ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | ros @ Robotics Stack Exchange
Ask Your Question

Jia's profile - activity

2015-05-28 22:10:26 -0500 received badge  Notable Question (source)
2015-05-28 22:10:26 -0500 received badge  Famous Question (source)
2013-11-04 06:08:36 -0500 received badge  Famous Question (source)
2013-07-30 12:14:10 -0500 received badge  Famous Question (source)
2013-07-17 22:33:50 -0500 received badge  Notable Question (source)
2013-07-10 19:18:20 -0500 received badge  Notable Question (source)
2013-07-09 22:28:51 -0500 received badge  Popular Question (source)
2013-07-02 05:26:46 -0500 received badge  Popular Question (source)
2013-06-25 05:47:00 -0500 asked a question libviso2 stereo result doesn't match mono result

I don't know what exactly the height and pitch are for mono demo dataset "2010_03_09_drive_0019", but I tried tens of pairs like pitch from +0.08 to -0.08, height from 0.57 to 1.57. The results look similar but they just can not match at the same end. They match fine at the beginning, but the mono results seem very inaccurate whenever it comes to a rotation.

BTW my goal is to estimate the speed from image. I only have one camera, any suggestion?

2013-06-20 13:26:16 -0500 received badge  Popular Question (source)
2013-06-17 10:45:16 -0500 commented question Warning about TF to MSG

sry, I did paste the warning but it didn't show. Now it should be fine.

2013-06-17 10:04:48 -0500 received badge  Editor (source)
2013-06-17 10:03:11 -0500 asked a question Warning about TF to MSG

When I run viso2 mono_odometer I get warnings like

TF to MSG: Quaternion Not Properly Normalized.

I find no translation happens when I move the camera tf are all zeros. Is that because of this warning, which prevent the node to publish tf to odom itself?

2013-06-17 09:54:29 -0500 commented answer viso2 mono_odometer data problem

Another thing is, in the tutorial, the frame relationships are world -> odom -> link_base -> camera, but I don't specify the world frame. Is that ok? And I use tf_echo, I found there is no transformation between any frame and odom has no parent frame. Any suggestion about that?

2013-06-17 09:29:44 -0500 commented answer viso2 mono_odometer data problem

I print out the numbers of matches in source code. They look fine. I tried translational movement, but just like I said, the position is around zero and the data is more like noise. And my goal is actually get the velocity of the camera. I just tried PTAM, and I have trouble to calibrate with it

2013-06-17 07:53:05 -0500 commented answer viso2 mono_odometer data problem

Yeah, I read the limitations. I am expecting it gives me some results but not just zeros. Even if it has the limitations, it can still detect some matches. I checked the number of matches, there are enough detected points. Do I miss any step?

2013-06-16 10:24:31 -0500 asked a question viso2 mono_odometer data problem

I am using viso2 mono_odometer. I am sure packages are working good because I check rxgraph and topics are linked properly. The problem is the position data in mono_odometer is always around zero like something to e-300, no matter how I move my computer. BTW, I am testing with my integrated camera of my laptop using gscam. Thank you in advance if anyone has any idea.