在实时Numpy视频上跟踪帧速率

Question

我正在做一个项目，可以识别设备上的7个段号

这是我的密码

import cv2
import numpy as np
from matplotlib import pyplot as plt
import urllib
from urllib import request 
import imutils


#I used this to connect the webcam app on the tablet 
url='http://192.168.0.121:8080/shot.jpg'
tW=52
tH=98
while True:

    
    
    imgResp = urllib.request.urlopen(url)

    
    imgNp = np.array(bytearray(imgResp.read()),dtype=np.uint8)

    
    frame = cv2.imdecode(imgNp,-1)

   
    height, width = frame.shape[:2]

   
    top_left_x = int (width / 4)
    top_left_y = int ((height / 2) + (height / 6))
    bottom_right_x = int ((width / 4) +(width/5))
    bottom_right_y = int ((height / 2) - (height / 55))

   
    cv2.rectangle(frame, (top_left_x,top_left_y), (bottom_right_x,bottom_right_y), 255, 3)
    cv2.imshow('user_window',frame)

     
    cropped = frame[bottom_right_y:top_left_y , top_left_x:bottom_right_x]


    
    cv2.imshow('cropped',cropped)

   
    gray = cv2.cvtColor(cropped, cv2.COLOR_BGR2GRAY)
  
    blur = cv2.GaussianBlur(gray, (5, 5), 0)
 
    canny = cv2.Canny(blur, 10, 70)
 
    ret, mask = cv2.threshold(canny, 70, 255, cv2.THRESH_BINARY)

    cv2.imshow('mask',mask)



    



   

       
    methods = ['cv2.TM_CCOEFF', 'cv2.TM_CCOEFF_NORMED']
    found=None
    detected_number=None
    for meth in methods: 
        print(meth)
        
     
        for a in range(0,10):
          
            
          
            templatepath = ('C:\\Users\\USER\\Desktop\\test\\verniersegment\\'+str(a)+'vernier.png') # trainImage
           
            template =  cv2.imread(templatepath,1) # trainImage
            print('비교하는 숫자',a)
            
            
           
            template = cv2.cvtColor(template, cv2.COLOR_BGR2GRAY)
            templateBinary = cv2.threshold(template, 84, 255, cv2.THRESH_BINARY)[1]
          
            template = cv2.Canny(templateBinary, 50, 200)
         
            (tH, tW) = template.shape[:2]
           
            cv2.imshow("Template", template)
          
          
           
            for scale in np.linspace (0.2,1.0,num=10)[::-1]:
               
                resized=imutils.resize(mask,width=int(mask.shape[1]*scale) )
              
                r=float(resized.shape[1]/mask.shape[1])
              

               
                cv2.imshow('resized',resized)
               

      
                if resized.shape[0]<tH or resized.shape[1]<tW:
                    print("비교이미지가 template보다 작아짐 ")
                    break
                 
                method=eval(meth)
                #matchtemplate함수로 사이즈가 바뀐 부분 ,template을 method방식으로 비교한다
                threshold = 0.8
                compare = cv2.matchTemplate(resized,template,method)
                
                    
              
                (minVal, maxVal, minLoc, maxLoc) = cv2.minMaxLoc(compare)

              
                clone = np.dstack([resized, resized, resized])
                #cv2.rectangle(clone, (maxLoc[0], maxLoc[1]),(maxLoc[0] + tW, maxLoc[1] + tH), (0, 0, 255), 2)
               

 
                if found is None or maxVal > found[0]:
                    maxVal2=maxVal
                    found = (maxVal2, maxLoc, r,a)
                 
                    
          
                maxLoc=found[1]
            
                r=found[2]
                (startX, startY) = (int(maxLoc[0] * r), int(maxLoc[1] * r))
                (endX, endY) = (int((maxLoc[0] + tW) * r), int((maxLoc[1] + tH) * r))
             
                if maxVal2>7000000:
                    cv2.rectangle(mask, (startX, startY), (endX, endY), (255,0, 0), 2)
              
        if maxVal2>5000000:
            cv2.putText(mask,str(found[3]),(startX+10,startY+10), cv2.FONT_HERSHEY_COMPLEX, 2 ,(255,0,0), 2)

    cv2.imshow("Finalized", mask)
    


    if cv2.waitKey(1) == 13: 
        break

cv2.destroyAllWindows()   

现在，输出的是在dtected数字上绘制矩形的实时视频。 这是我上传到youtube上的输出视频的链接

output video

视频livestream不是平滑的并且正在停止，我想知道每秒有多少帧正在被处理，这样我就可以使输出livestream平滑

我尝试了手动功能来计算帧数

def count_frames_manual(video):
    # initialize the total number of frames read
    total = 0
    # loop over the frames of the video
    while True:
        # grab the current frame
        (grabbed, frame) = video.read()

        # check to see if we have reached the end of the
        # video
        if not grabbed:
            break
        # increment the total number of frames read
        total += 1
        return total
    # return the total number of frames in the

print(count_frames_manual(mask))

但是当我运行这个函数时，我有以下错误

AttributeError                            Traceback (most recent call last)
<ipython-input-9-dd97690639f7> in <module>
----> 1 print(count_frames_manual(mask))

<ipython-input-8-ab227eb24e08> in count_frames_manual(video)
      5     while True:
      6         # grab the current frame
----> 7         (grabbed, frame) = video.read()
      8 
      9         # check to see if we have reached the end of the

AttributeError: 'numpy.ndarray' object has no attribute 'read'

似乎mask是一个NumPy对象，我不知道如何继续计数帧 在这种情况下

请帮忙

如果有办法使新蒸汽更平滑，也请让我知道

谢谢你

Answer 1

测量fps的方法在这个问题中描述：fps - how to divide count by time function to determine fps

为了使视频更平滑，请尝试在canny和gauassian过滤器之前调整图像大小，以降低计算成本，这一点不会丢失太多信息

您可以尝试另一种边缘检测算法，如拉普拉斯算子或sobel滤波器，您也可以使用高通滤波器（中心为正值，外围为负系数），这些滤波器牺牲精度以换取更好的时间。最后，我建议用C++实现更快的处理。p>

Answer 2

哇，我看这不可能顺利进行。你需要完全重构你的代码；并优先使用本地摄像机。此外，matchTemplate可能不是模式识别的好选择，因为它对所有变换和噪声都非常敏感，而且速度非常慢

要测量fps，请将其放置在文件的开头

import time
fps = 0
tau = time.time()

这是一个接近opencv的消息分派回调

now = time.time()
if now > tau:  # avoid div0
    fps = (fps*9 +1/(now-tau))/10
tau = now
print(fps)

if cv2.waitKey(1) == 13: 
    break