pwn0n / orbslam_mapsave Goto Github PK
View Code? Open in Web Editor NEWORB_SLAM2 with Map Save/Load Function. Without ROS Environment
License: Other
ORB_SLAM2 with Map Save/Load Function. Without ROS Environment
License: Other
Hi, and thank you for making this code available! The save function is working for me, but when I set bReuseMap
to true, I get a crash here:
//System.cc LoadMap
ia >> mpMap;
just after it prints:
{INFO}mspMapPoints size = 471
Do you have any idea why this might be happening?
Thanks!
Hi Thanks for your effort to build map save functionality to ORB SLAM.
I have built it it was working at the beginning but now I am receiving this error when I try to save map
"QObject::~QObject: Timers cannot be stopped from another thread
Segmentation fault (core dumped)"
Do you know how to fix it?
thanks
Hi! Thanks for sharing your code, but can you help with my problem, I got Segmentation fault error on step, when algorithm first time enters to TrackMonocular function in Map Load mode.
I got some warning during map loading, there are:
map point [1585] not found in KF 41
map point [1585] not found in KF 87
refernce KF - 4is not found for mappoint 1052
refernce KF - 11is not found for mappoint 1325
refernce KF - 11is not found for mappoint 1321
refernce KF - 26is not found for mappoint 1689
refernce KF - 26is not found for mappoint 1780
refernce KF - 26is not found for mappoint 1588
refernce KF - 26is not found for mappoint 1677
refernce KF - 26is not found for mappoint 1688
refernce KF - 11is not found for mappoint 1600
refernce KF - 26is not found for mappoint 1659
refernce KF - 26is not found for mappoint 1709
refernce KF - 26is not found for mappoint 1701
refernce KF - 26is not found for mappoint 1810
refernce KF - 26is not found for mappoint 1704
refernce KF - 26is not found for mappoint 1988
refernce KF - 26is not found for mappoint 1907
refernce KF - 30is not found for mappoint 1920
refernce KF - 30is not found for mappoint 2058
refernce KF - 26is not found for mappoint 1806
refernce KF - 30is not found for mappoint 2112
refernce KF - 30is not found for mappoint 2201
refernce KF - 26is not found for mappoint 2250
refernce KF - 30is not found for mappoint 2068
refernce KF - 26is not found for mappoint 1971
refernce KF - 30is not found for mappoint 2121
refernce KF - 30is not found for mappoint 2224
refernce KF - 30is not found for mappoint 2118
refernce KF - 30is not found for mappoint 2288
refernce KF - 26is not found for mappoint 2320
refernce KF - 30is not found for mappoint 2538
refernce KF - 30is not found for mappoint 2872
refernce KF - 45is not found for mappoint 2649
refernce KF - 26is not found for mappoint 2777
refernce KF - 45is not found for mappoint 3183
refernce KF - 26is not found for mappoint 2986
refernce KF - 48is not found for mappoint 3511
refernce KF - 74is not found for mappoint 3687
refernce KF - 48is not found for mappoint 3855
refernce KF - 26is not found for mappoint 5503
refernce KF - 73is not found for mappoint 5650
refernce KF - 48is not found for mappoint 5712
refernce KF - 49is not found for mappoint 5815
refernce KF - 73is not found for mappoint 5927
What can it be?
Thanks!
Thank you for sharing your code。
When i was compiling the code, i found a error . you miss the lib file in Thirdparty/g2o/.
HI~ i'm beginner on ORB_SLAM and i already build the package and it works fine in mono orb_slam.(but without ROS)
here is how i run the orb_slam command.
Can this package run with ros system? i have no clue to change the camera source to some ROS topic, cause i found out there is no ROS folder in Example directory like the pic as below from the origin ORB_SLAM2 directory.
hope someone can give me some suggestion !!
thanks
Hi, thank you again for making this code public. In stereo mode, it all works great. In monocular mode, the initial map is created, (with reuse == 0) and tracking starts, but the system will not make any more points.
The 'matches' counter on the frame window starts high, then drops to zero and tracking is lost.
The same dataset works well in the original orbslam2. Stereo datasets work great, I only see this in mono.
Do you have any idea what could be causing this? Thanks!
Hi @PWN0N the Map/save feature works great for small datasets. I saved the map of a 4000 frames dataset and was trying the map in another 687 frames. It worked well earlier when map was saved with 1000 frames. Could you please help me solve this issue.
No. of Images Loaded687
ORB-SLAM2 Copyright (C) 2014-2016 Raul Mur-Artal, University of Zaragoza.
This program comes with ABSOLUTELY NO WARRANTY;
This is free software, and you are welcome to redistribute it
under certain conditions. See LICENSE.txt.
Input sensor was set to: Monocular
Loading ORB Vocabulary. This could take a while...
Vocabulary loaded!
/home/orb_Shubham/mapsave-load/edit-orb/ORB_SLAM2/Examples/Monocular/Slam_latest_Map.bin
{INFO}mspMapPoints size = 17399
{INFO}mspKeyFrames size = 33940
terminate called after throwing an instance of 'std::length_error'
what(): vector::reserve
Aborted (core dumped)
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.