i´m new in Python and OpenCV. I played a little bit with the lucas-kanade example you can see below. Now I made a foto of my Raspberry PI box, where this code detects 5 Points (see figure 1) Lucas-Kanade-tracked-Points. In the second image I slightly moved a piece of paper from left to right in front of the box. There I saw, that my 5 tracked points can be moved by this piece of paper. These 5 points where now attached at the long side of this paper (see figure 2) moved tracked points. How is that possible? Why can I move this points? In my opinion they have to be lost, when I move this piece of paper over them. Can somebody help me please?
Best regards,
Hanz
import numpy as np
import cv2
cap = cv2.VideoCapture(0)
# params for ShiTomasi corner detection
feature_params = dict( maxCorners = 100,
qualityLevel = 0.3,
minDistance = 7,
blockSize = 7 )
# Parameters for lucas kanade optical flow
lk_params = dict( winSize = (15,15),
maxLevel = 2,
criteria = (cv2.TERM_CRITERIA_EPS | cv2.TERM_CRITERIA_COUNT, 10, 0.03))
# Create some random colors
color = np.random.randint(0,255,(100,3))
# Take first frame and find corners in it
ret, old_frame = cap.read()
old_gray = cv2.cvtColor(old_frame, cv2.COLOR_BGR2GRAY)
p0 = cv2.goodFeaturesToTrack(old_gray, mask = None, **feature_params)
# Create a mask image for drawing purposes
mask = np.zeros_like(old_frame)
while(1):
ret,frame = cap.read()
frame_gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
# calculate optical flow
p1, st, err = cv2.calcOpticalFlowPyrLK(old_gray, frame_gray, p0, None, **lk_params)
# Select good points
good_new = p1[st==1]
good_old = p0[st==1]
# draw the tracks
for i,(new,old) in enumerate(zip(good_new,good_old)):
a,b = new.ravel()
c,d = old.ravel()
mask = cv2.line(mask, (a,b),(c,d), color[i].tolist(), 2)
frame = cv2.circle(frame,(a,b),5,color[i].tolist(),-1)
img = cv2.add(frame,mask)
cv2.imshow('frame',img)
k = cv2.waitKey(30) & 0xff
if k == 27:
break
# Now update the previous frame and previous points
old_gray = frame_gray.copy()
p0 = good_new.reshape(-1,1,2)
cv2.destroyAllWindows()
cap.release()
I have found a solution. I have to check the prev points with the next points, like in this example, which can be found here https://github.com/opencv/opencv/blob/master/samples/python/lk_homography.py
And this is the relevant code line:
def checkedTrace(img0, img1, p0, back_threshold = 1.0):
p1, _st, _err = cv.calcOpticalFlowPyrLK(img0, img1, p0, None, **lk_params)
p0r, _st, _err = cv.calcOpticalFlowPyrLK(img1, img0, p1, None, **lk_params)
d = abs(p0-p0r).reshape(-1, 2).max(-1)
status = d < back_threshold
return p1, status
Related
i have a realsense l 515 camera. I want to find the size of an object inside. In my case, i am running darknet to detect a dummy object. Now Once the object is detected, i want to use the depth frame and the color frame to calculate the length and breadth of the object(roughly). For example, an apple. The bounding box is drawn around the apple. Now , how do i use this bounding box data along with the color frame and depth frame to find the dimensions of the apple? As the bounding box is roughly the size of the apple, i want to convert the pixel coordinates of the bounding box to calculate the dimensions of the apple in real life approximately. I read online about using point clouds but I am new to this, so i am quite unclear how to proceed.
import darknet
import cv2
import numpy as np
import pyrealsense2 as rs
"""##############. Function definitions. ##################"""
#Define the detection function
def image_detection(image, network, class_names, class_colors, thresh):
