Giter Site home page Giter Site logo

torrvision / collaborativeslamdataset Goto Github PK

View Code? Open in Web Editor NEW
42.0 42.0 10.0 340 KB

The dataset associated with our ISMAR 2018 paper on Collaborative SLAM.

Home Page: http://www.robots.ox.ac.uk/~tvg/projects/CollaborativeSLAM

Shell 100.00%

collaborativeslamdataset's People

Contributors

sgolodetz avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

collaborativeslamdataset's Issues

Some data format issues

Hi there,

Firstly, good work! I am interested in using your dataset in my research. However, after downloading and playing with the dataset for a while, I found it difficult to extract some camera parameters. I would appreciate it if you could instruct me a little bit.

Q1: Where can I find the camera calibration matrix K (or intrinsics)? I checked the "calib.txt" and could not find it. The third block seems to be some calibration between a stereo camera rig while I can not understand the first two blocks...

"calib.txt"

480 270
370.044 369.501
241.249 134.663

224 172
215.965 215.965
111.453 85.0044

0.999952 -0.009273 0.00302 0.000992
0.009273 0.999957 -0.000258 -0.011901
-0.003018 0.000286 0.999995 0.002581

affine 0.001 0

Q2:
In "frame-xxxx-pose.txt", is it true that the 4*4 transformation matrix takes as input a point in camera coordinate system and transform it into a point in world coordinate system, or is it the other way around?

"frame-xxxx-pose.txt"

-0.733823 -0.13459 0.665874 -0.354835
0.0155285 0.976599 0.214508 -0.211572
-0.679163 0.167751 -0.714561 0.049265
0 -0 -0 1

Many thanks in advance.

Best Regards

How can I get the frame poses and global poses?

I noticed that both the reconstruct-global.sh and reconstruct-collaborative.sh read the pose for every frame from disk, by specifying the -t Disk argument. But how can I get these poses, e.g., for a new sequence? When I try to remove the -t Disk argument and instead use -t InfiniTAM tracker, the tracking was immediately lost after a few frames. I also have confusions on how do I get the global_poses.txt for a new dataset. Any advice on how I can reproduce the results or start from a new sequence?

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.