Difference between revisions of "Objects recognition and position calculation (webcam)"
From robotica.unileon.es
(→Utilization of new OpenCV library in ROS Elecric) |
(→Utilization of a new OpenCV library in ROS Electric) |
||
Line 17: | Line 17: | ||
===Utilization of a new OpenCV library in ROS Electric=== | ===Utilization of a new OpenCV library in ROS Electric=== | ||
− | The previous ''package'' needs the [http://opencv.org/ OpenCV] version 2.4.3 or higher, but [http://wiki.ros.org/ ROS] Electric has | + | The previous ''package'' needs in order to compile the [http://opencv.org/ OpenCV] version 2.4.3 or higher, but [http://wiki.ros.org/ ROS] Electric has the [http://opencv.org/ OpenCV] version 2.3.1. We will |
<!-- | <!-- |
Revision as of 16:30, 30 December 2013
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.
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 library 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