I am trying to use opencv to create a rectangle around a cone. Where I am currently at is I have outlined the code which has resulted in a triangle shape. How can I use opencv to create a rectangle around the triangle.
My code so far:
import cv2
import numpy as np
img = cv2.imread('image.jpg')
ret, mask = cv2.threshold(img[:, :,2], 235, 255, cv2.THRESH_BINARY)
mask3 = np.zeros_like(img)
mask3[:, :, 0] = mask
mask3[:, :, 1] = mask
mask3[:, :, 2] = mask
orange = cv2.bitwise_and(img, mask3)
cv2.imwrite("output.jpg", orange)
im = cv2.imread('output.jpg')
imgray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
ret, thresh = cv2.threshold(imgray, 127, 255, 0)
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cv2.drawContours(im, contours, -1, (0,255,0), 3)
cv2.imshow('img',im)
cv2.waitKey(0)
cv2.destroyAllWindows
Jpeg File:
One approach is using multi-scale template matching
You crop the object you want to find:
Apply Canny edge-detection to find the edges
edged = cv2.Canny(resized, 50, 200)
Find the matched template using matchTemplate
result = cv2.matchTemplate(edged, template, cv2.TM_CCOEFF)
Result:
Code:
import numpy as np
import imutils
import glob
import cv2
template = cv2.imread("template.jpg")
template = cv2.cvtColor(template, cv2.COLOR_BGR2GRAY)
template = cv2.Canny(template, 50, 200)
(h, w) = template.shape[:2]
for imagePath in glob.glob("img2" + "/pXobJ.jpg"):
image = cv2.imread(imagePath)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
found = None
for scale in np.linspace(0.2, 1.0, 20)[::-1]:
resized = imutils.resize(gray, width=int(gray.shape[1] * scale))
r = gray.shape[1] / float(resized.shape[1])
if resized.shape[0] < h or resized.shape[1] < w:
break
edged = cv2.Canny(resized, 50, 200)
result = cv2.matchTemplate(edged, template, cv2.TM_CCOEFF)
(_, maxVal, _, maxLoc) = cv2.minMaxLoc(result)
if found is None or maxVal > found[0]:
found = (maxVal, maxLoc, r)
(_, maxLoc, r) = found
(startX, startY) = (int(maxLoc[0] * r), int(maxLoc[1] * r))
(endX, endY) = (int((maxLoc[0] + w) * r), int((maxLoc[1] + h) * r))
cv2.rectangle(image, (startX, startY), (endX, endY), (0, 0, 255), 2)
cv2.imwrite("img2/out.jpg", image)
print("Table coordinates: ({}, {}, {}, {})".format(startX, startY, endX, endY))
You can also use deep learning object detection with trained networks.
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?
How do I return the contours of the the inner square. Here is my code: I need the contours of the inner square so that I can use the corner points to image warp that area.I have used black tape to help detects the edges. enter image description here
def getBase(img, minarea=100, filter=0, draw=False):
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
mask = cv2.inRange(gray, 0, 50)
result = cv2.bitwise_not(gray, gray, mask=mask)
cv2.imshow("result", result)
_, contours, hierarchy = cv2.findContours(
mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE
)
finalContours = []
for i in contours:
area = cv2.contourArea(i)
if area > minarea:
peri = cv2.arcLength(i, True)
approx = cv2.approxPolyDP(i, 0.02 * peri, True)
bbox = cv2.boundingRect(approx)
if filter > 0:
if len(approx) == filter:
finalContours.append((len(approx), area, approx, bbox, i))
else:
finalContours.append((len(approx), area, approx, bbox, i))
finalContours = sorted(finalContours, key=lambda x: x[1], reverse=True)
if draw:
for con in finalContours:
cv2.drawContours(img, con[4], -1, (0, 0, 255), 3)
return img, finalContours
Here is the solution to detect inner rectangle and extract its left corner point, height and width.
