Localization of Objects by the Vision System

        This project integrates a computer vision system for the localization of certain objects according to a couple of algorithms, to mutually compare their results in the terms of reliability, stability and demand of computing power and to evaluate the possibilities of using them on the real industrial set. The system used in this work consists of a camera and a computer which processes the data retrieved from camera. The algorithms for object recognition are implemented in the programming language Python, along with the open-source library OpenCV. The resulting mutual comparison of the algorithms is based on the industrial set of bottle caps.

Project workflow

Step 1.  Determining the task

Step 2.  Defining the industrial set of bottle caps

Step 3.  Implementing the gray template matching algorithm

Step 4.  Implementing the binary template matching algorithm

Step 5.  Implementing the Canny edges Hough algorithm

Step 6.  Implementing the adaptive threshold Hough algorithm

Step 7.  Implementing the Haar cascade algorithm

Step 8.  Analyzing the results for different algorithms (shown for Haar cascade algorithm)

Run the project on Windows

Step 1.  Clone the repository:

cd %HOMEPATH%

git clone https://github.com/Doc1996/object-localization

Step 2.  Create the virtual environment and install dependencies:

cd %HOMEPATH%\object-localization

python -m pip install --upgrade pip
python -m pip install --user virtualenv

python -m venv python-virtual-environment
.\python-virtual-environment\Scripts\activate

.\WINDOWS_INSTALLING_PACKAGES.bat

Step 3.  Modify the changeable variables in OL_constants.py

Step 4.  Run the program:

cd %HOMEPATH%\object-localization

.\python-virtual-environment\Scripts\activate

.\WINDOWS_OBJECT_LOCALIZATION_APPLICATION.bat

Run the project on Linux

Step 1.  Clone the repository:

cd $HOME

git clone https://github.com/Doc1996/object-localization

Step 2.  Create the virtual environment and install dependencies:

cd $HOME/object-localization

python3 -m pip install --upgrade pip
python3 -m pip install --user virtualenv

python3 -m venv python-virtual-environment
source python-virtual-environment/bin/activate

source LINUX_INSTALLING_PACKAGES.sh

Step 3.  Modify the changeable variables in OL_constants.py

Step 4.  Run the program:

cd $HOME/object-localization

source python-virtual-environment/bin/activate

source LINUX_OBJECT_LOCALIZATION_APPLICATION.sh