Quantcast

[Discourse.ros.org] [Computer Vision / Perception] New Computer Vision Message Standards

classic Classic list List threaded Threaded
25 messages Options
12
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

[Discourse.ros.org] [Computer Vision / Perception] Proposal - New Computer Vision Message Standards

Procópio Stein via ros-users


First off: Thanks for this proposal! A standardized set of vision messages has been sorely missing for years.

Regarding [Detection3D](https://github.com/Kukanani/vision_msgs_proposal/blob/28acc935ddf6ef887fd5b3f5999cd7e14e8ee7e8/msg/Detection3D.msg):

I strongly believe we need a separate Pose for each object hypothesis. For example, when meshes are used to represent the object classes, the Pose specifies the pose of the mesh's reference frame in the `Detection3D.header.frame_id` frame. For example, the reference frame of the following mesh is at the bottom of the mug and in the center of the mug's round part, not at the center of the mesh's bounding box:

<img src="/uploads/ros/original/1X/f102dd3bd238347f63c920557e3baa161ee6da6e.png" width="500" height="500">

Without a Pose for each object class, we cannot express "this object could be either a laptop in its usual orientation, or a book lying flat (i.e., rotated by 90 if your mesh is of a book standing upright)".

My proposal would be to either include an array of Poses in a 3D-specific `CategoryDistribution` message, or (since we now have 3 arrays that must be the same size) as an array of `ObjectHypothesis` messages (or whatever we want to call it) that would have one `id`, `score` and `Pose` each.

--------------------------------------------------

I was also sorry to see that [BoundingBox3D](https://github.com/Kukanani/vision_msgs_proposal/blob/2a1682f322dc08bcaf268d0833dd1fc4758aedaf/msg/BoundingBox3D.msg) was removed. (This was meant to represent a bounding box of the points in `source_cloud`, right?) I've always included this in my own message definitions, and I've found it extremely useful.

On the other hand, this information can be re-computed from the `source_cloud`, so I can live with that (although it's a bit wasteful). Also, other people might prefer to use a `shape_msgs/Mesh bounding_mesh`, like in [object_recognition_msgs/RecognizedObject](https://github.com/wg-perception/object_recognition_msgs/blob/d55acd8aa14fac162e19573ccce6a266b4df23c2/msg/RecognizedObject.msg#L25-L27), or something completely different, and it would overcomplicate the message if we'd include all possible kinds of extra information.





---
[Visit Topic](https://discourse.ros.org/t/proposal-new-computer-vision-message-standards/1819/21) or reply to this email to respond.


If you do not want to receive messages from ros-users please use the unsubscribe link below. If you use the one above, you will stop all of ros-users from receiving updates.
______________________________________________________________________________
ros-users mailing list
[hidden email]
http://lists.ros.org/mailman/listinfo/ros-users
Unsubscribe: <http://lists.ros.org/mailman//options/ros-users>
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

[Discourse.ros.org] [Computer Vision / Perception] Proposal - New Computer Vision Message Standards

Procópio Stein via ros-users
In reply to this post by Procópio Stein via ros-users


You're right, when you have a CategoryDistribution, it is likely to change per pixel.

For most applications I've seen, a single label per pixel is fine. So then:

    string[] results
    sensor_msgs/Image mask





---
[Visit Topic](https://discourse.ros.org/t/proposal-new-computer-vision-message-standards/1819/22) or reply to this email to respond.


If you do not want to receive messages from ros-users please use the unsubscribe link below. If you use the one above, you will stop all of ros-users from receiving updates.
______________________________________________________________________________
ros-users mailing list
[hidden email]
http://lists.ros.org/mailman/listinfo/ros-users
Unsubscribe: <http://lists.ros.org/mailman//options/ros-users>
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

[Discourse.ros.org] [Computer Vision / Perception] Proposal - New Computer Vision Message Standards

Procópio Stein via ros-users
In reply to this post by Procópio Stein via ros-users


what do you think about unifying the BoundingBox2D.msg
<https://github.com/Kukanani/vision_msgs_proposal/blob/master/msg/BoundingBox2D.msg>
 and BoundingBox3D.msg
<https://github.com/Kukanani/vision_msgs_proposal/blob/master/msg/BoundingBox3D.msg>
 messages?
we could have the three fields (or vector) to the bounding box size and, in
the case it is a 2d bounding box, the Z field would be zero. I think we
would gain in simplicity, in a similar way we have a pose message
(geometry_msgs/Pose) that is generic and serves both 2d and 3d poses,
according to what is set in Z.





---
[Visit Topic](https://discourse.ros.org/t/proposal-new-computer-vision-message-standards/1819/23) or reply to this email to respond.


If you do not want to receive messages from ros-users please use the unsubscribe link below. If you use the one above, you will stop all of ros-users from receiving updates.
______________________________________________________________________________
ros-users mailing list
[hidden email]
http://lists.ros.org/mailman/listinfo/ros-users
Unsubscribe: <http://lists.ros.org/mailman//options/ros-users>
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

[Discourse.ros.org] [Computer Vision / Perception] Proposal - New Computer Vision Message Standards

Procópio Stein via ros-users
In reply to this post by Procópio Stein via ros-users


something like this, for both 2d and 3d bounding boxes:

    # position and rotation of the bounding box
    geometry_msgs/Pose pose

    # size of the bounding box
    geometry_msgs/Point size





---
[Visit Topic](https://discourse.ros.org/t/proposal-new-computer-vision-message-standards/1819/24) or reply to this email to respond.


If you do not want to receive messages from ros-users please use the unsubscribe link below. If you use the one above, you will stop all of ros-users from receiving updates.
______________________________________________________________________________
ros-users mailing list
[hidden email]
http://lists.ros.org/mailman/listinfo/ros-users
Unsubscribe: <http://lists.ros.org/mailman//options/ros-users>
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

[Discourse.ros.org] [Computer Vision / Perception] Proposal - New Computer Vision Message Standards

Procópio Stein via ros-users
In reply to this post by Procópio Stein via ros-users


In case somebody is still following this thread: The discussion seems to have moved to the [GitHub repository](https://github.com/Kukanani/vision_msgs_proposal/). I've just discovered that my proposed changes were silently accepted! :tada:





---
[Visit Topic](https://discourse.ros.org/t/proposal-new-computer-vision-message-standards/1819/25) or reply to this email to respond.


If you do not want to receive messages from ros-users please use the unsubscribe link below. If you use the one above, you will stop all of ros-users from receiving updates.
______________________________________________________________________________
ros-users mailing list
[hidden email]
http://lists.ros.org/mailman/listinfo/ros-users
Unsubscribe: <http://lists.ros.org/mailman//options/ros-users>
12
Loading...