Commit Graph

59 Commits

Author SHA1 Message Date
davidpagnon
e321228a75 beta: opensim integration 2024-09-19 00:39:58 +02:00
David PAGNON
75cbd8376b
interpolation more robust if only nans in keypoint coords 2024-08-28 01:00:15 +02:00
David PAGNON
90a7b86113
debugged sorting 2024-08-25 12:10:56 +02:00
davidpagnon
d35b64efcb clearer error when empty pose directories 2024-07-16 10:11:41 +02:00
davidpagnon
9925d6d8c8 minor fix for concision 2024-07-13 22:16:33 +02:00
davidpagnon
29e27ce355 minor fixes 2024-07-13 22:05:03 +02:00
David PAGNON
05c4502735
Fixed error when no person association 2024-07-11 11:26:50 +02:00
davidpagnon
b31215c8c0 integration of pose estimation 2024-07-10 10:12:57 +02:00
davidpagnon
86f7088b4e option to fill large gaps with nan, last valid value, or zeros 2024-07-09 20:54:18 +02:00
David PAGNON
b2fe4f7ba3
Pose estimation test (#116)
Edits from @hunminkim98's awesome work at integrating pose estimation into Pose2Sim with RTMLib. Most of the changes in syntax are not necessarily better, it is mostly for the code to be more consistent with the rest of the library. Thank you again for your fantastic work!

General:
- Automatically detects whether a valid CUDA install is available. If so, use the GPU with the ONNXRuntime backend. Otherwise, use the CPU with the OpenVINO backend
- The tensorflow version used for marker augmentation was incompatible with the cuda torch installation for pose estimation: edited code and models for it to work with the latest tf version.
- Added logging information to pose estimation
- Readme.md: provided an installation procedure for CUDA (took me a while to find something simple and robust)
- Readme.md: added information about PoseEstimation with RTMLib
- added poseEstimation to tests.py
- created videos for the multi-person case (used to only have json, no video), and reorganized Demo folders. Had to recreate calibration file as well

Json files:
- the json files only saved one person, I made it save all the detected ones
- tracking was not taken into account by rtmlib, which caused issues in synchronization: fixed, waiting for merge
- took the save_to_openpose function out from the main function
- minified the json files (they take less space when all spaces are removed)

Detection results:
- Compared the triangulated locations of RTMpose keypoints to the ones of OpenPose to potentially edit model marker locations on OpenSim. Did not seem to need it.

Others in Config.toml:
- removed the "to_openpose" option, which is not needed
- added the flag: save_video = 'to_images' # 'to_video' or 'to_images' or ['to_video', 'to_images']
- changed the way frame_range was handled (made me change synchronization in depth, as well as personAssociation and triangulation)
- added the flag: time_range_around_maxspeed in synchronization
- automatically detect framerate from video, or set to 60 fps if we work from images (or give a value)
- frame_range -> time_range
- moved height and weight to project (only read for markerAugmentation, and in the future for automatic scaling)
- removed reorder_trc from triangulation and Config -> call it for markerAugmentation instead

Others:
- Provided an installation procedure for OpenSim (for the future) and made continuous installation check its install (a bit harder since it cannot be installed via pip)
- scaling from motion instead of static pose (will have to study whether it's as good or not)
- added logging to synchronization
- Struggled quite a bit with continuous integration


* Starting point of integrating RTMPose into Pose2Sim. (#111)

