motion-detector's Introduction

Motion- Detector System Using OpenCV

Python/OpenCV scripts that detect motion on webcam and allow record it to a file and plot a graph for proper Visualization.

Description

The Process

The trivial idea is to compute the difference between two frames apply a threshold the separate pixels that have changed from the others and then count all the black pixels. Then the average is calculated with this count and the total number of pixels and depending of the ceil the event is triggered or not.

Additional informations:

initRecorder - initialise the recorder with an arbitrary codec it can be changed with problems in the run method no motion can be detected in the first 5 second because it is almost the time needed for the webcam to adjust the focus and the luminosity which imply lot's of changes on the image
processImage - contains all the images operations applied to the image
somethingHasMoved - The image iteration to count black pixels is contained in this method

Requirements

X86, X86_64, ARMv7 or ARMv8 version of Ubuntu 18.04 or Debian 8 (will most likely work on other Linux based operating systems as well)
Python 3.5 or above
Camera or Video file
Install OpenCV or pip install opencv-python
Install Bokeh library or pip install bokeh

Run Motion Detecto5

Clone the repository and run the command python plotting.py in the project directory.

Scenario 1

Scenario 2(Under motion)

Result

Plotting

Use case & Future Scope

Motion Detector can be used on SBCs such as Raspberry Pi, NanoPi M1, CHIP, ODROID C1/C2/XU4, Pine A64, etc. to create compact smart cameras.
Threading and subprocess based architecture allows consistent FPS while processing frames, writing video files, moving files to remote location, etc. all concurrently.
Run multiple copies on a central server for IP based "dumb" cameras.
Supports several types of video inputs including USB and IP (wired/wireless) cameras, video files, etc.
Threshold based motion detection, ignore mask, multiple object marking and video recording.
Human feature detection with the ability to train your own detector.
Add your own plugins.

Help me with a ⭐ if you like my work. happy Coding ! ❤️

motion-detector's People

Contributors

Stargazers

Watchers

motion-detector's Issues

Please help me to solve this issue

PS C:\Users\Jebz\Desktop\Motion-Detector-master> python motion_detector.py
Traceback (most recent call last):
  File "motion_detector.py", line 25, in <module>
    (_,cnts,_)=cv2.findContours(thresh_frame.copy(),cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
ValueError: not enough values to unpack (expected 3, got 2)
[ WARN:1] global C:\Users\appveyor\AppData\Local\Temp\1\pip-req-build-6sxsq0tp\opencv\modules\videoio\src\cap_msmf.cpp (435) `anonymous-namespace'::SourceReaderCB::~SourceReaderCB terminating async callback
PS C:\Users\Jebz\Desktop\Motion-Detector-master>

ValueError: not enough values to unpack (expected 3, got 2)

When using python3 this error was encountered:
Traceback (most recent call last):
File "plotting.py", line 1, in
from motion_detector import df
File "/Users/vlad/Documents/pythonwork/toolsForCar/mksh/basic-motion-detection/Motion-Detector/motion_detector.py", line 25, in
(,cnts,)=cv2.findContours(thresh_frame.copy(),cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
ValueError: not enough values to unpack (expected 3, got 2)

Recommend Projects

ashutoshtiwari13 / motion-detector Goto Github PK