Gazebo | Ignition | Community
Ask Your Question

Revision history [back]

click to hide/show revision 1
initial version

Scene labeling using a depth camera

Is there any way to get a labeling of the scene as seen from a depth camera - a mapping between each pixel of the image and the corresponding object that generated the depth for that pixel as seen via the depth camera? I've tried using the functions:

GetVisualAt(CameraPtr camera, const math::Vector2i &mousePos)

from gazebo::rendering::Scene, but these are too slow for my use (assuming a 640 x 480 image, this takes of the order of hundreds of seconds). I presume that OGRE would have access to this labeling when it renders depth maps, but I'm not too sure how to get access to this. Any suggestions?

Scene labeling using a depth camera

Is there any way to get a labeling of the scene as seen from a depth camera - a mapping between each pixel of the image and the corresponding object that generated the depth for that pixel as seen via the depth camera? I've tried using the functions:

GetVisualAt(CameraPtr camera, const math::Vector2i &mousePos)

from gazebo::rendering::Scene, but these are too slow for my use (assuming a 640 x 480 image, this takes of the order of hundreds of seconds). I presume that OGRE would have access to this labeling when it renders depth maps, but I'm not too sure how to get access to this. Any suggestions?

Scene labeling using from OGRE with a depth camera

Is there any way to get a labeling of the scene as seen from a depth camera - a mapping between each pixel of the image and the corresponding object that generated the depth for that pixel as seen via from the depth camera? camera's viewpoint? So, for a scene with a single table in the middle, all the pixels corresponding to the table have to be labelled as "table". I've tried using the functions:function:

GetVisualAt(CameraPtr camera, const math::Vector2i &mousePos)

from gazebo::rendering::Scene, gazebo::rendering::Scene which casts a ray into the scene to find the intersecting object for a pixel but these are this is too slow for my use case (assuming a 640 x 480 image, this takes of the order of hundreds of seconds). I presume think that OGRE would have access to compute this labeling when it renders depth maps, but I'm not too sure how or where to look to get access to this. Any suggestions?