Comments (7)
Hello! Thank you for filing this issue.
I'm guessing you have a line in your config.toml
file which looks like
[calibration]
calibration_init = 'calibration_init.toml'
This is (currently) an undocumented feature which allows you to specify initial parameters for the calibration if you have a guess. It's not needed and you should be able to remove the line to use the automated parameter initialization.
from anipose.
Hi @elhananby ,
Have you resolved this issue?
from anipose.
Hi Pierre, sorry for the very late response!
I took a small break from the specific project but recently tried to re-run it. I followed your advice and removed the line, however the current error I'm getting after running anipose --config [my config filename] calibrate
is:
/home/elhanan_la/Videos/experiment/session1/calibration/calibration.toml
/home/elhanan_la/Videos/experiment/session1/calibration/cam0_calibrate_191029_151437.mp4
43 boards detected
/home/elhanan_la/Videos/experiment/session1/calibration/cam1_calibrate_191029_151437.mp4
61 boards detected
/home/elhanan_la/Videos/experiment/session1/calibration/cam2_calibrate_191029_151437.mp4
95 boards detected
defaultdict(<class 'int'>, {})
Traceback (most recent call last):
File "/home/elhanan_la/.conda/envs/dlc-ubuntu-GPU/bin/anipose", line 8, in <module>
sys.exit(cli())
File "/home/elhanan_la/.conda/envs/dlc-ubuntu-GPU/lib/python3.6/site-packages/click/core.py", line 764, in __call__
return self.main(*args, **kwargs)
File "/home/elhanan_la/.conda/envs/dlc-ubuntu-GPU/lib/python3.6/site-packages/click/core.py", line 717, in main
rv = self.invoke(ctx)
File "/home/elhanan_la/.conda/envs/dlc-ubuntu-GPU/lib/python3.6/site-packages/click/core.py", line 1137, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
File "/home/elhanan_la/.conda/envs/dlc-ubuntu-GPU/lib/python3.6/site-packages/click/core.py", line 956, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/home/elhanan_la/.conda/envs/dlc-ubuntu-GPU/lib/python3.6/site-packages/click/core.py", line 555, in invoke
return callback(*args, **kwargs)
File "/home/elhanan_la/.conda/envs/dlc-ubuntu-GPU/lib/python3.6/site-packages/click/decorators.py", line 64, in new_func
return ctx.invoke(f, obj, *args, **kwargs)
File "/home/elhanan_la/.conda/envs/dlc-ubuntu-GPU/lib/python3.6/site-packages/click/core.py", line 555, in invoke
return callback(*args, **kwargs)
File "/home/elhanan_la/.conda/envs/dlc-ubuntu-GPU/lib/python3.6/site-packages/anipose/anipose.py", line 108, in calibrate
calibrate_all(config)
File "/home/elhanan_la/.conda/envs/dlc-ubuntu-GPU/lib/python3.6/site-packages/anipose/common.py", line 168, in fun
return process_all(config, process_session, **args)
File "/home/elhanan_la/.conda/envs/dlc-ubuntu-GPU/lib/python3.6/site-packages/anipose/common.py", line 153, in process_all
output[past_folders] = process_session(config, path, **args)
File "/home/elhanan_la/.conda/envs/dlc-ubuntu-GPU/lib/python3.6/site-packages/anipose/calibrate.py", line 183, in process_session
n_samp_iter=100, n_samp_full=2000)
File "/home/elhanan_la/.conda/envs/dlc-ubuntu-GPU/lib/python3.6/site-packages/calligator/cameras.py", line 1555, in calibrate_rows
rvecs, tvecs = get_initial_extrinsics(rtvecs)
File "/home/elhanan_la/.conda/envs/dlc-ubuntu-GPU/lib/python3.6/site-packages/calligator/utils.py", line 174, in get_initial_extrinsics
extrinsics = compute_camera_matrices(rtvecs, pairs)
File "/home/elhanan_la/.conda/envs/dlc-ubuntu-GPU/lib/python3.6/site-packages/calligator/utils.py", line 164, in compute_camera_matrices
source = pairs[0][0]
IndexError: list index out of range
From manually running the same videos through OpenCV board detection algorithms I know there are multiple frames where the boards are detected on at least two cameras, so I don't think it's an issue with lack of overlapping frames.
Best,
Elhanan
from anipose.
Huh, that's strange. Could you share your calibration videos and config.toml file so I could reproduce the error?
from anipose.
Looking over the error again, you seem to have very few boards detected, and it's possible there is no overlap between two cameras in those detections. Could it be that you mispecified your calibration board parameters?
from anipose.
Edit:
Ok, I've actually found the issue was with the camera name regex, which I didn't change from the default. the calibration seems to be working now!
I've ran it again on a longer video and got around 300 detections for each camera, and I still get the same error.
I have attached the calibration videos and my config file (which is mostly the default file, i'm just trying to get the calibration working now) via Google drive:
https://drive.google.com/drive/folders/1lfZFQfoNs-mEefIr1B0XiZD76Y2VmrG4?usp=sharing
from anipose.
That's great! I'm glad you got it to work!
I will close this issue then.
Feel free to open another issue if you get another problem!
from anipose.
Related Issues (20)
- anipose label-3d(Unable to access the X Display, is $DISPLAY set properly?)
- Error when running anipose analyze on the hand demo tutorial
- anipose label-3d results not clear on the hand demo tutorial HOT 1
- aniposelib multiple camera calibration HOT 1
- Error " It seems the model for iteration 0 and shuffle 1 and trainFraction 0.95 does not exist."
- windows 10 crashes at start of 'anipose analyze' HOT 2
- anipose analyze -- rename_dlc_files: FileExistsError HOT 1
- anipose analyze gives no output HOT 3
- Environmental test_3 label issue HOT 1
- Demo 3D labeled video doesn't look like as in example HOT 4
- No module named 'vtkCommonCorePython' HOT 1
- Calibration results
- Anipose analyzes videos, but doesn't complete through anipose filter HOT 2
- Anipose analyze not analyzing videos HOT 1
- Multi Camera Support
- Multi camera calibration HOT 4
- Anipose won't analyze HOT 3
- Naming of cameras for calibration
- Struggling to get a calibration .toml HOT 3
- Suggestions for multi-camera calibration
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 anipose.