# Darknet doesn't accept numpy images.
# Create one with image we reuse for each detect
width = darknet.network_width(network)
height = darknet.network_height(network)
darknet_image = darknet.make_image(width, height, 3)
#image = cv2.imread(image_path)
image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
image_resized = cv2.resize(image_rgb, (width, height),interpolation=cv2.INTER_LINEAR)
darknet.copy_image_from_bytes(darknet_image, image_resized.tobytes())
detections = darknet.detect_image(network, class_names, darknet_image, thresh=thresh)
darknet.free_image(darknet_image)
image = darknet.draw_boxes(detections, image_resized, class_colors)
return cv2.cvtColor(image, cv2.COLOR_BGR2RGB), detections
# Initialize and declare the neural network along with data files, config files etc
quantity_apples = []
config_file = "/home/jetson/Desktop/pano_l515/yolov4.cfg"
data_file = "/home/jetson/Desktop/pano_l515/coco.data"
weights = "/home/jetson/Desktop/pano_l515/yolov4.weights"
network, class_names, class_colors = darknet.load_network(
config_file,
data_file,
weights,
batch_size=1
)
## Realsense from align-depth2color.py
# Create a pipeline
pipeline = rs.pipeline()
# Create a config and configure the pipeline to stream
# different resolutions of color and depth streams
config = rs.config()
# Get device product line for setting a supporting resolution
pipeline_wrapper = rs.pipeline_wrapper(pipeline)
pipeline_profile = config.resolve(pipeline_wrapper)
device = pipeline_profile.get_device()
device_product_line = str(device.get_info(rs.camera_info.product_line))
config.enable_stream(rs.stream.depth, 1024, 768, rs.format.z16, 30)
if device_product_line == 'L500':
print(device_product_line)
config.enable_stream(rs.stream.color, 1280, 720, rs.format.bgr8, 30)
else:
config.enable_stream(rs.stream.color, 640, 480, rs.format.bgr8, 30)
# Start streaming
profile = pipeline.start(config)
# Getting the depth sensor's depth scale (see rs-align example for explanation)
depth_sensor = profile.get_device().first_depth_sensor()
depth_scale = depth_sensor.get_depth_scale()
print("Depth Scale is: " , depth_scale)
# We will be removing the background of objects more than
# clipping_distance_in_meters meters away
clipping_distance_in_meters = 1 #1 meter
clipping_distance = clipping_distance_in_meters / depth_scale
# Create an align object
# rs.align allows us to perform alignment of depth frames to others frames
# The "align_to" is the stream type to which we plan to align depth frames.
align_to = rs.stream.color
align = rs.align(align_to)
# Streaming loop
try:
for i in range(0,2):
# Get frameset of color and depth
frames = pipeline.wait_for_frames()
# frames.get_depth_frame() is a 640x360 depth image
# Align the depth frame to color frame
aligned_frames = align.process(frames)
# Get aligned frames
aligned_depth_frame = aligned_frames.get_depth_frame() # aligned_depth_frame is a 640x480 depth image
color_frame = aligned_frames.get_color_frame()
# Validate that both frames are valid
if not aligned_depth_frame or not color_frame:
continue
depth_image = np.asanyarray(aligned_depth_frame.get_data())
color_image = np.asanyarray(color_frame.get_data())
dn_frame_width = 416
dn_frame_height = 416
frame_width = color_image.shape[1]
frame_height = color_image.shape[0]
#### Passing the image to darknet
image, detections = image_detection(color_image, network, class_names, class_colors, thresh=0.05)
for i in range(len(detections)):
xc_percent = detections[i][2][0]/dn_frame_width
yc_percent = detections[i][2][1]/dn_frame_height
w_percent = detections[i][2][2]/dn_frame_width
h_percent = detections[i][2][3]/dn_frame_height
xc = xc_percent*frame_width
yc = yc_percent*frame_height
w = w_percent*frame_width
h = h_percent*frame_height
xmin = xc - w/2.0
ymin = yc - h/2.0
xmax = xc + w/2.0
ymax = yc + h/2.0
#If object is detected, increase the count of the object in the frame
if detections[i][0] == "apple":
cv2.rectangle(color_image, (int(xmin),int(ymin)),(int(xmax),int(ymax)),(0,0,255),2)
cv2.putText(color_image, "apple", (int(xmin), int(ymin-10)), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0,0,255), 2)
#cv2.imwrite(output_path, frame)
# Render images:
# depth align to color on left
# depth on right
depth_colormap = cv2.applyColorMap(cv2.convertScaleAbs(depth_image, alpha=0.03), cv2.COLORMAP_JET)
images = np.hstack((color_image, depth_colormap))
cv2.imwrite("test_images.jpg", color_image)
#cv2.namedWindow('Align Example', cv2.WINDOW_NORMAL)
#cv2.imshow('Align Example', images)
key = cv2.waitKey(1)
# Press esc or 'q' to close the image window
#if key & 0xFF == ord('q') or key == 27:
cv2.destroyAllWindows()
#break
finally:
pipeline.stop()
This is the output image so far. How do i proceed?
