Difference between revisions of "Objects recognition and position calculation (webcam)"

From robotica.unileon.es
Jump to: navigation, search
(→‎Utilization of a new OpenCV version in ROS Electric)
(→‎Installation of OpenCV)
Line 28: Line 28:
 
</syntaxhighlight>
 
</syntaxhighlight>
  
−
When the update/upgrade finish, we will place in the [http://opencv.org/ OpenCV] folder and execute the next commands in a terminal in order to compile:
+
When finish the update/upgrade, we will place us in the [http://opencv.org/ OpenCV] folder in a terminal and execute the next commands in the terminal in order to compile:
−
 
 
−
<syntaxhighlight enclose="div">
 
−
mkdir build
 
−
cd build
 
−
cmake -D WITH_TBB=ON -D BUILD_NEW_PYTHON_SUPPORT=ON -D WITH_V4L=ON -D INSTALL_C_EXAMPLES=ON -D INSTALL_PYTHON_EXAMPLES=ON -D BUILD_EXAMPLES=ON -D WITH_QT=ON -D WITH_OPENGL=ON ..
 
−
make
 
−
sudo make install
 
−
</syntaxhighlight>
 
−
<!--
 
−
 
 
−
Realizada la actualización vamos a continuar compilando [http://opencv.org/ OpenCV]. Para esto, desde un terminal, vamos a situarnos dentro del directorio "OpenCV-2.4.3", carpeta por defecto al descomprimir el archivo con [http://opencv.org/ OpenCV]. Una vez situados en el directorio que contiene [http://opencv.org/ OpenCV] vamos a ejecutar los siguientes comandos en un terminal:
 
  
 
<syntaxhighlight enclose="div">
 
<syntaxhighlight enclose="div">
Line 49: Line 38:
 
</syntaxhighlight>
 
</syntaxhighlight>
  
−
Solo queda configurar [http://opencv.org/ OpenCV]. Ejecutaremos en un terminal el siguiente comando:
+
We will execute the next command in the terminal in order to configure [http://opencv.org/ OpenCV]:
  
 
<syntaxhighlight>sudo gedit /etc/ld.so.conf.d/opencv.conf</syntaxhighlight>
 
<syntaxhighlight>sudo gedit /etc/ld.so.conf.d/opencv.conf</syntaxhighlight>
  
−
Añadimos la siguiente línea de código al archivo que hemos abierto y guardamos los cambios:
+
We add the next code line to the opened file and save the changes:
  
 
<syntaxhighlight>/usr/local/lib</syntaxhighlight>
 
<syntaxhighlight>/usr/local/lib</syntaxhighlight>
  
−
Ahora ejecutamos en un terminal los siguientes comandos:
+
Now, we will execute the next commands in a terminal:
  
 
<syntaxhighlight>
 
<syntaxhighlight>
Line 64: Line 53:
 
</syntaxhighlight>
 
</syntaxhighlight>
  
−
En el archivo que hemos abierto añadimos las siguientes líneas al final y guardamos los cambios:
+
We add the next code lines at the end of the opened file and save the changes:
  
 
<syntaxhighlight>
 
<syntaxhighlight>
Line 71: Line 60:
 
</syntaxhighlight>
 
</syntaxhighlight>
  
−
Para finalizar la instalación vamos a reiniciar el equipo.
+
We will restart the PC to finish the installation.
 +
 
 +
====Modification of the package cv_bridge====
 +
 
 +
<!--
 +
 
  
 
====Modificación de cv_bridge====
 
====Modificación de cv_bridge====

Revision as of 17:21, 30 December 2013

< go back to main

Objects recognition

We have used the package find_object_2d which has been develop by Mathieu Labbé (Université de Sherbrooke). The program can recognizes objects in the scene using an image of the object. The program has a graphical user interface which allow to capture an image of the scene and save it.

Screenshot find_object_2d

In the screenshot that is shown above, we can see how the recognized object is within a boundary box which coincide with the corners of the object image.

The program provides several data of each found object in the scene. We will use the next data:

  • Width of the object image (number of pixels).
  • Height of the object image (number of pixels).
  • Position of the corners of the object image in the scene.

Utilization of a new OpenCV version in ROS Electric

The previous package needs in order to compile the OpenCV version 2.4.3 or higher, but ROS Electric has the OpenCV version 2.3.1. We will install the OpenCV version 2.4.3, modify the package cv_bridge and modify the package find_object_2d.

Installation of OpenCV

First we will download the OpenCV version 2.4.3 by the official web. We will extract the content of the downloaded file in the personal folder. We will execute the next commands in a terminal in order to update the ubuntu packages: 

sudo apt-get update
sudo apt-get upgrade

When finish the update/upgrade, we will place us in the OpenCV folder in a terminal and execute the next commands in the terminal in order to compile: 

mkdir build
cd build
cmake -D WITH_TBB=ON -D BUILD_NEW_PYTHON_SUPPORT=ON -D WITH_V4L=ON -D INSTALL_C_EXAMPLES=ON -D INSTALL_PYTHON_EXAMPLES=ON -D BUILD_EXAMPLES=ON -D WITH_QT=ON -D WITH_OPENGL=ON ..
make
sudo make install

We will execute the next command in the terminal in order to configure OpenCV: 

sudo gedit /etc/ld.so.conf.d/opencv.conf

We add the next code line to the opened file and save the changes: 

/usr/local/lib

Now, we will execute the next commands in a terminal: 

sudo ldconfig
sudo gedit /etc/bash.bashrc

We add the next code lines at the end of the opened file and save the changes: 

PKG_CONFIG_PATH=$PKG_CONFIG_PATH:/usr/local/lib/pkgconfig
export PKG_CONFIG_PATH

We will restart the PC to finish the installation.

Modification of the package cv_bridge

< go back to main

Retrieved from "https://robotica.unileon.es/index.php?title=Objects_recognition_and_position_calculation_(webcam)&oldid=2782"