视频流中出现了一个矩形,找到“最大目标区域”,并分屏显示出来了。左上为原始的视频,右上为“最大目标区域”,下方的视频也是“最大目标区域”
以下是python 代码:
import cv2
import numpy as np
widthImg = 640
heightImg = 480
cap = cv2.VideoCapture(0)
cap.set(3, widthImg)
cap.set(4, heightImg)
cap.set(10, 130)
#1.合并
def stackImages(scale,imgArray):
rows = len(imgArray)
cols = len(imgArray[0])
rowsAvailable = isinstance(imgArray[0], list)
width = imgArray[0][0].shape[1]
height = imgArray[0][0].shape[0]
if rowsAvailable:
for x in range ( 0, rows):
for y in range(0, cols):
if imgArray[x][y].shape[:2] == imgArray[0][0].shape [:2]:
imgArray[x][y] = cv2.resize(imgArray[x][y], (0, 0), None, scale, scale)
else:
imgArray[x][y] = cv2.resize(imgArray[x][y], (imgArray[0][0].shape[1], imgArray[0][0].shape[0]), None, scale, scale)
if len(imgArray[x][y].shape) == 2: imgArray[x][y]= cv2.cvtColor( imgArray[x][y], cv2.COLOR_GRAY2BGR)
imageBlank = np.zeros((height, width, 3), np.uint8)
hor = [imageBlank]*rows
hor_con = [imageBlank]*rows
for x in range(0, rows):
hor[x] = np.hstack(imgArray[x])
ver = np.vstack(hor)
else:
for x in range(0, rows):
if imgArray[x].shape[:2] == imgArray[0].shape[:2]:
imgArray[x] = cv2.resize(imgArray[x], (0, 0), None, scale, scale)
else:
imgArray[x] = cv2.resize(imgArray[x], (imgArray[0].shape[1], imgArray[0].shape[0]), None,scale, scale)
if len(imgArray[x].shape) == 2: imgArray[x] = cv2.cvtColor(imgArray[x], cv2.COLOR_GRAY2BGR)
hor= np.hstack(imgArray)
ver = hor
return ver
#2.图片或者视频流厚薄灰度显示
def preProcessing(img):
imgGray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
imgBlur = cv2.GaussianBlur(imgGray,(5,5),1)
imgCanny = cv2.Canny(imgBlur,200,200) #边缘检测
# 给边缘加粗
kernel = np.ones((5,5))
imgDial = cv2.dilate(imgCanny,kernel,iterations=2)
imgThres = cv2.erode(imgDial,kernel,iterations=1)
return imgThres
#3.形状边界检测 得到最大边界坐标
def getContours(img):
biggest = np.array([])
maxArea = 0
contours,hierarchy = cv2.findContours(img,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE)
for cnt in contours:
area = cv2.contourArea(cnt)
if area>5000:
#cv2.drawContours(imgContour, cnt, -1, (255, 0, 0), 3)
peri = cv2.arcLength(cnt,True)
approx = cv2.approxPolyDP(cnt,0.02*peri,True) #计算边数
if area >maxArea and len(approx) == 4:
biggest = approx
maxArea = area
cv2.drawContours(imgCounter, biggest, -1, (255, 0, 0), 20)
return biggest
#4.坐标点重排序
# 所有坐标点相加 降序排列
def reorder(myPoints):
#1.相加
myPoints = myPoints.reshape((4, 2))
myPointsNew = np.zeros((4, 1, 2), np.int32)
add = myPoints.sum(1)
print("add", add)
#2.重排序
myPointsNew[0] = myPoints[np.argmin(add)]
myPointsNew[3] = myPoints[np.argmax(add)]
print("newPoints", myPointsNew)
#3.不同点 axis=1
diff = np.diff(myPoints, axis=1)
#4.重排序了[0 0][width 0][0 high][width high]
myPointsNew[1] = myPoints[np.argmin(diff)]
myPointsNew[2] = myPoints[np.argmax(diff)]
print("newPoints", myPointsNew)
return myPointsNew
# 5.按坐标点截取视频流图像
def getWarp(img,biggest):
biggest = reorder(biggest)
print(biggest.shape)
pts1 = np.float32(biggest)
pts2 = np.float32([[0, 0], [widthImg, 0], [0, heightImg], [widthImg, heightImg]])
matrix = cv2.getPerspectiveTransform(pts1, pts2)
imgoutput = cv2.warpPerspective(img, matrix, (widthImg, heightImg))
imgCropped = imgoutput[20:imgoutput.shape[0] - 20, 20:imgoutput.shape[1] - 20]
imgCropped = cv2.resize(imgCropped, (widthImg, heightImg))
return imgoutput
while True:
success, img = cap.read()
cv2.resize(img, (widthImg, heightImg))
#1.复制图片
imgCounter = img.copy()
#2.改图片灰度厚薄
imgThres = preProcessing(img)
#3.得到4个角的坐标
biggest = getContours(imgThres)
#print(biggest)
#4.截取最大区域视图并拼接视图
if biggest.size != 0:
imgWarped = getWarp(img, biggest)
# imageArray = ([img,imgThres],
# [imgContour,imgWarped])
imageArray = ([imgCounter, imgWarped])
cv2.imshow("ImageWarped", imgWarped)
else:
# imageArray = ([img, imgThres],
# [img, img])
imageArray = ([imgCounter, img])
stackedImages = stackImages(0.6, imageArray)
cv2.imshow("WorkFlow", stackedImages)
if cv2.waitKey(1) & 0XFF == ord('q'):
break