I'm currently trying to create a detector of aphids (green and rose) on plants but only using "classic" image processing technique (no neural network).
Here are an image I'm working on:
'aphids.jpg'
I'm working on a code (see below). If you apply it on the image you should have the plants alone. My problem is that I want to isolate the aphids that can be seen on the plants. There are a lot of them but I just want to detect the biggest or the more obvious.
On the code there is an "edges_detect" function I'm currently working on. One of the problem I have is that I can detect some of the aphids as contour but it will also take simple lines...
I tried to drop those line using the hierarchy of contour but it seems those line have inner contour so I can't easily delete them.
I also tried the adjust_gamma and contrast, but it doesn't give that much result.
I'm looking for more ideas. What would you try ?
Thank you in advance !
Here is the code:
import cv2
import numpy as np
import matplotlib.pyplot as plt
def adjust_gamma(image, gamma=1.0):
# build a lookup table mapping the pixel values [0, 255] to
# their adjusted gamma values
invGamma = 1.0 / gamma
table = np.array([((i / 255.0) ** invGamma) * 255
for i in np.arange(0, 256)]).astype("uint8")
# apply gamma correction using the lookup table
return cv2.LUT(image, table)
def adjust_contrast(image,alpha=1.0,beta=0):
new = np.zeros(image.shape,image.dtype)
for y in range(image.shape[0]):
for x in range(image.shape[1]):
for c in range(image.shape[2]):
new[y,x,c] = np.clip(alpha*image[y,x,c]+beta,0,255)
return(new)
def img_process(img):
(h1, w1) = img.shape[:2]
center = (w1 / 2, h1 / 2)
blur = cv2.GaussianBlur(img.copy(),(5,5),0)
hsv = cv2.cvtColor(blur,cv2.COLOR_BGR2HSV)
#image = img.copy()
#Boundaries to separate plants from the image
l_bound = np.array([20,0,0])
h_bound = np.array([90,250,170])#green
mask = cv2.inRange(hsv,l_bound,h_bound)
res = cv2.bitwise_and(img,img,mask=mask)
#Find contour plants
cnt,_ = cv2.findContours(mask,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)
sort_cnt = sorted(cnt,key=cv2.contourArea,reverse=True)
cnt = [sort_cnt[i] for i in range(len(sort_cnt)) if cv2.contourArea(sort_cnt[i])>300]
cv2.drawContours(res, cnt, -1, (0,255,0), -1)
#Inverse mask to have only the plant in the image
mask2 = cv2.inRange(res,np.array([0,0,0]),np.array([250,250,250]))
mask2 = cv2.bitwise_not(mask2)
res2 = cv2.bitwise_and(img,img,mask=mask2)
#Augment bright/contrast
res2=res2*1.45
res2=res2.astype('uint8')
#Crop
res2 = res2[:-50,int(center[0]-300):int(center[0]+550)]
return res2
def edge_detec(img):
(h1, w1) = img.shape[:2]
center = (w1 / 2, h1 / 2)
blur = cv2.GaussianBlur(img.copy(),(5,5),0)
gray = cv2.cvtColor(blur,cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(gray,30,70,apertureSize = 3)
edges = edges[:-50,int(center[0]-300):int(center[0]+550)]
#kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE,(3,3))
#edges = cv2.morphologyEx(edges, cv2.MORPH_GRADIENT, kernel)
cnt,hierarchy = cv2.findContours(edges,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
cnt = sorted(cnt,key=cv2.contourArea,reverse=True)
listArea = list(map(cv2.contourArea,cnt))
sort_cnt = [x for x in cnt if cv2.contourArea(x)>10]
cv2.drawContours(edges, sort_cnt, -1, (0,255,0), -1)
return edges,center,img
### Debut programme
img = cv2.imread('051.jpg')
while True:
##Put processing function here
img_mod = img_process(img)
cv2.imshow('img',img_mod)
if cv2.waitKey(1) & 0xFF == 27:
break
cv2.destroyAllWindows()
I am learning Image Filtering using opencv. I wrote some code but my code could only detect objects with red color, How can I detect objects with other colors.
