框框 img = Image.open(image_name) draw_instance = ImageDraw.Draw(img) count=0 for (x1,y1,w,h) in faceRect: draw_instance.rectangle((x1,y1,x1+w,y1+h), outline=(255, 0,0)) img.save(’drawfaces_’+image_name) count=count+1 if count==0: print ('No face detected!')else: print ('Picture '+ image_name +' is not exist in '+os.path.abspath('.'))#detectFaces()返回圖像中所有人臉的矩形坐標(biāo)（矩形左上、右下頂點(diǎn)）#使用haar特征的級(jí)聯(lián)分類(lèi)器haarcascade_frontalface_default.xml，在haarcascades目錄下還有其他的訓(xùn)練好的xml文件可供選擇。#注：haarcascades目錄下訓(xùn)練好的分類(lèi)器必須以灰度圖作為輸入。from PIL import Image,ImageDrawimage_name='why63.png'frame=cv2.imread(image_name,0)if not (frame is None): classfier=cv2.CascadeClassifier('E:0yflopencv-masterdatahaarcascadeshaarcascade_fullbody.xml') faceRect=classfier.detectMultiScale(frame,scaleFactor=3.0, minNeighbors=3, minSize=(32, 32)) #畫(huà)框框 img = Image.open(image_name) draw_instance = ImageDraw.Draw(img) count=0 for (x1,y1,w,h) in faceRect: draw_instance.rectangle((x1,y1,x1+w,y1+h), outline=(255, 0,0)) img.save(’drawfaces_’+image_name) count=count+1 if count==0: print ('No face detected!')else: print ('Picture '+ image_name +' is not exist in '+os.path.abspath('.'))

以上就是python 實(shí)時(shí)調(diào)取攝像頭的示例代碼的詳細(xì)內(nèi)容，更多關(guān)于python 調(diào)取攝像頭的資料請(qǐng)關(guān)注好吧啦網(wǎng)其它相關(guān)文章！