Revision as of 13:33, 29 July 2009

Modules

This is the general architecture currently under development

(updated 28/07/09)

The interface between modules is under development. The current version (subject to changes as we refine it) is as follows:

We should add some kind of context to the on command (imitation or learning being the very basic).

blobDescriptor -> query
- Affordance descriptor. Same format as camshiftplus
- tracker init data. histogram (could be different from affordance) + saturation + intensity

@@ Line 18: / Line 18: @@
 * Query to Effect Detector. The main objective of this port is to start the tracker at the object of interest. We need to send at least:
+** position (x,y) within the image. 2 doubles.
+** size (h,w). 2 doubles.
+** color histogram. TBD.
+** saturation parameters (max min). 2 int.
+** intenity (max min). 2 int.
-** position (x,y) within the image
-** size (h,w)
-** color histogrambs
-** saturation parameters
-*
+* blobDescriptor -> query
+** Affordance descriptor. Same format as camshiftplus
+** tracker init data. histogram (could be different from affordance) + saturation + intensity
+* query -> object segmentation
-  ok &= port_behavior_out.open("/demoAffv2/behavior:o");
+** vocab message: "do seg"
- ok &= port_eff.open("/demoAffv2/effect");
+* object segmentation -> blob descriptor
-  ok &= port_sync.open("/demoAffv2/synccamshift");
+** labelled image
-  ok &= port_descriptor.open("/demoAffv2/objsdesc");
+** raw image
-  ok &= port_askobj.open("/demoAffv2/");
-  ok &= port_primitives.open("/demoAffv2/motioncmd");
-  ok &= port_gaze.open("/demoAffv2/gazecmd");
-  ok &= port_output.open("/demoAffv2/out");
-  ok &= port_emotions.open("/demoAffv2/out");