fabianschenk / revo Goto Github PK
View Code? Open in Web Editor NEWRobust Edge-based Visual Odometry (REVO)
Robust Edge-based Visual Odometry (REVO)
When the data set of more than 1500 frames was used to verify the algorithm, it was found that it could not fully map all scenes of the data set. Is there a buffer mechanism that makes the algorithm stop drawing after exceeding a certain limit value? Please give me some suggestions, thank you !
Hi,
I just wanted to reproduce the results with TUM dataset, but I saw the error "Could not open file list". It seems like I need to make "associate.txt" somehow. Any advice would be appreciated.
Thanks,
Yutaka
Hi,
I have one question about Orbbec Astra sensor.
Can I use Orbbec Astra? Is it for Pro version only for now?
If we use only VGA, it seems like we can use both.
Thanks,
Yutaka
Hi, I just found out about REVO from my GitHub notifications. It's nice to see more RGB-D visual odometry algorithms open sourced out there!
Best regards,
Matthieu
I downloaded some dataset from TUM dataset provided by you and tried to run it.
(1) Should there be a 'INPUT_TYPE:=0' in the settings.yaml file? It seems that I should specify the INPUT_TYPE in advance.
(2) I got nothing when run "build/REVO config/revo_settings.yaml config/dataset_tum1.yaml". If I switch it to "build/REVO config/dataset_tum1.yaml config/revo_settings.yaml", I can get a gui window with no result. But I fixed it after combining the contents of revo_settings.yaml and dataset_tum1.yaml. Why did that happen?
(3) The TUM dataset is based on Kinnect. What kind of RGBD sensor does the parameters in settings yaml file correspond to?
Thank you very much!
This error occurs when I run REVO on my own data set:
Sophus ensure failed in function 'static Sophus::SO3<Scalar_> Sophus::SO3<Scalar_, Options>::expAndTheta(const Tangent&, Sophus::SO3<Scalar_, Options>::Scalar*) [with Scalar_ = float; int Options = 0; Sophus::SO3<Scalar_, Options>::Tangent = Eigen::Matrix<float, 3, 1>; Sophus::SO3<Scalar_, Options>::Scalar = float]', file '/home/one/REVO-fabian/thirdparty/Sophus/sophus/so3.hpp', line 563.
SO3::exp failed! omega: -nan -nan 0, real: -nan, img: -nan
Aborted (core dumped)
In this regard, I have made some attempts, such as changing camera internal parameters, Canny threshold value and resolution, but none of them had any effect. Could you please give me some suggestions
Thank for your excellent work. I encountered an error when use camke.. ,enven through I installed ffmpeg.
c@cc-K55VD:~/code/REVO-master/build$ cmake ..
cmake: /home/cc/code/REVO-master/ThirdParty/libuvc/build/CMakeFiles
-- The compiler /usr/bin/c++ has C++11 support. Please use a different C++ compiler.
CMake Error at CMakeLists.txt:100 (include):
include could not find load file:
cmake/external_FFMPEG.cmake
OpenCV: /opt/ros/kinetic/include/opencv-3.3.1-dev;/opt/ros/kinetic/include/opencv-3.3.1-dev/opencv
Eigen found: /usr/include/eigen3
-- Boost version: 1.58.0
-- Found the following Boost libraries:
-- system
-- filesystem
libuvc_LIBRARIES: , pangolin;realsense;/home/cc/code/REVO-master/orbbec_astra_pro/drivers/libOpenNI2.so;opencv_core;opencv_videoio;opencv_imgcodecs;opencv_imgproc;opencv_calib3d;opencv_highgui;/usr/lib/x86_64-linux-gnu/libboost_filesystem.so;/usr/lib/x86_64-linux-gnu/libboost_system.so
-- Configuring incomplete, errors occurred!
See also "/home/cc/code/REVO-master/build/CMakeFiles/CMakeOutput.log".
Can you provide clear dependencies?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.