import cv2
import numpy as np
def is_rect_contour(contour):
peri = cv2.arcLength(contour, True)
approx = cv2.approxPolyDP(contour, 0.01 * peri, True)
if len(approx) == 4:
return True
else:
return False
image = cv2.imread("./rect.jpg")
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blurred = cv2.GaussianBlur(gray, (7, 7), 0)
thresh = cv2.threshold(blurred, 40, 255, cv2.THRESH_BINARY_INV)[1]
cnts = cv2.findContours(thresh.copy(), cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0]
refined_contours = []
for cnt in cnts:
if is_rect_contour(cnt):
refined_contours.append(cnt)
inner_rect_cnt = min(refined_contours, key=cv2.contourArea)
(x, y, w, h) = cv2.boundingRect(inner_rect_cnt)
print("x: {}, y:{}, widhth:{}, height:{}".format(x, y, w, h))
cv2.drawContours(image, [inner_rect_cnt], -1, (0, 255, 0), 2)
cv2.imshow('Contours', image)
cv2.waitKey(0)
cv2.destroyAllWindows()
Output:
x: 425, y:126, widhth:1104, height:720
I am trying to do background subtraction using MOG2, It was working fine, but when there is deep shadow of a moving object then the shadow is considered as foreground object and I don't want that shadow as foreground object (I'm running MOG2 for 13 images). How can I remove these shadow so that it does not come in foreground?
Here is a sample image...
original img
image after applying MOG2
here is my sample code...
import os
import numpy as np
import cv2
import glob
import imutils
i=0
bg_flag = 0
image_list = []
bgs_list = []
#bgsfinal function
def detection(image_list):
global i
global bg_flag
bgs3_img = None
backsub = cv2.createBackgroundSubtractorMOG2(128, cv2.THRESH_BINARY, 1)
print("start2")
for k in range(len(image_list)):
frame = image_list[k]
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
cv2.imwrite('./gray/'+str(k)+'.jpg', frame)
#blur = cv2.medianBlur(frame, 21)
blur = frame
bgs_list.append(blur)
for bg in range(len(bgs_list)):
rects = []
#start_time = time.time()
frame_blur = bgs_list[bg]
img = image_list[bg].copy()
s_frame = image_list[bg]
new_frame = s_frame.copy()
fgmask = backsub.apply(frame_blur)
cv2.imwrite("./bgs/"+str(i)+".jpg", fgmask)
fgmask[fgmask==127] = 0
cv2.imwrite("./dilate/"+str(i)+".jpg", fgmask)
thresh = cv2.threshold(fgmask, 128, 255, cv2.THRESH_BINARY)[1]
thresh = cv2.erode(thresh, None, iterations = 1)
thresh = cv2.dilate(thresh, None, iterations=1)
cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
for c in cnts:
#M = cv2.moments(c)
A = cv2.contourArea(c)
(x, y, w, h) = cv2.boundingRect(c)
cv2.rectangle(new_frame, (x, y), (x + w, y + h), (0,0, 255), 1)
cv2.putText(new_frame, str(A), (x - 10, y - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 1)
cv2.imwrite("./area/"+str(i)+".jpg", new_frame)
cv2.rectangle(thresh, (x, y), (x + w, y + h), (255,255, 255), 1)
cv2.putText(thresh, str(A), (x - 10, y - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 1)
cv2.imwrite("./area_bgs/"+str(i)+".jpg", thresh)
i+=1
print("Done!")
#this folder contains 13 continuous images
images = glob.glob('./inci4/*.jpg')
for j in range(len(images)):
img = cv2.imread(images[j])
img = cv2.resize(img, (360, 640))
image_list.append(img)
detection(image_list)
I'm new to Python but want to learn it a bit so I decided to create a program
with template matching from desktop input.
Can any one help with this ? How to write template matching with stream from desktop ?
import time
import cv2
import mss
import numpy
template = cv2.imread('template.jpg', 0)
w, h = template.shape[::-1]
with mss.mss() as sct:
# Part of the screen to capture
monitor = {"top": 40, "left": 0, "width": 800, "height": 640}
while "Screen capturing":
last_time = time.time()
# Get raw pixels from the screen, save it to a Numpy array
img = numpy.array(sct.grab(monitor))
# Display the picture
# cv2.imshow("OpenCV/Numpy normal", img)
# Display the picture in grayscale
cv2.imshow('OpenCV/Numpy grayscale', cv2.cvtColor(img, cv2.COLOR_BGRA2GRAY))
# Print fps
print("fps: {}".format(1 / (time.time() - last_time)))
# Search template in stream
# Press "q" to quit
if cv2.waitKey(25) & 0xFF == ord("q"):
cv2.destroyAllWindows()
break
The first thing I noticed that you did not apply any edge-detection to your template image. The edge-detection is not necessary but useful for finding the features of the template image.
