Welcome
This page explains how to use the Aldebaran vision recognition Module (identifier: ALVisionRecognition). Please refer to the Framework section to get general information on modules.
| Note: | Depending on your package, this module might not be available. |
|---|
The ALVisionRecognition module is a vision module in which NAO tries to recognize different pictures, objects sides or even locations learned previously.
| Note: | This module is based on the recognition of patterns and not on the shape of the objects, so it can recognize objects instances but not objects classes. |
|---|
The learning process is currently requesting a computer running Choregraphe, and you will find details on how to use the Choregraphe's Video monitor in the Choregraphe documentation. With few minutes experience, nao should be able to learn any new thing in less than 30s.
The recognition process is partially robust to distance (up to half and twice the distance used for learning), angle (up to 50° inclination when for something learned facing the camera), light conditions and rotation. In addition, learned objects can be partially hidden for the recognition stage.
The next section contains some notes to remind you basics about vision modules, category that vision recognition belongs to. Then you will get details on the returned values. Finally examples for using this module are available in the Tutorial section.