I would like to save two vides together at the same time using python. like this YoloV2, Yolo 9000, SSD Mobilenet, Faster RCNN NasNet comparison, I am not sure he saved them at the same time or not, likely he used another program to merage them.
can I do it using python?
this my code, I saved two vides separately
import cv2
import numpy as np
from imutils.video import FPS
# capturing video through webcam
import time
fourcc = cv2.VideoWriter_fourcc('M', 'J', 'P', 'G') #Define the codec and create VideoWriter object
fourcc1 = cv2.VideoWriter_fourcc('M', 'J', 'P', 'G') #Define the codec and create VideoWriter object
out = cv2.VideoWriter('colors.avi', fourcc, 20.0, (640, 480))
out1 = cv2.VideoWriter('colors1.avi', fourcc1, 20.0, (640, 480))
cap = cv2.VideoCapture(0)
#video dimension in python-opencv
width = cap.get(3) # float
height = cap.get(4) # float
print width,height
time.sleep(2.0)
while(1):
_, img = cap.read()
if _ is True:
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
else:
continue
red_lower = np.array([136,87,111],np.uint8)
red_upper = np.array([180,255,255],np.uint8)
red = cv2.inRange(hsv, red_lower, red_upper)
kernal = np.ones((5, 5), "uint8")
red = cv2.dilate(red, kernal)
res_red = cv2.bitwise_and(img, img, mask = red)
(_, contours, hierarchy)=cv2.findContours(red, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
for pic, contour in enumerate(contours):
area = cv2.contourArea(contour)
if(area > 300):
x, y, w, h = cv2.boundingRect(contour)
img = cv2.rectangle(img, (x, y), (x + w, y + h), (0, 0, 255), 2)
cv2.putText(img, "Red Colour", (x, y), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255))
out.write(res_red)
out1.write(img)
cv2.imshow("Color Tracking", img)
cv2.imshow("Color Tracking1", res_red)
if cv2.waitKey(10) & 0xFF == ord('q'):
cap.release()
cv2.destroyAllWindows()
break
output: two vides
Related
I'm trying to load several images from a folder so that they are processed in an exact same manner. The code below detects a blue object in webcam feed and overlays it with the template image img where the webcam frame is im0
hsv = cv2.cvtColor(im0, cv2.COLOR_BGR2HSV)
mask = cv2.inRange(hsv, (0, 120, 120), (180, 255, 255))#<- blue # RED: (0, 120, 120), (10, 255, 255))
thresh = cv2.dilate(mask, None, iterations=2)
contours = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0]
for contour in contours:
x, y, w, h = cv2.boundingRect(contour)
height = 480
width = 640
if y + h < height and x + w < width:
logo = cv2.resize(img, (w, h))
img2gray = cv2.cvtColor(logo, cv2.COLOR_BGR2GRAY)
_, logo_mask = cv2.threshold(img2gray, 1, 255, cv2.THRESH_BINARY)
roi = im0[y:y+h, x:x+w]
roi[np.where(logo_mask)] = 0
roi += logo
cv2.imshow(str(p), im0)#im0 2
cv2.waitKey(1) # 1 millisecond
I am wondering how should I create a timer here so that the exact same processing happens to the img2, img3 and so on?
Im trying to save only the rectangular ROI region from a video file into images. But the entire image is getting saved with the RED rectangular ROI box on it. What am I doing wrong here ?
I tried saving rect_img but thats giving error "!_img.empty() in function 'imwrite'" ,
and not saving any images at all.
The upper_left and bottom_right coordinates are for a 1920 X 1080p video, you wil have to adjust is as per your video resolution.
import cv2
from matplotlib import pyplot as plt
import imutils
import numpy as np
import pytesseract
cam_capture = cv2.VideoCapture('1080_EDIT.webm')
upper_left = (1400, 700)
bottom_right = (700, 1000)
ctr=1 #filename counter
while True:
_, image_frame = cam_capture.read()
ctr+=1
#Rectangle marker
r = cv2.rectangle(image_frame, upper_left, bottom_right, (100, 50, 200), 5)
rect_img = image_frame[upper_left[1] : bottom_right[1], upper_left[0] : bottom_right[0]]
cv2.imwrite("rect"+str(ctr)+".jpg",r)
#print (rect_img)
#img=cv2.imread(rect_img)
gray = cv2.cvtColor(r, cv2.COLOR_BGR2GRAY)
gray = cv2.bilateralFilter(gray, 13, 15, 15)
edged = cv2.Canny(gray, 30, 200)
contours = cv2.findContours(edged.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
contours = imutils.grab_contours(contours)
contours = sorted(contours, key = cv2.contourArea, reverse = True)[:10]
screenCnt = None
for c in contours:
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.018 * peri, True)
if len(approx) == 4:
screenCnt = approx
break
if screenCnt is None:
detected = 0
print ("No contour detected")
else:
detected = 1
if detected == 1:
cv2.drawContours(r, [screenCnt], -1, (0, 0, 255), 3)
cv2.imshow("image", image_frame)
if cv2.waitKey(1) % 256 == 27 :
break
cam_capture.release()
cv2.destroyAllWindows()
Solved it by
roi=r[700:1000,700:1400]
cv2.imwrite("rect"+str(ctr)+".jpg",roi)
i write a code from Open CV Document about Motion Detection .i want to save my input as a video and my output as a video but i have problems. i save video but i can just save the output video and some time the input video is the same out put video.my input video is from my computer's camera and it's like a normal video but the output is that video in addition by squares around motion objects.i need your help.
