Python OpenCV高速公路道路汽车车辆摄像头视频侦测检测识别统计数量

Python OpenCV高速公路道路汽车车辆侦测检测识别统计数量

如需安装运行环境或远程调试,可加QQ905733049由专业技术人员远程协助!

运行结果如下:

运行主要代码如下:

import cv2
import numpy as np
import time

cap=cv2.VideoCapture("video.mp4")
fgbg=cv2.createBack(detectShadows=False,history=200,varThreshold = 90)
kernalOp = np.ones((3,3),np.uint8)
kernalOp2 = np.ones((5,5),np.uint8)
kernalCl = np.ones((11,11),np.uint8)
font = cv2.FONT_HERSHEY_SIMPLEX
cars = []
max_p_age = 5
pid = 1
cnt_up=0
cnt_down=0

print("Car counting and classification")

line_up=400
line_down=250

up_limit=230
down_limit=int(4.5*(500/5))

while(cap.isOpened()):
    ret,frame=cap.read()
    frame=cv2.resize(frame,(900,500))
    for i in cars:
        i.age_one()
    fgmask=fgbg.apply(frame)
        mask,countours0,hierarchy=cv2.findContours(mask,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE)
        for cnt in countours0:
            area=cv2.contourArea(cnt)
            print(area)
            if area>300:

                m=cv2.moments(cnt)
                cx=int(m['m10']/m['m00'])
                cy=int(m['m01']/m['m00'])
                x,y,w,h=cv2.boundingRect(cnt)

                new=True
                if cy in range(up_limit,down_limit):
                    for i in cars:
                        if abs(x - i.getX()) <= w and abs(y - i.getY()) <= h:
                            new = False
                            i.updateCoords(cx, cy)

                            if i.going_UP(line_down,line_up)==True:
                                cnt_up+=1

                            elif i.going_DOWN(line_down,line_up)==True:
                                cnt_down+=1

                            break

                    if new==True:
                        p=vehicles.Car(pid,cx,cy,max_p_age)
                        cars.append(p)
                        pid+1
                cv2.circle(frame, (cx, cy), 2, (0, 0, 255), -1)

        for i in cars:
            cv2.putText(frame, str(i.getId()), (i.getX(), i.getY()), font, 0.3, (255,255,0), 1, cv2.LINE_AA)
            if line_down+20<= i.getY() <= line_up-20:
               a = (h + (.74*w)- 100)

               if a >= 0:
                     cv2.putText(frame, "Truck", (i.getX(), i.getY()), font, 1, (0,0,255), 2, cv2.LINE_AA)
               else:
                     cv2.putText(frame, "car", (i.getX(), i.getY()), font, 1, (0,0,255), 2, cv2.LINE_AA)


        str_up='UP: '+str(cnt_up)
        str_down='DOWN: '+str(cnt_down)
        frame=cv2.line(frame,(0,line_up),(900,line_up),(0,0,255),3,8)
        frame=cv2.line(frame,(0,up_limit),(900,up_limit),(0,0,0),1,8)

        frame=cv2.line(frame,(0,down_limit),(900,down_limit),(255,255,0),1,8)
        frame = cv2.line(frame, (0, line_down), (900, line_down), (255, 0,0), 3, 8)


        cv2.imshow('Frame',frame)

        if cv2.waitKey(1)&0xff==ord('q'):
            break

    else:
        break

cap.release()
cv2.destroyAllWindows()

运行结果如下:

C++学习参考实例

C++实现图形界面五子棋游戏源码:

https://blog.csdn.net/alicema1111/article/details/90035420

C++实现图形界面五子棋游戏源码2:

https://blog.csdn.net/alicema1111/article/details/106479579

C++ OpenCV相片视频人脸识别统计人数:

https://blog.csdn.net/alicema1111/article/details/105833928

VS2017+PCL开发环境配置:

https://blog.csdn.net/alicema1111/article/details/106877145

VS2017+Qt+PCL点云开发环境配置:

https://blog.csdn.net/alicema1111/article/details/105433636

C++ OpenCV汽车检测障碍物与测距:

https://blog.csdn.net/alicema1111/article/details/105833449

Windows VS2017安装配置PCL点云库:

https://blog.csdn.net/alicema1111/article/details/105111110

 

你可能感兴趣的:(机器学习,tensorflow,pytorch,神经网络,自动驾驶)