-
Notifications
You must be signed in to change notification settings - Fork 1.7k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
what is K.txt? Why can't I run on my own images? #1564
Comments
What you need to see here is that you have no intrinsic data for your images (see the log So I would advise you to add your camera to the Camera Sensor database For your information K.txt is provided in the sample folder just to provide an Intrinsic camera matrix for reference and if someone wants to use the imagery for another purpose. |
@pmoulon thanks a lot for your time. It is working now. This error is gone. but I am still facing bellow errors in in few cases: Colorize Structure |
Hi @pmoulon I am keep trying with different set of images to construct the lower leg 3d. Do you thing, there is any issue with code or images I am using. please see the full below running process for both files --> SfM_SequentialPipeline.py & SfM_GlobalPipeline.py
|
Are you sure about your focal length value, the initial residual seems very high |
Hi @pmoulon , I am not sure about focal length. but I just tried with random f I guess. |
@pmoulon can you guide me on the attached images how to make perfect 3d out of it. I tried by myself but I do get few points on final ply |
I check your images, here some observations
The best setting for such an application would be to have your patient standing in front of a textured wall and turn around the leg with a camera on a tripod. Shooting 8-12 images with very sharp images would be sufficient and should provide better results. |
(base) D:\git_hub\ralph\openMVG\build\software\SfM>python SfM_SequentialPipeline.py D:\git_hub\ralph\Newfolder\openMVG\build\software\SfM\XRV1\images D:\git_hub\ralph\Newfolder\openMVG\build\software\SfM\output
Using input dir : D:\git_hub\ralph\Newfolder\openMVG\build\software\SfM\XRV1\images
output_dir : D:\git_hub\ralph\Newfolder\openMVG\build\software\SfM\output
You called :
D:/git_hub/ralph/openMVG/build/Windows-AMD64-/Release\openMVG_main_SfMInit_ImageListing
--imageDirectory D:\git_hub\ralph\Newfolder\openMVG\build\software\SfM\XRV1\images
--sensorWidthDatabase D:/git_hub/ralph/openMVG/src/software/SfM/../../openMVG/exif/sensor_width_database\sensor_width_camera_database.txt
--outputDirectory D:\git_hub\ralph\Newfolder\openMVG\build\software\SfM\output\matches
--focal -1
--intrinsics
--camera_model 3
--group_camera_model 1
0% 10 20 30 40 50 60 70 80 90 100%
|----|----|----|----|----|----|----|----|----|----|
Warning & Error messages:
k.txt: Unkown image file format.
SfMInit_ImageListing report:
listed #File(s): 12
usable #File(s) listed in sfm_data: 11
usable #Intrinsic(s) listed in sfm_data: 0
2. Compute features
You called :
D:/git_hub/ralph/openMVG/build/Windows-AMD64-/Release\openMVG_main_ComputeFeatures
--input_file D:\git_hub\ralph\Newfolder\openMVG\build\software\SfM\output\matches\sfm_data.json
--outdir D:\git_hub\ralph\Newfolder\openMVG\build\software\SfM\output\matches
--describerMethod SIFT
--upright 0
--describerPreset NORMAL
--force 0
--numThreads 0
0% 10 20 30 40 50 60 70 80 90 100%
|----|----|----|----|----|----|----|----|----|----|
Task done in (s): 0
3. Compute matches
You called :
D:/git_hub/ralph/openMVG/build/Windows-AMD64-/Release\openMVG_main_ComputeMatches
--input_file D:\git_hub\ralph\Newfolder\openMVG\build\software\SfM\output\matches\sfm_data.json
--out_dir D:\git_hub\ralph\Newfolder\openMVG\build\software\SfM\output\matches
Optional parameters:
--force 0
--ratio 0.8
--geometric_model f
--video_mode_matching -1
--pair_list
--nearest_matching_method AUTO
--guided_matching 0
--cache_size unlimited
0% 10 20 30 40 50 60 70 80 90 100%
|----|----|----|----|----|----|----|----|----|----|
PUTATIVE MATCHES -
PREVIOUS RESULTS LOADED; #pair: 0
'neato' is not recognized as an internal or external command,
operable program or batch file.
Geometric filtering -
0% 10 20 30 40 50 60 70 80 90 100%
|----|----|----|----|----|----|----|----|----|----|
Task done in (s): 0
Export Adjacency Matrix of the pairwise's geometric matches
'neato' is not recognized as an internal or external command,
operable program or batch file.
4. Do Sequential/Incremental reconstruction
Sequential/Incremental reconstruction
Perform incremental SfM (Initial Pair Essential + Resection).
0% 10 20 30 40 50 60 70 80 90 100%
|----|----|----|----|----|----|----|----|----|----|
Track building
Track filtering
Track export to internal struct
Track stats
-- Tracks Stats --
Tracks number: 0
Images Id:
TrackLength, Occurrence
The input SfM_Data file "D:\git_hub\ralph\Newfolder\openMVG\build\software\SfM\output\reconstruction_sequential\sfm_data.bin" cannot be read.
6. Structure from Known Poses (robust triangulation)
Compute Structure from the provided poses
The input SfM_Data file "D:\git_hub\ralph\Newfolder\openMVG\build\software\SfM\output\reconstruction_sequential\sfm_data.bin" cannot be read.
obust.bin" cannot be read.:\git_hub\ralph\Newfolder\openMVG\build\software\SfM\output\reconstruction_sequential
The text was updated successfully, but these errors were encountered: