Recording x/y axis movement with openCV-python - python

I'm trying to record the distance travelled by an object (in this instance, part of a face as detected by a haar cascade) from a video file. So far, I have a rectangle drawn to the section of the face that I wish to record x/y travel data for, but have been unable to find info on exactly how to store info on how far/which way the face has travelled in 2 dimensions. My code is below:
import cv2
import numpy as py
from matplotlib import pyplot as plt
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
cap = cv2.VideoCapture("resources/video/EXAMPLE.mp4")
while True:
ret, img = cap.read()
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.3, 9)
for (x,y,w,h) in faces:
cv2.rectangle(img, (x,y), (x+w, int(y+h/3)), (255,0,0), 2)
cv2.imshow('img',img)
k = cv2.waitKey(30) & 0xff
if k == 27:
break
cap.release()
cap.destroyAllWindows()
Any info/pointers as far as how I can record movement data would be appreciated!

If you simply want to store the coordinates, you can add the (x,y) tuple to a list
If you're tracking just one face you could use object tracking
If you want to track multiple faces you can check out the multitracker.

Related

capture only one photo of face per person and save it automatically (without pressing a key) in opencv Python

I'm trying to build a face detector with webcam using opencv in Python.
When human face is detected, the system need to be able to capture only one photo of face per person and save it automatically (without pressing a key), until the person leaves the frame and another person enters and again his face detected and saved in an image file.
I'm using a while loop for the live video stream and the continous face detection. I tried to create an inner while loop for saving the face photo, but it takes multiple frames.
The code:
import numpy as np
import cv2
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
cap=cv2.VideoCapture(0)
while True:
ret, img=cap.read()
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.3, 5, minSize=(150, 150), maxSize=(300, 300))
for (x,y,w,h) in faces:
cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
face_img_gray = gray[y:y+h, x:x+w]
face_img_color = img[y:y+h, x:x+w]
laplacian_var = cv2.Laplacian(face_img_gray, cv2.CV_64F).var()
#print(laplacian_var)
if laplacian_var > 140: # avoid blur frame capture
cv2.imwrite('Frame.jpg', face_img_color)
cv2.imshow('img', img)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()

Set background color outside ROI in OpenCV

I successfully displayed the video feed and am trying to change the background color of the area outside ROI from black to blue but the screen still shows black background. Please help me solve the problem. Any help would be greatly appreciated.
Original code
import numpy as np
from cv2 import cv2
'''
ML object detection algo(haarcascade)used to identify objects.
the XML file consists of trained Haar Cascade models.
'''
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
#initialize video from the webcam
video = cv2.VideoCapture(1)
while True:
# ret tells if the camera works properly. Frame is an actual frame from the video feed
ret, frame= video.read()
# print(cv2.VideoCapture(0).isOpened())
# make sure port is working and read the image
if frame is not None and video.isOpened():
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# Detect the faces within the subregions of the image in scales
faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=6)
# Draw the rectangle around each face
for (x, y, w, h) in faces:
#Use the coordinates to find the center of the face and from that point draw a rectangle of radius w/2 or h/2.
center_coordinates = x + w // 2, y + h // 2
radius = w // 2 # or can be h / 2 or can be anything based on your requirements
#background color(black)
mask=np.zeros(frame.shape[:2] , dtype="uint8")
# Draw the desired region to crop out in white
cv2.circle(mask, center_coordinates, radius, (255,255,255),-1)
masked=cv2.bitwise_and(frame,frame,mask=mask)
cv2.imshow('mask applied',masked)
if cv2.waitKey(30) & 0xff==27:
break
video.release()
cv2.destroyAllWindows()
The above code detects and displays the face in the circular mask on the black background. But as mentioned above, The background color outside circular ROI should be blue.
I tried replacing mask=np.zeros(frame.shape[:2], dtype="uint8")with the code below and fails. Frame.shape[0:2]doesn't even include channel and I can't figure out how to change the color in the first place.
mask=np.ones(frame.shape[0:2], dtype="uint8")
mask[:,:,0]=255
mask[:,:,1]=0
mask[:,:,2]=0
I also tried creating a circular masked image then place it on another image only to find out it results in the same problem.
import numpy as np
from cv2 import cv2
'''
ML object detection algo(haarcascade)used to identify objects.
the XML file consists of trained Haar Cascade models.
'''
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
#initialize video from the webcam
video = cv2.VideoCapture(1)
print(cv2.VideoCapture(1).isOpened())
while True:
# ret tells if the camera works properly. Frame is an actual frame from the video feed
ret, frame= video.read()
# print(cv2.VideoCapture(0).isOpened())
# make sure port is working and read the image
if frame is not None and video.isOpened():
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# Detect the faces within the subregions of the image in scales
faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=6)
# Draw the rectangle around each face
for (x, y, w, h) in faces:
#Use the coordinates to find the center of the face and from that point draw a rectangle of radius w/2 or h/2.
center_coordinates = x + w // 2, y + h // 2
radius = w // 2 # or can be h / 2 or can be anything based on your requirements
#background color(black)
mask=np.zeros(frame.shape[:2] , dtype="uint8")
# create blue colored background
color = np.full_like(frame, (255,0,0))
# Draw the desired region to crop out in white
roi=cv2.circle(mask, center_coordinates, radius, (255,255,255),-1)
masked=cv2.bitwise_and(frame,frame,mask=mask)
mask_blue=cv2.bitwise_and(color,color,mask=mask-roi)
# combine the two masked images
result = cv2.add(masked,mask_blue)
cv2.imshow('result',result)
if cv2.waitKey(30) & 0xff==27:
break
video.release()
cv2.destroyAllWindows()
I have changed your code as follows according to your requirement. Here i have added an extra line
masked[np.where((masked==[0,0,0]).all(axis=2))]=[255,0,0]
where you can change pixel values of black region to any specific color.
import numpy as np
import cv2
'''
ML object detection algo(haarcascade)used to identify objects.
the XML file consists of trained Haar Cascade models.
'''
face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades +'haarcascade_frontalface_default.xml')
#initialize video from the webcam
video = cv2.VideoCapture(0)
print(cv2.VideoCapture(0).isOpened())
while True:
# ret tells if the camera works properly. Frame is an actual frame from the video feed
ret, frame= video.read()
# print(cv2.VideoCapture(0).isOpened())
# make sure port is working and read the image
if frame is not None and video.isOpened():
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# Detect the faces within the subregions of the image in scales
faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=6)
# Draw the rectangle around each face
for (x, y, w, h) in faces:
#Use the coordinates to find the center of the face and from that point draw a rectangle of radius w/2 or h/2.
center_coordinates = x + w // 2, y + h // 2
radius = w // 2 # or can be h / 2 or can be anything based on your requirements
#background color(black)
mask=np.zeros(frame.shape[:2] , dtype="uint8")
# Draw the desired region to crop out in white
roi=cv2.circle(mask, center_coordinates, radius, (255,255,255),-1)
masked=cv2.bitwise_and(frame,frame,mask=mask)
masked[np.where((masked==[0,0,0]).all(axis=2))]=[255,0,0]
cv2.imshow('result',masked)
if cv2.waitKey(30) & 0xff==27:
break
video.release()
cv2.destroyAllWindows()

