Comments (9)
Processing Video Input
num frames: 1101
fps: 10.0
using groundtruth: video
num_levels: 3
using opencv 4.5.3
WARNING: using NON-ORIENTED features: SHI_TOMASI - NONE (i.e. kp.angle=0)
num_levels: 3
LkFeatureTracker: num levels on LK pyr optic flow: 3
..................................
frame: 0
detector: SHI_TOMASI , #features: 2000 , [kp-filter: SAT ]
The X11 connection broke: No error (code 0)
XIO: fatal IO error 2 (No such file or directory) on X server ":0"
after 734 requests (734 known processed) with 14 events remaining
from pyslam.
from pyslam.
Hi,
thanks for the feedback. Could you please share some info about your OS and its configuration? Python version?etc
from pyslam.
Another question: how did you install pyslam? Did you use one of the install scripts?
from pyslam.
This seems an issue connected to the usage of Tigervnc or similar tools.
See also this thread gnuradio/gnuradio#3568
I recommend finding a support forum for TigerVNC and asking there
from pyslam.
Hi,
thanks for the feedback. Could you please share some info about your OS and its configuration? Python version?etc
It's Ubuntu 20.04 , these are the steps I followed :
- $ git clone --recursive https://github.com/luigifreda/pyslam.git
- $ git checkout ubuntu20
- ./install_basic.sh (which built successfully)
- python3 -O main_vo.py
This is when the error occured.
from pyslam.
Just tested under Ubuntu 20.04 (after an upgrade with sudo apt-get dist-upgrade
) and under an Ubuntu 20.04 docker container run from Ubuntu 18.04 and I didn't get any trouble.
Did you read the instructions in the README?
https://github.com/luigifreda/pyslam#install-pyslam-under-ubuntu-2004
You have to follow the instructions on the following page
https://github.com/luigifreda/pyslam/blob/master/PYTHON-VIRTUAL-ENVS.md
Do not run
./install_basic.sh
Instead, run
. install_all_venv.sh
N.B.: do not forget the dot! (without '/' !)
from pyslam.
It's working now , thank you!
I have an .mp4 file I want to test the "main_vo.py" script with, as I only have the .mp4 file and no camera settings or groundtruth file, is the a way i could go about to run mvo or slam on my .mp4 file.
Any tips to do the same would be greatly appreciated.
I'm familiar with splitting the mp4 file into frames using : ffmpeg and then have a py script to generate timestamps for each image so as to use with ORB SLAM.
I used this blog post for reference : http://20sep1995.blogspot.com/2019/02/how-to-run-orb-slam-with-your-own-data.html
Would love to do something similar using pyslam , to run mvo or SLAM on my custom .mp4 file .
from pyslam.
Did you take a look at the main README file?
https://github.com/luigifreda/pyslam#datasets
https://github.com/luigifreda/pyslam#camera-settings
If you want to use your camera, you have to:
- calibrate it and configure WEBCAM.yaml accordingly. <=== !you always need a calibration file!
- record a video (for instance, by using save_video.py in the folder calibration)
- configure the [VIDEO_DATASET] section of config.ini in order to point to your video. <=== !there's already the management of videos!
from pyslam.
Related Issues (20)
- Seeking clarification on the functions with @property decorator in Frame class in frame.py HOT 1
- Reference material for the SlamDynamicConfig class / Is implementation of search_map_by_projection same as ORB-SLAM2? HOT 1
- is_opencv_version_greater_equal function not working HOT 1
- Why use RANSAC and not USAC from open cv? HOT 3
- How to save slam estimated trajectory for evo evaluate HOT 2
- some question about the edge.set_information in pose_optimization.py HOT 1
- install_all_venv.sh gives error in pangolin lib HOT 2
- What are good parameters for VO? HOT 1
- Can not create "pyslam" environment with python 3.6.9 HOT 1
- Camera pose and map covariance HOT 1
- documentation HOT 1
- Best brutal force SLAM configuration HOT 1
- Error with tensorflow-gpu HOT 2
- ORB_SLAM3 HOT 3
- feature_detector file HOT 2
- webcam error HOT 3
- MatplotLib Not responding HOT 5
- How to reach estimated X,Y,Z,Yaw,Roll and Pitch HOT 14
- Getting error when running the slam HOT 1
- Failed Building wheel for opencv-contrib-python HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pyslam.