© 2018 - Analytics Link

Creating a sketched video using OpenCV & Python

October 18, 2019

A very quick post, showing how to take a video and create a 'sketched' version of it using OpenCV.

 

I have used and modified code that was originally posted here, so credit to askaswiss.com.

 

I've taken their code and applied it to a video file, stacking the output so we can see how cool the sketch looks vs. the original!

 

Code below:

 

#################################################################

# import packages

#################################################################

 

import numpy as np

import cv2

 

#################################################################

# bring in video file

#################################################################

 

cap = cv2.VideoCapture("driving_dubai_clipped.mp4")

 

#################################################################

# loop through frames

#################################################################

 

while True:

    

    ret, frame = cap.read()

 

    # convert to sketch

    img_gray = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)

    img_blur = cv2.GaussianBlur(img_gray, (21, 21), 0, 0)

    img_blend = cv2.divide(img_gray, img_blur, scale=256)

    img_blend = cv2.cvtColor(img_blend,cv2.COLOR_GRAY2BGR)

 

    # stack original and sketch frames

    dual_image = np.vstack((img_blend,frame))

 

    # display the resulting frame

    cv2.imshow('img_contour',dual_image)

    if cv2.waitKey(1) & 0xFF == ord('q'):

        break

 

# release capture

cap.release()

cv2.destroyAllWindows()

 

 

 

 

We only require numpy and cv2 for this project.

 

After importing the video file, we loop through the frames, firstly converting to greyscale then applying a Gaussian blur to reduce noise in the frame.  We then blend the original greyscale frame and the blurred frame, and I force it back to 3 colour channels using cv2.COLOR_GRAY2BGR purely so I can stack it with the original colour frame.

 

We then use numpy's vstack function to put the frames together and then visualise them.  The result is below...

 

 

 

 

 

 

 

Share on Facebook
Please reload

Please reload

Recent Posts