how to keep Several parts of the matrix and zero the rest?

I'm trying to write a program that detects my eyes and then just keeps them and blackens the rest of the video.
so I just have the coordinates of eyes and I want to keep these sub-matrices
and make the rest of the matrix to zero.
import numpy as np
import cv2
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
eye_cascade = cv2.CascadeClassifier('haarcascade_eye.xml')
cap = cv2.VideoCapture(0)
while(True):
ret, img = cap.read()
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x,y,w,h) in faces:
roi_gray = gray[y:y+h, x:x+w]
roi_color = img[y:y+h, x:x+w]
eyes = eye_cascade.detectMultiScale(roi_gray)
for (ex,ey,ew,eh) in eyes:
# how to keep this : img[y+ey:y+ey+eh,x+ex:x+ex+ew] ????
cv2.rectangle(roi_color,(ex,ey),(ex+ew,ey+eh),(0,255,0),4)
cv2.imshow('img',img)
k = cv2.waitKey(30) & 0xff
if k==ord('q'):
break
cap.release()
cv2.destroyAllWindows()
generally, how can we do this fast and simple?
I think it's hard to think about how to keep parts of the matrix and zero the rest, simply because "the rest" is a rather irregular shape.
Since you can easily process rectangular sub-matrices using a Region of Interest, you can create a zero matrix of the same size as your initial matrix, compute ROIs for the regions you want to keep, and assign them to ROIs at identical positions in the zero matrix.
See OpenCV C++, getting Region Of Interest (ROI) using cv::Mat for details on how to get the ROIs.

Getting specific image cross-section from opencv cascade with python

I'm hoping to be able to isolate a small rectangular section of the area that is returned by a haar cascade (the cascade I'm using detects faces, so for example I would like to be able to isolate just the forehead within a given face). I know that training it specifically to detect the area I want is an option, but I'm hoping that it is easy to specify an arbitrary area within the face (for example, the top 20% of the rectangle). I include the code I'm using below:
import cv2
import numpy as py
from matplotlib import pyplot as plt
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
cap = cv2.VideoCapture("resources/video/EXAMPLE.mp4")
while True:
ret, img = cap.read()
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.3, 9)
for (x,y,w,h) in faces:
cv2.rectangle(img, (x,y), (x+w, y+h), (255,0,0), 2)
cv2.imshow('img',img)
k = cv2.waitKey(30) & 0xff
if k == 27:
break
cap.release()
cap.destroyAllWindows()
Is there a way to manipulate/gain info about the pixels in "faces"? Any help/pointers would be hugely appreciated.
basicly you can divide h with 3 to getting forehead:
for (x,y,w,h) in faces:
cv2.rectangle(img, (x,y), (x+w, int(y+h/3)), (255,0,0), 2)
but if you want to getting optimized results you can use landmark detection

how to identify the position of detected face

I have to detect faces using openCV and python. Then identify the position of the detected face if it is in the right, the left or the middle of the screen.
I already succeed to detect faces using the code below and still to know the position of the faces could someone please help me ?
import cv2
import sys
import numpy as np
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
cap = cv2.VideoCapture(1)
while True:
#capture frame by frame
ret,frame = cap.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray,
scaleFactor=1.1,
minNeighbors= 5,
minSize=(30, 30),
flags=cv2.cv.CV_HAAR_SCALE_IMAGE)
#Draw a rectangle around the faces
for (x, y, w,h) in faces:
cv2.rectangle(frame, (x, y), (x+w, y+h), (0,255, 0), 2)
cv2.imshow('video',frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
You could get the centre of the rectangle:
centre_x = x + w/2
centre_y = y + y/2
Then compare it with the size of the image. Assuming you have the image shape information:
height, width, channels = frame.shape #it could be gray.shape too
You can understand for example if the face is detected on the left side of the image by checking centre_x<width.
You have all the information to divide the image into a grid and understand where the rectangle places itself.

Categories

Resources