I tried different numpy array values, still I'm not satisfied with output
hsv = cv2.cvtColor(frame,cv2.COLOR_BGR2HSV)
lower_blue = np.array([150,150,0])
upper_blue = np.array([255,255,225])
mask = cv2.inRange(hsv,lower_blue,upper_blue)
res = cv2.bitwise_and(frame,frame,mask=mask)
cv2.imshow('res',res)
You just need to change the boundary values (in your case lower_blue and upper_blue) to different values. The values may range ass follows [0 < H< 179], [0 < S < 255], [0 < V < 255]. You can see it better from the picture.
Good luck!
First, the range of H should be from 0 to 179. To get the feeling of what combination of HSV values produces what color here is a small piece of code. Below code creates trackbars for H, S, V. Adjust the trackbars to segment the different colors.
import cv2
import numpy as np
def nothing(x):
pass
cap = cv2.VideoCapture(0)
# Create a window
cv2.namedWindow('image',cv2.WINDOW_NORMAL)
# create trackbars for color change
cv2.createTrackbar('lowH','image',0,179,nothing)
cv2.createTrackbar('highH','image',179,179,nothing)
cv2.createTrackbar('lowS','image',0,255,nothing)
cv2.createTrackbar('highS','image',255,255,nothing)
cv2.createTrackbar('lowV','image',0,255,nothing)
cv2.createTrackbar('highV','image',255,255,nothing)
while(True):
ret, frame = cap.read()
# get current positions of the trackbars
ilowH = cv2.getTrackbarPos('lowH', 'image')
ihighH = cv2.getTrackbarPos('highH', 'image')
ilowS = cv2.getTrackbarPos('lowS', 'image')
ihighS = cv2.getTrackbarPos('highS', 'image')
ilowV = cv2.getTrackbarPos('lowV', 'image')
ihighV = cv2.getTrackbarPos('highV', 'image')
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
lower_hsv = np.array([ilowH, ilowS, ilowV])
higher_hsv = np.array([ihighH, ihighS, ihighV])
mask = cv2.inRange(hsv, lower_hsv, higher_hsv)
frame = cv2.bitwise_and(frame, frame, mask=mask)
cv2.imshow('image', frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
Template matching in OpenCV is great. And you can pass a mask to cv2.minMaxLoc so that you only search (sort of) in part of the image for the template you want. You can also use a mask at the matchTemplate operation, but this only masks the template.
I want to find a template and I want to be assured that this template is within some other region of my image.
Calculating the mask for minMaxLoc seems kind of heavy. That is, calculating an accurate mask feels heavy. If you calculate a mask the easy way, it ignores the size of the template.
Examples are in order. My input images are show below. They're a bit contrived. I want to find the candy bar, but only if it's completely inside the white circle of the clock face.
clock1
clock2
template
In clock1, the candy bar is inside the circular clock face and it's a "PASS". But in clock2, the candy bar is only partially inside the face and I want it to be a "FAIL". Here's a code sample for doing it the easy way. I use cv.HoughCircles to find the clock face.
import numpy as np
import cv2
img = cv2.imread('clock1.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
template = cv2.imread('template.png')
t_h, t_w = template.shape[0:2] # template height and width
# find circle in gray image using Hough transform
circles = cv2.HoughCircles(gray, method = cv2.HOUGH_GRADIENT, dp = 1,
minDist = 150, param1 = 50, param2 = 70,
minRadius = 131, maxRadius = 200)
i = circles[0,0]
x0 = i[0]
y0 = i[1]
r = i[2]
# display circle on color image
cv2.circle(img,(x0, y0), r,(0,255,0),2)
# do the template match
result = cv2.matchTemplate(img, template, cv2.TM_CCOEFF_NORMED)
# finally, here is the part that gets tricky. we want to find highest
# rated match inside circle and we'd like to use minMaxLoc
# make mask by drawing circle on zero array
mask = np.zeros(result.shape, dtype = np.uint8) # minMaxLoc will throw
# error w/o np.uint8
cv2.circle(mask, (x0, y0), r, color = 1, thickness = -1)
# call minMaxLoc
min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(result, mask = mask)
# draw found rectangle on img
if max_val > 0.4: # use 0.4 as threshold for finding candy bar
cv2.rectangle(img, max_loc, (max_loc[0]+t_w, max_loc[1]+t_h), (0,255,0), 4)
cv2.imwrite('output.jpg', img)
output using clock1
output using clock2
finds candy bar even
though part of it is outside circle
So to properly make a mask, I use a bunch of NumPy operations. I make four separate masks (one for each corner of the template bounding box) and then AND them together. I'm not aware of any convenience functions in OpenCV that would do the mask for me. I'm a little nervous that all of the array operations will be expensive. Is there a better way to do this?
