We are doing a project on license plate recognition using python(2.7.12). We have divided the video into frames using the following code:
import cv2 #importing opencv library
import numpy #importing numpy
cap = cv2.VideoCapture('C:/Python27/project/license.avi') #read the video
success,image = cap.read() #divide into frames
count = 0
success = True
while (cap.isOpened()):
success,image = cap.read()
print 'Read a new frame: ', success #when frame has been read successfully
if (type(image) == type(None)): #check for invalid frame
break
else:
gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) #convert frame into grey
cv2.imwrite("frame%d.jpg" % count, gray_image) # save frame as JPEG file
count += 1 #repeat for all the frames
cap.release()
We are trying to get the best frame(with high quality).Is it possible to automatically select a frame that has the complete license plate?
Any suggestions would be helpful.
Related
While extracting frames from a video using OpenCV, how can I set a particular value at which the frame extraction will occur?
I have seen many available sample codes for image extraction, but they are not shown any option for the frame rate.
There are many ways of frame extraction, one is to use ffmg for frame extraction.
other is, You can try this code, but we can't use any random value that you will understand while trying at different values.
change directories ap per your system.
import math
count = 0
videoFile = "train/train.mp4"
cap = cv2.VideoCapture(videoFile)
frameRate = cap.get(5) #frame rate
x=1
while(cap.isOpened()):
frameId = cap.get(1)
ret, frame = cap.read()
if (ret != True):
break
else (frameId % math.floor(frameRate) == 0):
filename ="train/frame2/frame%d.jpg" % count;count+=1
cv2.imwrite(filename, frame)
cap.release()
print ("Done!")
I have conferance call video with different people's tiles arranged on a grid.
Example:
gallery view zoom
Can I crop every video tile to a separate file using python or nodejs?
Yes, you can achieve that using OpenCV library
Read the video in OpenCV using VideoCapture API. Note down framerate while reading.
Parse through each frame and crop the frame:
Write the frame in a video using OpenCV VideoWriter
Here is the example code using (640,480) to be the new dimensions:
cap = cv2.VideoCapture(<video_file_name>)
fps = cap.get(cv2.CAP_PROP_FPS)
out = cv2.VideoWriter('<output video file name>, -1, fps, (640,480))
while(cap.isOpened()):
ret, frame = cap.read()
crop_frame = frame[y:y+h, x:x+w]
# write the crooped frame
out.write(crop_frame)
# Release reader wand writer after parsing all frames
cap.release()
out.release()
Here's the code (tested). It works by initialising a number of video outputs, then for each frame of the input video: cropping the region of interest (roi) and assigning each to the relevent output video. You might need to make tweaks depending on input video dimensions, number of times, offsets etc.
import numpy as np
import cv2
import time
cap = cv2.VideoCapture('in.mp4')
ret, frame = cap.read()
(h, w, d) = np.shape(frame)
horiz_divisions = 5 # Number of tiles stacked horizontally
vert_divisions = 5 # Number of tiles stacked vertically
divisions = horiz_divisions*vert_divisions # Total number of tiles
seg_h = int(h/vert_divisions) # Tile height
seg_w = int(w/horiz_divisions) # Tile width
# Initialise the output videos
outvideos = [0] * divisions
for i in range(divisions):
outvideos[i] = cv2.VideoWriter('out{}.avi'.format(str(i)),cv2.VideoWriter_fourcc('M','J','P','G'), 10, (seg_w,seg_h))
# main code
while(cap.isOpened()):
ret, frame = cap.read()
if ret == True:
vid = 0 # video counter
for i in range(vert_divisions):
for j in range(horiz_divisions):
# Get the coordinates (top left corner) of the current tile
row = i * seg_h
col = j * seg_w
roi = frame[row:row+seg_h,col:col+seg_w,0:3] # Copy the region of interest
outvideos[vid].write(roi)
vid += 1
if cv2.waitKey(1) & 0xFF == ord('q'):
break
else:
break
# Release all the objects
cap.release()
for i in range(divisions):
outvideos[i].release()
# Release everything if job is finished
cv2.destroyAllWindows()
Hope this helps!
I want to create a csv file which should have the coordinates of each object as i am getting in my python shell window.
import cv2
import pandas as pd
# capture frames from a video
cap = cv2.VideoCapture('video.avi')
# Trained XML classifiers describes some features of some object we want
to detect
car_cascade = cv2.CascadeClassifier('cars.xml')
no_obj_det=0
frames_got_processed = 0
frame_processed = []
number_of_object_detected= []
# loop runs if capturing has been initialized.
while True:
# reads frames from a video
try:
ret, frames = cap.read()
frames_got_processed += 1
# convert to gray scale of each frames
gray = cv2.cvtColor(frames, cv2.COLOR_BGR2GRAY)
# Detects cars of different sizes in the input image
cars = car_cascade.detectMultiScale(gray, 1.1, 1)
# To draw a rectangle in each cars
for (x,y,w,h) in cars:
cv2.rectangle(frames,(x,y),(x+w,y+h),(0,0,255),2)
cv2.imshow('video2', frames)
if cv2.waitKey(33) == 27:
break
# loop to count the number of objects detected at every 5th frame
if frames_got_processed % 5 == 0:
print "appended in frame
number",frames_got_processed,len(cars),cars
frame_processed.append(frames_got_processed)
number_of_object_detected.append(len(cars))
df.to_csv('example.csv')
# De-allocate any associated memory usage
cv2.destroyAllWindows()
Output on python shell same output i want in my csv file
[1]: https://i.stack.imgur.com/vfPEP.png
As you probably need to write data to the CSV continuously, it is probably better to do this as you go rather than trying to append all of the data and then write it at the end. Doing it this way would avoid you eventually running out of memory.
