tn0432's profile - activity

I have 2 cameras looking at an object, estimating the transformation between two camera images using OpenCV feature matching. I have ROS driver for 2 cameras (gscam). When receiving new image topic (/driver/image_raw), image_call_back() function is called to processing the image:

Step 1: CV.bridge to transfer the ROS image to OpenCV image

Step 2: Transfer to grayscale image

Step 3: Remove distortion effect

Step 4: Histogram equalization to eliminate light effect.

Step 5: Feature detection, matching and estimate transformation

When trying with two images, my transformation algorithm is fine and stable. But when I try with the static cameras (2 sequence images streaming and 2 cameras do not move), my transformation algorithm gives unstable result. I guess it is due to the effect of video stream noise. Have you tried it before and do you have any way to eliminate noise in video stream.

Thanks

I want to use some functions in sfm (structure from motion), an extra module, in opencv3 library. So, I install opencv3 going with indigo. However, the library does not have sfm. But, I test with another extra module such as bgsegm. It is fine!

Have anyone tried using sfm module? Is there any way to use sfm module with python?

Thanks

If I have two frames: /parent and /child. I can use tf:lookuptransform to find the transformation between two frames. Now, I want to find the azimuth and elevation angles in spherical coordinate between two frames. Do ROS have any available function to do something like that?

Thanks

Hi! Let us know what kind of simulation and packages are you using? The changes in y -coordinate may be from the noise. Some simulation includes noise which makes vehicle moves although you do not command.

Hi!

I just have a question when writing the ROS wiki page for my package. If I modify package.xml file (such as add author, change maintainer, ...), the ROS wiki page will automatically update or I need to do something else?

Thanks

For my case when starting to learn image processing with ROS, I use gscam package to get image from camera. CV Bridge package to transfer from ROS standard image to OpenCV standard image. When you image is presented at OpenCV standard, you are able to use available functions in OpenCV for image processing.

Good luck!

My robot is quadrotor. PID is good enough. Actually, I want to find out the best way to provide the desired trajectory and desired position? Or other anyway to provide desired trajectory in ROS?

Hello! I am studying the problem of robot tracking a desired trajectory. I have designed my implementation as following description:

I have my robot frame, \robot_frame, and desired position frame, \goal. I write a ROS node to make the \goal run on a desired trajectory. I use tf to calculate the position errors (i.e. transforms between \goal and \robot_frame). By minimizing the position errors, the robot can track the desired trajectory.

However, when the robot bypass the desired position (overshoot), it will try to turn back because my \goal frame runs slowly on the desired trajectory. It will make my robot unstable. I can improve my position controller for better performance but it is not good way to go.

Does anyone have any idea how to eliminate the turning back?

Thanks

hi! Not that one. I put in indigo 4 days ago https://github.com/tn0432/rosdistro/c... , but still not find out in ROS build server. Let I try again! hope it work

Hello! I have uploaded my project with Indigo to github and made a pull request. Do you know when document job is scheduled in order to do wiki indexing? Thanks

Sorry! Here is the link: http://wiki.ros.org/rosdistro/Tutoria...

Actually, I have made a ROS fuerte package. I am trying to upload to ROS wiki. Is the link the best way to follow? Thanks! I very appreciate your help.

Hi! I make a package on ROS Fuerte and want to upload the package on ROS Wiki. I follow steps in tutorial until the step "Verify your changes before commiting the changes". How can I do that with ros fuerte? I can not find out the distribution.yaml file

Thanks

Hello,

I need to measure the complexity of my algorithm. The algorithm is developed to run in ROS node. How do we measure the space of the running ROS node taken?

Thanks

In my experience, it depends on how much you want to achieve. The key point is at simulation step. If you only try with simple dynamic model of the system (few equations), Matlab is prefered. If you want to try advanced simulation (Gazebo, V-Rep) with many complicationted robots and sensors, ROS is prefered. I do not say we can not do the same thing with Matlab but it will take more time and efforts. Remember that, ROS is produced after Matlab. It means that the inventors in the early day had seen some problems with Matlab.

Hello,

I am trying to use PID for position control of ardrone. I use ardrone_autonomy as a package to connect with Ardrone and send /cmd_vel. The values of /cmd_vel are calculated by PID controlling. The feedback Ardrone current positions are gotten from Motion Capture System. I am struggling at tuning PID parameters. Does anyone try it before?

My PID tunning, Ardrone can fly to /goal frame but still too osscilation and overshoot. My PID x,y is Kp_0.15, Ki_0.0, Kd_0.05. My target is that the position errors is about <20 cm. Is my target realistic with Ardrone? Any suggestion?

Thank you very much! I very appreciate.