h, w = result.shape[0:2]
# make arrays that hold x,y coords
grid = np.indices((h, w))
x = grid[1]
y = grid[0]
top_left_mask = np.hypot(x - x0, y - y0) - r < 0
top_right_mask = np.hypot(x + t_w - x0, y - y0) - r < 0
bot_left_mask = np.hypot(x - x0, y + t_h - y0) - r < 0
bot_right_mask = np.hypot(x + t_w - x0, y + t_h - y0) - r < 0
mask = np.logical_and.reduce((top_left_mask, top_right_mask,
bot_left_mask, bot_right_mask))
mask = mask.astype(np.uint8)
cv2.imwrite('mask.png', mask*255)
Here's what the "fancy" mask looks like:
Seems about right. It cannot be circular because of the template shape. If I run clock2.jpg with this mask I get:
It works. No candy bars are identified. But I wish I could do it in fewer lines of code...
EDIT:
I've done some profiling. I ran 100 cycles of the "easy" way and the "accurate" way and calculated frames per second (fps):
easy way: 12.7 fps
accurate way: 7.8 fps
so there is some price to pay for making the mask with NumPy. These tests were done on a relatively powerful workstation. It could get uglier on more modest hardware...
Method 1: 'mask' image before cv2.matchTemplate
Just for kicks, I tried to make my own mask of the image that I pass to cv2.matchTemplate to see what kind of performance I can achieve. To be clear, this isn't a proper mask -- I set all of the pixels to ignore to one color (black or white). This is to get around the fact only TM_SQDIFF and TM_CORR_NORMED support a proper mask.
#Alexander Reynolds makes a very good point in the comments that some care must be taken if the template image (the thing we're trying to find) has lots of black or lots of white. For many problems, we will know a priori what the template looks like and we can specify a white background or black background.
I use cv2.multiply, which seems to be faster than numpy.multiply. cv2.multiply has the added advantage that it automatically clips the results to the range 0 to 255.
import numpy as np
import cv2
import time
img = cv2.imread('clock1.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
template = cv2.imread('target.jpg')
t_h, t_w = template.shape[0:2] # template height and width
mask_background = 'WHITE'
start_time = time.time()
for i in range(100): # do 100 cycles for timing
# find circle in gray image using Hough transform
circles = cv2.HoughCircles(gray, method = cv2.HOUGH_GRADIENT, dp = 1,
minDist = 150, param1 = 50, param2 = 70,
minRadius = 131, maxRadius = 200)
i = circles[0,0]
x0 = i[0]
y0 = i[1]
r = i[2]
# display circle on color image
cv2.circle(img,(x0, y0), r,(0,255,0),2)
if mask_background == 'BLACK': # black = 0, white = 255 on grayscale
mask = np.zeros(img.shape, dtype = np.uint8)
elif mask_background == 'WHITE':
mask = 255*np.ones(img.shape, dtype = np.uint8)
cv2.circle(mask, (x0, y0), r, color = (1,1,1), thickness = -1)
img2 = cv2.multiply(img, mask) # element wise multiplication
# values > 255 are truncated at 255
# do the template match
result = cv2.matchTemplate(img2, template, cv2.TM_CCOEFF_NORMED)
# call minMaxLoc
min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(result)
# draw found rectangle on img
if max_val > 0.4:
cv2.rectangle(img, max_loc, (max_loc[0]+t_w, max_loc[1]+t_h), (0,255,0), 4)
fps = 100/(time.time()-start_time)
print('fps ', fps)
cv2.imwrite('output.jpg', img)
Profiling results:
BLACK background 12.3 fps
WHITE background 12.1 fps
Using this method has very little performance hit relative to 12.7 fps in original question. However, it has the drawback that it will still find templates that still stick over the edge a little bit. Depending on the exact nature of the problem, this may be acceptable in many applications.
