Git Product home page Git Product logo

Comments (18)

weblucas avatar weblucas commented on June 17, 2024

Test another fork with a indigo-devel branch. I am using srv( https://github.com/srv/ORB_SLAM.git
) repository and it is working well.

from orb_slam.

NilsL3 avatar NilsL3 commented on June 17, 2024

Thanks a lot for the help. I am currently trying this fork and I have bumped into a problem when launching the orb_slam.launch file. I obtain the following in the terminal:

Vocabulary loaded!

Camera Parameters:

  • fps: 30
  • color order: RGB (ignored if grayscale)
  • Images are rectified: No
  • camera: MONO

ORB Extractor Parameters:

  • Number of Features: 1000
  • Scale Levels: 8
  • Scale Factor: 1.2
  • Fast Threshold: 20
  • Score: FAST

However, the window titled "/image", which appears when running the launch file is grey and the RViz opens and mentions the following warning:

Global Status: Warn
Fixed Frame
No tf data. Actual error: Fixed Frame [ORB_SLAM/Camera] does not exist

I suppose I can't get it work because I didn't edit the launch file correctly. I was not sure where to insert the topic I was receiving the raw video stream from. Could you please tell me where in the launch file I should insert the topic I am subscribing to in order to receive the raw video stream? I would appreciate it a lot if you could tell me what I am doing wrong based on the error information above or if I should launch orb_slam differently.

from orb_slam.

weblucas avatar weblucas commented on June 17, 2024

I suggest you start first with the example sequence from the readme. With
this sequence you can use the launch file bellow. and play the "rosbag play
Example.bag"


When you manage to run with this. Next step is to try your own data

you basically need two things. Calibration parameters in the Opencv
fashion. (use the ros calibrator - http://wiki.ros.org/camera_calibration).
These parameters go in the file (Data/Settings.yaml)
the second thing is remap to the input of your camera.
you need to uncomment the line and change the parameter "to" with your input address. The
Example.bag publish its image already with the name expected by the
ORB-SLAM. this is why to run the example the remap is commented.

Good Luck

On 14 July 2015 at 22:29, NilsL3 [email protected] wrote:

Thanks a lot for the help. I am currently trying this fork and I have
bumped into a problem when launching the orb_slam.launch file. I obtain the
following in the terminal:

Vocabulary loaded!

Camera Parameters:

  • fps: 30
  • color order: RGB (ignored if grayscale)
  • Images are rectified: No
  • camera: MONO

ORB Extractor Parameters:

  • Number of Features: 1000
  • Scale Levels: 8
  • Scale Factor: 1.2
  • Fast Threshold: 20
  • Score: FAST

However, the window titled "/image", which appears when running the launch
file is grey and the RViz opens and mentions the following warning:

Global Status: Warn
Fixed Frame
No tf data. Actual error: Fixed Frame [ORB_SLAM/Camera] does not exist

I suppose I can't get it work because I didn't edit the launch file
correctly. I was not sure where to insert the topic I was receiving the raw
video stream from. Could you please tell me where in the launch file I
should insert the topic I am subscribing to in order to receive the raw
video stream? I would appreciate it a lot if you could tell me what I am
doing wrong based on the error information above or if I should launch
orb_slam differently.


Reply to this email directly or view it on GitHub
#45 (comment).

from orb_slam.

NilsL3 avatar NilsL3 commented on June 17, 2024

Thanks a lot for the detailed explanation. I'll keep you up to date on how I'm doing.

from orb_slam.

NilsL3 avatar NilsL3 commented on June 17, 2024

I have tried executing orb_slam with the provided dataset, but I still have had no success. I followed your instructions, I made the according modifications to the launch file and then I used "roslaunch" to execute the launch file. And then I used "rosbag play" to play the dataset, but the image view window now titled "ORB_SLAM/Frame" is black and in the bottom corner a text mentions the following: "WAITING FOR IMAGES. (Topic: /camera/image_raw)".

The Rviz window is blank and I still have the following error:
Global Status: Warn
Fixed Frame
No tf data. Actual error: Fixed Frame [ORB_SLAM/Camera] does not exist

When playing the dataset sequence, there are no changes neither in the image view window nor Rviz.

from orb_slam.

weblucas avatar weblucas commented on June 17, 2024

Use the rqt application to double check that your bag is playing and see
the name of the topic
On 15 Jul 2015 18:54, "NilsL3" [email protected] wrote:

I have tried executing orb_slam with the provided dataset, but I still
have had no success. I followed your instructions, I made the according
modifications to the launch file and then I used "roslaunch" to execute the
launch file. And then I used "rosbag play" to play the dataset, but the
image view window now titled "ORB_SLAM/Frame" is black and in the bottom
corner a text mentions the following: "WAITING FOR IMAGES. (Topic:
/camera/image_raw)".