import cv2 as cv
import numpy as np
cap = cv.VideoCapture(0)
(grabbed, frame) = cap.read()
fshape = frame.shape
fheight = fshape[0]
fwidth = fshape[1]
print (fwidth , fheight)
ret, frame1 = cap.read()
ret, frame2 = cap.read()
while cap.isOpened():
diff = cv.absdiff(frame1, frame2)
gray = cv.cvtColor(diff, cv.COLOR_BGR2GRAY)
blur = cv.GaussianBlur(gray, (5, 5), 0)
_, thresh = cv.threshold(blur, 20, 255, cv.THRESH_BINARY)
dilated = cv.dilate(thresh, None, iterations=3)
contours, _ = cv.findContours(dilated, cv.RETR_TREE,
cv.CHAIN_APPROX_SIMPLE)
for contour in contours:
(x, y, w, h) = cv.boundingRect(contour)
if cv.contourArea(contour) < 100:
continue
cv.rectangle(frame1, (x, y), (x+w, y+h), (0, 0, 255), 3)
Final_Movie = cv.putText(frame1, "Status: {}".format('Movement'), (10,
20), cv.FONT_HERSHEY_DUPLEX,
1, (0, 0, 255), 3)
#cv.drawContours(frame1, contours, -1, (0, 0, 255), 3)
cv.imshow("feed", frame1)
cv.imshow("feed1", blur)
cv.imshow("feed2", gray)
cv.imshow("feed3", diff)
cv.imshow("feed4", thresh)
cv.imshow("feed5", dilated)
#cv.imshow("feed6", contours)
frame1 = frame2
ret, frame2 = cap.read()
if cv.waitKey(40) == 27:
break
cv.destroyAllWindows()
cap.release()
i tried this but it doesn't work.
import cv2 as cv
import numpy as np
cap = cv.VideoCapture(0)
(grabbed, frame) = cap.read()
fshape = frame.shape
fheight = fshape[0]
fwidth = fshape[1]
print (fwidth , fheight)
fourcc = cv.VideoWriter_fourcc(*'XVID')
out = cv.VideoWriter('output.avi', fourcc, 20.0, (fwidth, fheight))
out1 = cv.VideoWriter('input.avi', fourcc, 20.0, (fwidth, fheight))
ret, frame1 = cap.read()
ret, frame2 = cap.read()
while cap.isOpened():
diff = cv.absdiff(frame1, frame2)
gray = cv.cvtColor(diff, cv.COLOR_BGR2GRAY)
blur = cv.GaussianBlur(gray, (5, 5), 0)
_, thresh = cv.threshold(blur, 20, 255, cv.THRESH_BINARY)
dilated = cv.dilate(thresh, None, iterations=3)
contours, _ = cv.findContours(dilated, cv.RETR_TREE,
cv.CHAIN_APPROX_SIMPLE)
for contour in contours:
(x, y, w, h) = cv.boundingRect(contour)
if cv.contourArea(contour) < 100:
continue
cv.rectangle(frame1, (x, y), (x+w, y+h), (0, 0, 255), 3)
Final_Movie = cv.putText(frame1, "Status: {}".format('Movement'), (10,
20), cv.FONT_HERSHEY_DUPLEX,
1, (0, 0, 255), 3)
#cv.drawContours(frame1, contours, -1, (0, 0, 255), 3)
cv.imshow("feed", frame1)
cv.imshow("feed1", blur)
cv.imshow("feed2", gray)
cv.imshow("feed3", diff)
cv.imshow("feed4", thresh)
cv.imshow("feed5", dilated)
#cv.imshow("feed6", contours)
if ret == True:
out.write(Final_Movie)
out.write(frame2)
frame1 = frame2
ret, frame2 = cap.read()
if cv.waitKey(40) == 27:
break
cv.destroyAllWindows()
cap.release()
Here is the python code I have written :-
import cv2
import argparse
ap = argparse.ArgumentParser()
ap.add_argument("-v", "--video",
help = "path to the (optional) video file")
args = vars(ap.parse_args())
if not args.get("video", False):
cap = cv2.VideoCapture(0)
else:
cap = cv2.VideoCapture(args["video"])
fgbg = cv2.bgsegm.createBackgroundSubtractorMOG()
while True:
ret, frame = cap.read()
fgmask = fgbg.apply(frame)
cv2.imshow('frame',fgmask)
k = cv2.waitKey(30) & 0xff
if k == 27:
break
cap.release()
cv2.destroyAllWindows()
How to put bounding box around the detected human outline and improve efficiency of the python code to perform background subtraction on the live video feed taken from webcam. Can someone help?