Method 2: use cv2.boxFilter to create mask for minMaxLoc
In this technique, we start with a circular mask (as in OP), but then modify it with cv2.boxFilter. We change the anchor from default center of kernel to the top left corner (0, 0)
import numpy as np
import cv2
import time
img = cv2.imread('clock1.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
template = cv2.imread('target.jpg')
t_h, t_w = template.shape[0:2] # template height and width
print('t_h, t_w ', t_h, ' ', t_w)
start_time = time.time()
for i in range(100):
# find circle in gray image using Hough transform
circles = cv2.HoughCircles(gray, method = cv2.HOUGH_GRADIENT, dp = 1,
minDist = 150, param1 = 50, param2 = 70,
minRadius = 131, maxRadius = 200)
i = circles[0,0]
x0 = i[0]
y0 = i[1]
r = i[2]
# display circle on color image
cv2.circle(img,(x0, y0), r,(0,255,0),2)
# do the template match
result = cv2.matchTemplate(img, template, cv2.TM_CCOEFF_NORMED)
# finally, here is the part that gets tricky. we want to find highest
# rated match inside circle and we'd like to use minMaxLoc
# start to make mask by drawing circle on zero array
mask = np.zeros(result.shape, dtype = np.float)
cv2.circle(mask, (x0, y0), r, color = 1, thickness = -1)
mask = cv2.boxFilter(mask,
ddepth = -1,
ksize = (t_w, t_h),
anchor = (0,0),
normalize = True,
borderType = cv2.BORDER_ISOLATED)
# mask now contains values from zero to 1. we want to make anything
# less than 1 equal to zero
_, mask = cv2.threshold(mask, thresh = 0.9999,
maxval = 1.0, type = cv2.THRESH_BINARY)
mask = mask.astype(np.uint8)
# call minMaxLoc
min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(result, mask = mask)
# draw found rectangle on img
if max_val > 0.4:
cv2.rectangle(img, max_loc, (max_loc[0]+t_w, max_loc[1]+t_h), (0,255,0), 4)
fps = 100/(time.time()-start_time)
print('fps ', fps)
cv2.imwrite('output.jpg', img)
This code gives a mask identical to OP, but at 11.89 fps. This technique gives us more accuracy with slightly more performance hit than Method 1.
Basically the code I'm writing needs to add a string in front of values being calculated every frame
For example:
Face 1: (eye aspect ratio), (mouth aspect ratio)
Face 2: (eye // //), (// // //)
... and so on, depending on how many faces are found using dlib's predictor.
The String needed here is "Face1: " |||| "Face2: " ... the other values are already found
Here's the code:
# Start capturing WebCam
#cap = cv2.VideoCapture(0)
framecount = 0
while True:
ret, frame = cap.read()
framecount += 1
frame = imutils.resize(frame, width = 1500)
if ret:
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
rects = detector(gray, 0)
for rect in rects:
x = rect.left()
y = rect.top()
x1 = rect.right() - x
y1 = rect.bottom() - y
landmarks = np.matrix([[p.x, p.y] for p in predictor(frame, rect).parts()])
left_eye = landmarks[LEFT_EYE_POINTS]
right_eye = landmarks[RIGHT_EYE_POINTS]
inner_mouth = landmarks[MOUTH_INNER_POINTS]
outer_mouth = landmarks[MOUTH_OUTLINE_POINTS]
left_eye_hull = cv2.convexHull(left_eye)
right_eye_hull = cv2.convexHull(right_eye)
inner_mouth_hull = cv2.convexHull(inner_mouth)
outer_mouth_hull = cv2.convexHull(outer_mouth)
# drawing the contours on frame
cv2.drawContours(frame, [left_eye_hull], -1, (0, 255, 0), 1)
cv2.drawContours(frame, [right_eye_hull], -1, (0, 255, 0), 1)
# Eye aspect ratio and Mouth aspect ratio
ear_left = eye_aspect_ratio(left_eye)
ear_right = eye_aspect_ratio(right_eye)
MAR = mouth_aspect_ratio(inner_mouth)
## This part below:
print(framecount," {:.2f}".format(ear_left), " {:.2f}".format(MAR))
print("Number of faces: ", len(rects))
The first print function will print out the frame of video and display the Eye aspect ratio and Mouth aspect ratio. And if there is more than one face, it will repeat the frame number more than once but will have different values.
So, it does what I need it to do, however I want to add a name before each of these values.
Second print function displays the number of faces present in a video, in my case its number 3 for three faces.
Example of output:
Output example
Example of output with Enumerate:
Output example enum