The Python csv library could be used to do this as follows:
import cv2
import csv
# capture frames from a video
cap = cv2.VideoCapture('video.avi')
# Trained XML classifiers describes some features of some object we want to detect
car_cascade = cv2.CascadeClassifier('cars.xml')
frames_got_processed = 0
with open('example.csv', 'w', newline='') as f_output:
csv_output = csv.writer(f_output)
# loop runs if capturing has been initialized.
while True:
# reads frames from a video
try:
ret, frames = cap.read()
frames_got_processed += 1
# convert to gray scale of each frames
gray = cv2.cvtColor(frames, cv2.COLOR_BGR2GRAY)
# Detects cars of different sizes in the input image
cars = car_cascade.detectMultiScale(gray, 1.1, 1)
# To draw a rectangle in each cars
for (x,y,w,h) in cars:
cv2.rectangle(frames,(x,y),(x+w,y+h),(0,0,255),2)
cv2.imshow('video2', frames)
if cv2.waitKey(33) == 27:
break
# loop to count the number of objects detected at every 5th frame
if frames_got_processed % 5 == 0:
print "appended in frame number", frames_got_processed, len(cars), cars
csv_output.writerow([frames_got_processed, len(cars)] + list(cars))
except:
pass
# De-allocate any associated memory usage
cv2.destroyAllWindows()
This should give you a row containing the frame number, the number of cars, followed by the co-ordinates for each car.
I am taking input from a video and I want to take the median value of the first 5 frames so that I can use it as background image for motion detection using deferential.
Also, I want to use a time condition that, say if motion is not detected then calculate the background again, else wait t seconds. I am new to opencv and I don't know how to do it.. Please help
Also, I want to take my video in 1 fps but this does not work. Here is the code I have:
import cv2
BLUR_SIZE = 3
NOISE_CUTOFF = 12
cam = cv2.VideoCapture('gh10fps.mp4')
cam.set(3, 640)
cam.set(4, 480)
cam.set(cv2.cv.CV_CAP_PROP_FPS, 1)
fps=cam.get(cv2.cv.CV_CAP_PROP_FPS)
print "Current FPS: ",fps
If you really want the median of the first 5 frames, then following should do what you are looking for:
import numpy as np
import cv2
cap = cv2.VideoCapture(0)
frames = []
for _ in range(5):
ret, frame = cap.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
frames.append(gray)
median = np.median(frames, axis=0).astype(dtype=np.uint8)
cv2.imshow('frame', median)
cv2.waitKey(0)
cap.release()
cv2.destroyAllWindows()
Note, this is just taking the source from a webcam as an example.
What I need to do is fairly simple:
load a 5 frames video file
detect background
On every frames, one by one :
subtract background (create foreground mask)
do some calculations on foreground mask
save both original frame and foreground mask
Just to see the 5 frames and the 5 corresponding fgmasks :
import numpy as np
import cv2
cap = cv2.VideoCapture('test.avi')
fgbg = cv2.BackgroundSubtractorMOG()
while(True):
# Capture frame-by-frame
ret, frame = cap.read()
fgmask = fgbg.apply(frame)
# Display the fgmask frame
cv2.imshow('fgmask',fgmask)
# Display original frame
cv2.imshow('img', frame)
k = cv2.waitKey(0) & 0xff
if k == 5:
break
cap.release()
cv2.destroyAllWindows()
Every frame gets opened and displayed correctly but the showed fgmask do not correspond to the showed original frame. Somewhere in the process, the order of the fgmasks gets mixed up.
The background does get subtracted correctly but I don't get the 5 expected fgmasks.
What am I missing ? I feel like this should be straightforward : the while loop runs over the 5 frames of the video and fgbg.apply apply the background subtraction function to each frame.
OpenCV version that I use is opencv-2.4.9-3
As bikz05 suggested, running average method worked pretty good on my 5 images sets. Thanks for the tip !
import cv2
import numpy as np
c = cv2.VideoCapture('test.avi')
_,f = c.read()
avg1 = np.float32(f)
avg2 = np.float32(f)
# loop over images and estimate background
for x in range(0,4):
_,f = c.read()
cv2.accumulateWeighted(f,avg1,1)
cv2.accumulateWeighted(f,avg2,0.01)
res1 = cv2.convertScaleAbs(avg1)
res2 = cv2.convertScaleAbs(avg2)
cv2.imshow('img',f)
cv2.imshow('avg1',res1)
cv2.imshow('avg2',res2)
k = cv2.waitKey(0) & 0xff
if k == 5:
break