The Rviz window is blank and I still have the following error:
Global Status: Warn
Fixed Frame
No tf data. Actual error: Fixed Frame [ORB_SLAM/Camera] does not exist

When playing the dataset sequence, there are no changes neither in the
image view window nor Rviz.


Reply to this email directly or view it on GitHub
#45 (comment).

from orb_slam.

NilsL3 avatar NilsL3 commented on June 17, 2024

I have used the rqt application and I can view the dataset sequence on the "/camera/image_raw" topic, however the "ORB_SLAM/Frame" image view window remains black and in the bottom corner of this window a message announces the following "WAITING FOR IMAGES. (Topic: /camera/image_raw)".

from orb_slam.

NilsL3 avatar NilsL3 commented on June 17, 2024

I tried a different fork and I got orb_slam to work with the dataset sequence. Thanks a lot for the help.

from orb_slam.

weblucas avatar weblucas commented on June 17, 2024

No problem.

from orb_slam.

mihaibujanca avatar mihaibujanca commented on June 17, 2024

I am having similar problems. Camera is working on camera/image_raw and I can view ORB_SLAM/Frame using image_view, but I am still getting No tf data. Actual error: Fixed Frame [ORB_SLAM/Camera] does not exist with rviz.

from orb_slam.

pvmilk avatar pvmilk commented on June 17, 2024

Just incase anyone encounter the same issue.

Make sure the lunch file (ExampleGroovyOrNewer.launch) load the type 'orb_slam' not 'ORB_SLAM'

There will be a few more errors regarding the libraries of the Thirdparty.
Simply add the path to your LD_LIBRARY_PATH.

from orb_slam.

weblucas avatar weblucas commented on June 17, 2024

Hi Pierre,

To fix this error you have to change in the Global Options-> Fixed Frame to
another option on the combo box while you are running the ORB-SLAM.

Best

Lucas

On 1 November 2015 at 13:41, Pierre Moulon [email protected] wrote:

@weblucas https://github.com/weblucas,
I cannot connect my webcam. I have also the message "No tf data. Actual
error: Fixed Frame [ORB_SLAM/Camera] does not exist" in rviz.
@mihaibujanca https://github.com/mihaibujanca -> Do you have found the
solution to your problem?

here my Launcher.

<node pkg="rviz" type="rviz" name="rviz" args="-d $(find ORB_SLAM)/Data/rviz.rviz" output="log">
<node pkg="ORB_SLAM" type="ORB_SLAM" name="ORB_SLAM"  args="Data/ORBvoc.txt Data/Settings.yaml" cwd="node" output="screen">
<remap from="/camera/image_raw" to="/usb_cam/image_raw" />


Reply to this email directly or view it on GitHub
#45 (comment).

from orb_slam.

mhzaki avatar mhzaki commented on June 17, 2024

Hello,
hey @NilsL3 can you give me the fork which it works for you.? because i still have the same problem than you ..
thank you.

from orb_slam.

NilsL3 avatar NilsL3 commented on June 17, 2024

Hello mhzaki,

The fork which worked for me is the following: bmagyar/ORB_SLAM
I hope it helps.

from orb_slam.

mhzaki avatar mhzaki commented on June 17, 2024

hello @NilsL3
I this fork but i still have the same problem i don't know, I am using ros hydro on ubuntu 12.04.
Did you cactinized it or use the way described in the readme file ?

from orb_slam.

NilsL3 avatar NilsL3 commented on June 17, 2024

Hi @mhzaki
I used this fork with Ubuntu 14.04, ROS Indigo, and I used it just as it is described in the readme file.

from orb_slam.

KathiravanNatarajan avatar KathiravanNatarajan commented on June 17, 2024

@NilsL3 how is it exactly working ? I have done the setups mentioned in the README.md file.

can you explain briefly about your observation ??

from orb_slam.

KathiravanNatarajan avatar KathiravanNatarajan commented on June 17, 2024

@weblucas : Hi..I have done with the setups mentioned. what is the vocab file ? I couldn't understand certain things..you seemed to have good knowledge on it. Could you explain the complete process ? I am ready with the setups

from orb_slam.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.