* RTM_to_Open

Convert format from RTMPose to OpenPose

* rtm_intergrated

* rtm_integrated

* rtm_integrated

* rtm_integrated

* rtm

* Delete build/lib/Pose2Sim directory

* rtm

* Delete build/lib/Pose2Sim directory

* Delete onnxruntime-gpu

* device = cpu

* add pose folder

* Update tests.py

* added annotation

* fix typo

* Should work be still lots of tests to run. Detailed commit coming soon

* intermediary commit

* last checks before v0.9.0

* Update continuous-integration.yml

* Update tests.py

* replaced tabs with spaces

* unittest issue

* unittest typo

* deactivated display for CI test of pose detection

* Try to make continuous integration work

* a

* b

* c

* d

* e

* f

* g

* h

* i

* j

* k

* l

---------

Co-authored-by: HunMinKim <144449115+hunminkim98@users.noreply.github.com>
2024-07-09 16:39:33 +02:00
davidpagnon
21a5e7742b small minor edits 2024-06-24 17:21:56 +02:00
davidpagnon
6cee2078c1 only consider directories when looking for calib_dir 2024-04-26 23:15:34 +02:00
davidpagnon
de14598a42 replace non interpolated values by last valid value; change lxml version; fixed interpolation message 2024-04-26 23:07:48 +02:00
davidpagnon
9a60007a5a forgot an os.listdir -> could not find calib when run from trial + version update 2024-04-26 22:06:03 +02:00
David PAGNON
3a9d405cae
forgot a debugging thing
L181: frame_by_frame_dist += [euclidean_distance(Q_kpt_old[comb[0]][:3],Q_kpt[comb[1]][:3])]
--> removed the [:3]
2024-04-17 09:41:58 +02:00
davidpagnon
db8014c3f5 few changes to the conversion to c3d 2024-04-16 17:28:37 +02:00
HunMinKim
46652a8eaa
Save to c3d and convert trc to c3d (#92)
* make c3d
2024-04-16 11:14:25 +02:00
davidpagnon
139279950b Should be all good 2024-04-15 14:12:14 +02:00
davidpagnon
bd9bbb68ab works both for single trial and batch 2024-04-13 18:42:30 +02:00
davidpagnon
c4773faa68 draft synchro 2024-03-19 10:33:07 +01:00
David PAGNON
ded436e9fe
Merge pull request #78 from ANaaim/minor_correction
Change of the testing of Calib and calib to work properly
2024-03-12 16:40:57 +01:00
davidpagnon
56f55674bf revert to model.predict(outputs) 2024-03-12 16:08:12 +01:00
Anaaim
7e8a93f1a2 Change of the testing of Calib and calib to work properly 2024-03-12 08:39:12 +01:00
davidpagnon
66df6bbd7c small improvements on multi-person detection 2024-03-04 18:46:56 +01:00
David PAGNON
80802c9226
catch interpolation error 2024-02-29 12:55:32 +01:00
davidpagnon
a948c205cf multi-person analysis almost there 2024-02-28 16:28:09 +01:00
davidpagnon
05ffe7f36f multi-person frame of work works with single person 2024-02-26 18:13:39 +01:00
davidpagnon
607865e3d4 beta: multi-person 2024-02-23 18:16:56 +01:00
David PAGNON
ecd39ff943
Check for consistent camera number 2024-02-19 13:30:27 +01:00
davidpagnon
6eeaef6445 change version 2024-02-05 17:49:10 +01:00
davidpagnon
db145942de careless push had overwritten previous changes 2024-02-05 11:51:26 +01:00
davidpagnon
a4d38da980 Added videos and foolproofing stuff 2024-02-05 00:04:36 +01:00
David PAGNON
63a3e3133d
Count cameras with likelihood< threshold as excluded 2024-01-24 13:15:56 +01:00
davidpagnon
fe0a3e66c2 fixed "The requested array has an inhomogeneous shape" 2024-01-08 14:48:19 +01:00
davidpagnon
4ce2cdbcfd Add OpenSim folders 2024-01-08 14:16:21 +01:00
davidpagnon
6f26819827 works in cases where almost all cameras are bad - still disto to be tested 2024-01-05 16:37:41 +01:00
davidpagnon
778b880bad all finally works - last tests still to be run 2024-01-05 14:32:55 +01:00
davidpagnon
5ef5bd1441 typo 2024-01-05 10:43:17 +01:00
davidpagnon
a4f327b13f mostly fixed - last tests to run 2024-01-05 10:33:37 +01:00
davidpagnon
f356f16076 nightly commit. Excluded cameras correctly calculated 2024-01-05 04:22:51 +01:00
davidpagnon
d6b991cf3a nightly commit: cam excluded correctly calculated 2024-01-05 04:20:12 +01:00
davidpagnon
5bee7bf425 wrong copy-paste 2024-01-04 17:20:06 +01:00
davidpagnon
9f8f40d413 undistortion applied to calibration and personAssociation too 2024-01-04 14:19:08 +01:00
davidpagnon
47bbb17d0c fix lens distortion correction. Still to be fully tested 2024-01-03 03:58:10 +01:00
davidpagnon
76c39fcafd should work on cameras with distortions; still needs to be fully tested 2024-01-02 20:15:43 +01:00
davidpagnon
b2046530d5 handle limb swapping 2024-01-01 03:51:31 +01:00
davidpagnon
294914bc3a limb swapping should work but still commented bc not fully tested 2023-12-28 23:08:50 +01:00
davidpagnon
cc25269920 Merge branch 'draft' 2023-12-17 20:04:18 +01:00
davidpagnon
37354e2598 batch processing works but someth strange in filt 2023-12-16 22:15:12 +01:00
davidpagnon
2e6700e747 undistort draft 2023-12-16 19:17:36 +01:00