Quantcast

Working object detection and recognition code

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

Working object detection and recognition code

dlmypr
Hi all,

I use tod_training and tod_detecting for object recognition. It works pretty well but the output of the program is just an image showing the estimated pose and the name of the recognized object. How can I get this output of estimated pose like as a matrix but not just the image?

Also does any one knows any other working! object detection or recognition code?

Thanks..
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Working object detection and recognition code

Matei Ciocarlie
Hi,

The package tabletop_object_detector is extremely limited, and
hopefully soon to be replace by TOD and other detectors, but it's what
we've been using for the past year.

http://www.ros.org/wiki/tabletop_object_detector

Matei

On Thu, Feb 17, 2011 at 3:20 PM, dlmypr <[hidden email]> wrote:

>
> Hi all,
>
> I use tod_training and tod_detecting for object recognition. It works pretty
> well but the output of the program is just an image showing the estimated
> pose and the name of the recognized object. How can I get this output of
> estimated pose like as a matrix but not just the image?
>
> Also does any one knows any other working! object detection or recognition
> code?
>
> Thanks..
> --
> View this message in context: http://ros-users.122217.n3.nabble.com/Working-object-detection-and-recognition-code-tp2523250p2523250.html
> Sent from the ROS-Users mailing list archive at Nabble.com.
> _______________________________________________
> ros-users mailing list
> [hidden email]
> https://code.ros.org/mailman/listinfo/ros-users
>



--
Matei Ciocarlie
Research Scientist
Willow Garage Inc.
650-475-9780
_______________________________________________
ros-users mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-users
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Working object detection and recognition code

Dejan Pangercic
Also:
http://www.ros.org/wiki/objects_of_daily_use_finder
D.

On Fri, Feb 18, 2011 at 12:30 AM, Matei Ciocarlie
<[hidden email]> wrote:

> Hi,
>
> The package tabletop_object_detector is extremely limited, and
> hopefully soon to be replace by TOD and other detectors, but it's what
> we've been using for the past year.
>
> http://www.ros.org/wiki/tabletop_object_detector
>
> Matei
>
> On Thu, Feb 17, 2011 at 3:20 PM, dlmypr <[hidden email]> wrote:
>>
>> Hi all,
>>
>> I use tod_training and tod_detecting for object recognition. It works pretty
>> well but the output of the program is just an image showing the estimated
>> pose and the name of the recognized object. How can I get this output of
>> estimated pose like as a matrix but not just the image?
>>
>> Also does any one knows any other working! object detection or recognition
>> code?
>>
>> Thanks..
>> --
>> View this message in context: http://ros-users.122217.n3.nabble.com/Working-object-detection-and-recognition-code-tp2523250p2523250.html
>> Sent from the ROS-Users mailing list archive at Nabble.com.
>> _______________________________________________
>> ros-users mailing list
>> [hidden email]
>> https://code.ros.org/mailman/listinfo/ros-users
>>
>
>
>
> --
> Matei Ciocarlie
> Research Scientist
> Willow Garage Inc.
> 650-475-9780
> _______________________________________________
> ros-users mailing list
> [hidden email]
> https://code.ros.org/mailman/listinfo/ros-users
>



--
MSc. Dejan Pangercic
PhD Student/Researcher
Intelligent Autonomous Systems Group
Technische Universit√§t M√ľnchen
Telephone: +49 (89) 289-26908
E-Mail: [hidden email]
WWW: http://ias.cs.tum.edu/people/pangercic
_______________________________________________
ros-users mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-users
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Working object detection and recognition code

rusu
Administrator
In reply to this post by dlmypr
The code in tod_* is currently undergoing major changes until it will be ready for release. We're doing our best to make
sure that everything fits nicely together in our REIN (Recognition Infrastructure) framework, but we don't have a
concrete deadline for when this will be ready.

Bottom line is: there are quite a few novel methods that we worked on in parallel, some using geometry, some using
texture, that will come together in a nice way in the end. :)

Cheers,
Radu.
--
http://pointclouds.org

On 02/17/2011 03:20 PM, dlmypr wrote:

>
> Hi all,
>
> I use tod_training and tod_detecting for object recognition. It works pretty
> well but the output of the program is just an image showing the estimated
> pose and the name of the recognized object. How can I get this output of
> estimated pose like as a matrix but not just the image?
>
> Also does any one knows any other working! object detection or recognition
> code?
>
> Thanks..
_______________________________________________
ros-users mailing list
[hidden email]
https://code.ros.org/mailman/listinfo/ros-users
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Working object detection and recognition code

dlmypr
Thanks for the replies,

rusu so I am not doing something wrong? The output of the tod_detecting is just images? I can't get the pose numerically instead of the image?
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Working object detection and recognition code

nandhini
hi all,
i'm new to ROS.
my project is to implement object detection in ROS.
I'm stuck now.
can anyone guide me how to start with this project!
Loading...