Assume I have the following image:
To detect the above template image precisely I should be applying an edge detection algorithm.
template = cv2.imread("three.png")
template = cv2.cvtColor(template, cv2.COLOR_BGR2GRAY)
template = cv2.Canny(template, 50, 200)
I should also apply edge detection to the stream from desktop.
img = sct.grab(mon)
gray = cv2.cvtColor(np.array(img), cv2.COLOR_BGR2GRAY)
edged = cv2.Canny(gray, 50, 200)
Check if the template matches with the captured image
result = cv2.matchTemplate(edged, template, cv2.TM_CCOEFF)
(_, maxVal, _, maxLoc) = cv2.minMaxLoc(result)
If template image matched in the stream from desktop then get the coordinates.
(_, maxLoc, r) = found
(startX, startY) = (int(maxLoc[0] * r), int(maxLoc[1] * r))
(endX, endY) = (int((maxLoc[0] + w) * r), int((maxLoc[1] + h) * r))
Finally draw the rectangle for displaying the location:
cv2.rectangle(img, (startX, startY), (endX, endY), (180, 105, 255), 2)
Result:
From above we see that the our template 3 value is matched on the stream from desktop.
Code:
import time
import cv2
import numpy as np
import imutils
from mss import mss
template = cv2.imread("three.png")
template = cv2.cvtColor(template, cv2.COLOR_BGR2GRAY)
template = cv2.Canny(template, 50, 200)
(h, w) = template.shape[:2]
start_time = time.time()
mon = {'top': 200, 'left': 200, 'width': 200, 'height': 200}
with mss() as sct:
while True:
last_time = time.time()
img = sct.grab(mon)
img = np.array(img)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
edged = cv2.Canny(gray, 50, 200)
found = None
for scale in np.linspace(0.2, 1.0, 20)[::-1]:
resized = imutils.resize(gray, width=int(gray.shape[1] * scale))
r = gray.shape[1] / float(resized.shape[1])
if resized.shape[0] < h or resized.shape[1] < w:
break
edged = cv2.Canny(resized, 50, 200)
cv2.imwrite("canny_image.png", edged)
result = cv2.matchTemplate(edged, template, cv2.TM_CCOEFF)
(_, maxVal, _, maxLoc) = cv2.minMaxLoc(result)
if found is None or maxVal > found[0]:
found = (maxVal, maxLoc, r)
(_, maxLoc, r) = found
(startX, startY) = (int(maxLoc[0] * r), int(maxLoc[1] * r))
(endX, endY) = (int((maxLoc[0] + w) * r), int((maxLoc[1] + h) * r))
cv2.rectangle(img, (startX, startY), (endX, endY), (180, 105, 255), 2)
print('The loop took: {0}'.format(time.time()-last_time))
cv2.imshow('test', np.array(img))
if cv2.waitKey(25) & 0xFF == ord('q'):
cv2.destroyAllWindows()
break
Let untitled.png be a file storing the image
Here is a working program. I used the following to put it together,
OpenCV Org: Template Matching
Taking screenshots with OpenCV and Python
OpenCV python: ValueError: too many values to unpack
import os
import cv2 as cv
import numpy as np
import pyautogui
import time
import winsound # for sound
from matplotlib import pyplot as plt
os.chdir("C:\\Users\\Mike\\\Desktop")
img = cv.imread('untitled.png',0)
img_piece = cv.cvtColor(img, cv.COLOR_RGB2BGR)
c, w, h = img_piece.shape[::-1]
while 1:
pic = pyautogui.screenshot()
template = cv.cvtColor(np.array(pic), cv.COLOR_RGB2BGR)
meth = 'cv.TM_CCOEFF'
method = eval(meth)
# Apply template Matching
res = cv.matchTemplate(img_piece,template,method)
min_val, max_val, min_loc, max_loc = cv.minMaxLoc(res)
top_left = max_loc
bottom_right = (top_left[0] + w, top_left[1] + h)
cv.rectangle(img,top_left, bottom_right, 255, 2)
if max_val > 66000000.0:
print(max_val, top_left, bottom_right)
winsound.Beep(888, 111)
if 1:
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()
break
time.sleep(1)
Below is the basic code to perform a match template. Place it below img = numpy.array(sct.grab(monitor)) and it will run every frame.
# create grayscale of image - because template is also grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# perform match
res = cv2.matchTemplate(gray,template ,cv2.TM_CCOEFF)
# get coordinates of best match
min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(res)
top_left = min_loc
bottom_right = (top_left[0] + w, top_left[1] + h)
# draw red rectangle over original screen capture
cv2.rectangle(img,top_left, bottom_right,(0,0,255),3)
# display image
cv2.imshow('Result',img)
You can find some more info on matchTemplate here
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