<- back to shop

rc_reason SilhouetteMatch Module

The rc_reason SilhouetteMatch Module detects position and orientation of comparatively flat objects that are positioned on a plane, by matching the scene at hand to a previously taught template.

  • Detection of shallow objects, calculation of their 3D pose
  • Teaching of new objects provided as a service
  • Automatic and flexible detection of the base plane
  • Works with static and robot-mounted sensors
  • On-board data processing: No external hardware required
Categories: ,

Description

The rc_reason SilhouetteMatch Module is an optional software component that can be easily activated on-board any rc_visard and operated through the sensor’s standard interface. It enables the rc_visard to detect comparatively flat objects lying on a planar surface in unmixed scenes. For each object, the 3D position and orientation is determined.

The rc_reason SilhouetteMatch requires a template of the objects that are to be detected. Creation of this template is offered as a service, teaching of the first ten objects being included with the license cost. Users simply upload the CAD model (alternatively: a recording of the object with an rc_visard) and Roboception provides the necessary template.

rc_reason SilhouetteMatch automatically detects the base-plane of the scene at hand, which is then stored on the rc_visard in order to be occluded during the sensing operation. Typical applications include machine tending or emptying load carriers of several (separated) layers of objects.

Depending on scene/ object complexity, and especially when the base plane is detected using the rc_visard’s point cloud, coupling the module with a RandomDot Projector is advisable.


Downloads and Links

rc_visard product documentation: chapter on SilhouetteMatch (html)
rc_reason SilhouetteMatch tutorials (html)
rc_visard complete product documentation (.pdf)
Template request: Request an object template to be created

Additional information

Hardware requirements

Any rc_visard sensor
On-board installation, no additional hardware required
If using plane estimation via point cloud: RandomDot Projector and IOControl Module
Robotic system equipped with grasping device

Depth range (recommendation)

0.2 – 1 m for rc_visard 65
0.5 – 1.5 m for rc_visard 160
For greater depth ranges, please consult with us prior to your purchase.

Grasp computation time

1 to 3 seconds (depending on object and scene)

Capturing mode

One-shot mode

You may also like…