Saturday, February 25, 2017

Linux: OpenCV and using Lucas-Kanade Optical Flow function.

Fist I install OpenCV python module and I try using with Fedora 25.
I used python 2.7 version.
[root@localhost mythcat]# dnf install opencv-python.x86_64 
Last metadata expiration check: 0:21:12 ago on Sat Feb 25 23:26:59 2017.
Dependencies resolved.
 Package              Arch          Version                Repository      Size
 opencv               x86_64        3.1.0-8.fc25           fedora         1.8 M
 opencv-python        x86_64        3.1.0-8.fc25           fedora         376 k
 python2-nose         noarch        1.3.7-11.fc25          updates        266 k
 python2-numpy        x86_64        1:1.11.2-1.fc25        fedora         3.2 M

Transaction Summary
Install  4 Packages

Total download size: 5.6 M
Installed size: 29 M
Is this ok [y/N]: y
Downloading Packages:
(1/4): opencv-python-3.1.0-8.fc25.x86_64.rpm    855 kB/s | 376 kB     00:00    
(2/4): opencv-3.1.0-8.fc25.x86_64.rpm           1.9 MB/s | 1.8 MB     00:00    
(3/4): python2-nose-1.3.7-11.fc25.noarch.rpm    543 kB/s | 266 kB     00:00    
(4/4): python2-numpy-1.11.2-1.fc25.x86_64.rpm   2.8 MB/s | 3.2 MB     00:01    
Total                                           1.8 MB/s | 5.6 MB     00:03     
Running transaction check
Transaction check succeeded.
Running transaction test
Transaction test succeeded.
Running transaction
  Installing  : python2-nose-1.3.7-11.fc25.noarch                           1/4 
  Installing  : python2-numpy-1:1.11.2-1.fc25.x86_64                        2/4 
  Installing  : opencv-3.1.0-8.fc25.x86_64                                  3/4 
  Installing  : opencv-python-3.1.0-8.fc25.x86_64                           4/4 
  Verifying   : opencv-python-3.1.0-8.fc25.x86_64                           1/4 
  Verifying   : opencv-3.1.0-8.fc25.x86_64                                  2/4 
  Verifying   : python2-numpy-1:1.11.2-1.fc25.x86_64                        3/4 
  Verifying   : python2-nose-1.3.7-11.fc25.noarch                           4/4 

  opencv.x86_64 3.1.0-8.fc25            opencv-python.x86_64 3.1.0-8.fc25       
  python2-nose.noarch 1.3.7-11.fc25     python2-numpy.x86_64 1:1.11.2-1.fc25    

[root@localhost mythcat]# 
This is my test script with opencv to detect flow using Lucas-Kanade Optical Flow function.
This tracks some points in a black and white video.
First you need:
- one black and white video;
- not mp4 file type file;
- the color args need to be under 4 ( see is 3);
- I used this video:
I used cv2.goodFeaturesToTrack().
We take the first frame, detect some Shi-Tomasi corner points in it, then we iteratively track those points using Lucas-Kanade optical flow.
The function cv2.calcOpticalFlowPyrLK() we pass the previous frame, previous points and next frame.
The returns next points along with some status numbers which has a value of 1 if next point is found, else zero.
That iteratively pass these next points as previous points in next step.
See the code below:
import numpy as np
import cv2

cap = cv2.VideoCapture('candle')

# params for ShiTomasi corner detection
feature_params = dict( maxCorners = 77,
                       qualityLevel = 0.3,
                       minDistance = 7,
                       blockSize = 7 )

# Parameters for lucas kanade optical flow
lk_params = dict( winSize  = (17,17),
                  maxLevel = 1,
                  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 =
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)

    ret,frame =
    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 =,(a,b),5,color[i].tolist(),-1)
    img = cv2.add(frame,mask)

    k = cv2.waitKey(30) & 0xff
    if k == 27:

    # Now update the previous frame and previous points
    old_gray = frame_gray.copy()
    p0 = good_new.reshape(-1,1,2)

The output of this file is:

Thursday, February 23, 2017

The bad and good urllib.

This is a simple python script:
import urllib
opener = urllib.FancyURLopener({})
f ="")
fo = open('workfile.txt', 'w')
The really bad news come from here:

Wednesday, February 22, 2017

The twill python module with Fedora 25.

Today I tested the twill python module with python 2.7 and Fedora 25.
This is: a scripting system for automating Web browsing. Useful for testing Web pages or grabbing data from password-protected sites automatically.
To install this python module I used pip command:
[root@localhost mythcat]# pip install twill
Collecting twill
Downloading twill-1.8.0.tar.gz (176kB)
100% |████████████████████████████████| 184kB 2.5MB/s
Installing collected packages: twill
Running install for twill ... done
Successfully installed twill-1.8.0

Let's try some tests:
[mythcat@localhost ~]$ python
Python 2.7.13 (default, Jan 12 2017, 17:59:37) 
[GCC 6.3.1 20161221 (Red Hat 6.3.1-1)] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> from twill import get_browser
>>> b = get_browser()
>>> from twill.commands import *
>>> go("")
==> at
>>> b.showforms()

Form #1
## ## __Name__________________ __Type___ __ID________ __Value__________________
1     q                        search    id-searc ...   
To talk to the Web browser directly, call the get_browser function.
You can see most of the twill commands by using:
>>> import

 -= Welcome to twill! =-

current page:
>> ?

Undocumented commands:
add_auth             fa           info             save_html           title
add_extra_header     find         load_cookies     setglobal           url  
agent                follow       notfind          setlocal          
back                 formaction   redirect_error   show              
clear_cookies        formclear    redirect_output  show_cookies      
clear_extra_headers  formfile     reload           show_extra_headers
code                 formvalue    reset_browser    showforms         
config               fv           reset_error      showhistory       
debug                get_browser  reset_output     showlinks         
echo                 getinput     run              sleep             
exit                 getpassword  runfile          submit            
extend_with          go           save_cookies     tidy_ok           

current page:
Basic is used by setlocal to fill website forms and the go function.
Ban can be very good for some tasks.
Now twill also provides a simple wrapper for mechanize functionality with the API is still unstable.

Thursday, February 16, 2017

Compare two images: the histogram method.

This is a very simple example about how to compare the histograms of both images and print the inconsistencies are bound to arise.
The example come with alternative solution: Histogram method.
The script was run under Fedora 25.
If the images are the same the result will be 0.0.
For testing I change the image2.png by make a line into this with a coverage of 10%.
The result of the script was:
The images come with this dimensions: 738 x 502 px.
import math
import operator
from math import *
import PIL

from PIL import Image
h1 ="image1.png").histogram()
h2 ="image2.png").histogram()

rms = math.sqrt(reduce(operator.add,
        map(lambda a,b: (a-b)**2, h1, h2))/len(h1))
print rms
About the operator module exports a set of efficient functions corresponding to the intrinsic operators of Python.
Example:, b)
operator.le(a, b)
operator.eq(a, b), b), b), b)
operator.__lt__(a, b)
operator.__le__(a, b)
operator.__eq__(a, b)
operator.__ne__(a, b)
operator.__ge__(a, b)
operator.__gt__(a, b)

This is like math operators:
lt(a, b) is equivalent to a < b
le(a, b) is equivalent to a <= b
Another example:
>>> # Elementwise multiplication
>>> map(mul, [0, 1, 2, 3], [10, 20, 30, 40])
[0, 20, 60, 120]

>>> # Dot product
>>> sum(map(mul, [0, 1, 2, 3], [10, 20, 30, 40]))