Drawing Contour Using Background Subtraction
import cv2
import argparse
ap = argparse.ArgumentParser()
ap.add_argument("-v", "--video",
help = "path to the (optional) video file")
args = vars(ap.parse_args())
if not args.get("video", False):
cap = cv2.VideoCapture(0)
else:
cap = cv2.VideoCapture(args["video"])
fgbg = cv2.bgsegm.createBackgroundSubtractorMOG()
while True:
ret, frame = cap.read()
fgmask = fgbg.apply(frame)
gray=cv2.cvtColor(fgmask,cv2.COLOR_BGR2GRAY)
ret,th1 = cv2.threshold(gray,25,255,cv2.THRESH_BINARY)
_,contours,hierarchy = cv2.findContours(th1,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
for cnt in contours:
area = cv2.contourArea(cnt)
if area > 1000 and area < 40000:
x,y,w,h = cv2.boundingRect(cnt)
cv2.rectangle(fgmask,(x,y),(x+w,y+h),(255,0,0),2)
cv2.imshow('frame',fgmask)
k = cv2.waitKey(30) & 0xff
if k == 27:
break
cap.release()
cv2.destroyAllWindows()
Drawing Contour using HSV Masking and Convex Hull
Set value for hsv mask.
import cv2
import argparse
ap = argparse.ArgumentParser()
ap.add_argument("-v", "--video",
help = "path to the (optional) video file")
args = vars(ap.parse_args())
if not args.get("video", False):
cap = cv2.VideoCapture(0)
else:
cap = cv2.VideoCapture(args["video"])
fgbg = cv2.bgsegm.createBackgroundSubtractorMOG()
while True:
ret, frame = cap.read()
frame = cv2.imread(frame)
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
lower = np.array([50,103,40])
upper = np.array([255,255, 255])
mask = cv2.inRange(hsv, lower, upper)
fg = cv2.bitwise_and(frame, frame, mask=255-mask)
fg = cv2.cvtColor(fg.copy(),cv2.COLOR_HSV2BGR)
fg = cv2.cvtColor(fg,cv2.COLOR_BGR2GRAY)
fg = cv2.threshold(fg, 120,255,cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1]
#plt.imshow(fg)
#plt.show()
fgclosing = cv2.morphologyEx(fg.copy(), cv2.MORPH_CLOSE, kernel)
se = np.ones((3,3),np.uint8)
#fgdilated = cv2.morphologyEx(fgclosing, cv2.MORPH_CLOSE,cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (4,4)))
fgdilated = cv2.dilate(fgclosing, kernel = se , iterations = 8)
img = frame.copy()
ret, threshed_img = cv2.threshold(fgdilated,
127, 255, cv2.THRESH_BINARY)
image, contours, hier = cv2.findContours(threshed_img,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE)
for cnt in contours:
#print(cv2.contourArea(cnt))
if cv2.contourArea(cnt) > 44000:
# get convex hull
hull = cv2.convexHull(cnt)
#cv2.drawContours(img, [hull], -1, (0, 0, 255), 1)
#print(hull)
(x,y,w,h) = cv2.boundingRect(cnt)
#cv2.rectangle(img, (x,y), (x+w,y+h), (255, 0, 0), 2)
contours = hull
#c1 = max(contours, key=cv2.contourArea)
hull = cv2.convexHull(cnt)
c = hull
#print(c)
cv2.drawContours(img, [hull], -1, (0, 0, 255), 1)
# determine the most extreme points along the contour
extLeft = tuple(c[c[:, :, 0].argmin()][0])
extRight = tuple(c[c[:, :, 0].argmax()][0])
extTop = tuple(c[c[:, :, 1].argmin()][0])
extBot = tuple(c[c[:, :, 1].argmax()][0])
cv2.drawContours(img, [c], -1, (0, 255, 255), 2)
cv2.circle(img, extLeft, 8, (0, 0, 255), -1)
cv2.circle(img, extRight, 8, (0, 255, 0), -1)
cv2.circle(img, extTop, 8, (255, 0, 0), -1)
cv2.circle(img, extBot, 8, (255, 255, 0), -1)
lx = extLeft[1]
ly = extLeft[0]
rx = extRight[1]
ry = extRight[0]
tx = extTop[1]
ty = extTop[0]
bx = extBot[1]
by = extBot[0]
x,y = lx,by
w,h = abs(rx-lx),abs(ty-by)
#cv2.rectangle(img, (x,y), (x+w,y+h), (255, 0, 0), 2)
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(img,str(extLeft[0])+','+str(extLeft[1]),(extLeft), font, 2,(0, 0, 255),2,cv2.LINE_AA)
cv2.putText(img,str(extRight[0])+','+str(extRight[1]),(extRight), font, 2,(0, 255, 0),2,cv2.LINE_AA)
cv2.putText(img,str(extTop[0])+','+str(extTop[1]),(extTop), font, 2,(255, 0, 0),2,cv2.LINE_AA)
cv2.putText(img,str(extBot[0])+','+str(extBot[1]),(extBot), font, 2,(255, 255, 0),2,cv2.LINE_AA)
im = frame[tx:bx,ly:ry,:]
cx = im.shape[1]//2
cy = im.shape[0]//2
cv2.circle(im, (cx,cy), 15, (0, 255, 0))
plt.imshow(img)
plt.show()
You can use findContours.
import cv2
import argparse
ap = argparse.ArgumentParser()
ap.add_argument("-v", "--video",
help = "path to the (optional) video file")
args = vars(ap.parse_args())
if not args.get("video", False):
cap = cv2.VideoCapture(0)
else:
cap = cv2.VideoCapture(args["video"])
fgbg = cv2.bgsegm.createBackgroundSubtractorMOG()
while True:
ret, frame = cap.read()
fgmask = fgbg.apply(frame)
mask = 255 - fgmask
_, contours, _ = cv2.findContours(
mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
fgmask = cv2.cvtColor(fgmask, cv2.COLOR_GRAY2BGR)
for contour in contours:
area = cv2.contourArea(contour)
#only show contours that match area criterea
if area > 500 and area < 20000:
rect = cv2.boundingRect(contour)
x, y, w, h = rect
cv2.rectangle(fgmask, (x, y), (x+w, y+h), (0, 255, 0), 3)
cv2.imshow('frame',fgmask)
k = cv2.waitKey(30) & 0xff
if k == 27:
break
cap.release()
cv2.destroyAllWindows()
I have tested with the video https://github.com/opencv/opencv/blob/master/samples/data/vtest.avi
I'm trying to create a aplication with opencv that overlaps a glass on me face. However, when the video appears the glasses have a black on the alpha layer. Here is my code:
video_capture = cv2.VideoCapture(0)
anterior = 0
glasses = cv2.imread('Glasses_1.png')
def put_glasses(glasses,fc,x,y,w,h):
face_width = w
face_height = h
glasses_width = int(face_width)
glasses_height = int(face_height*0.32857)
glasses = cv2.resize(glasses,(glasses_width,glasses_height))
for i in range(glasses_height):
for j in range(glasses_width):
for k in range(3):
if glasses[i][j][k]<235:
fc[y+i-int(-0.25*face_height)-1][x+j][k] = glasses[i][j][k]
return fc
while True:
if not video_capture.isOpened():
print('Unable to load camera.')
sleep(5)
pass
ret, frame = video_capture.read()
if ret is True:
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
else:
continue
faces = faceCascade.detectMultiScale(
gray,
scaleFactor=1.1,
minNeighbors=5,
minSize=(40,40)
)
for (x, y, w, h) in faces:
cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 255, 0), 2)
cv2.putText(frame,"Person Detected",(x,y),cv2.FONT_HERSHEY_SIMPLEX,1,(0,0,255),2)
frame = put_glasses(glasses, frame, x, y, w, h)
I will be very grateful if anyone could help.
You read the png in bgr format, not the bgra or unchanged format. Then I don't think your glass image in the program is shape of (h,w,4). You should read with flag cv2.IMREAD_UNCHANGED.
glasses = cv2.imread("xxx.png", cv2.IMREAD_UNCHANGED)
Maybe this link will help. How do I clear a white background in OpenCV with c++?
The bgra worm:
Blending: