Commit Graph

77 Commits

Author SHA1 Message Date
David PAGNON
de5342e51d
width, height, and file_id to int 2024-11-07 11:20:52 +01:00
David PAGNON
d39acd8a12
Do not add annotation if nan in bbox 2024-10-25 18:48:42 +02:00
davidpagnon
02c6512b15 reproj to mmpose/coco format 2024-10-10 00:11:27 +02:00
davidpagnon
5484812929 fixed mmpose reproj 2024-10-09 13:00:05 +02:00
davidpagnon
e321228a75 beta: opensim integration 2024-09-19 00:39:58 +02:00
peterlololsss
215c8a6e6c
implementing OpensimProcessing (#130)
* implementing opensimProcessing

* edited in cooperating with opensimProcessing

* Update scaling2IK.py

* implementing opensimProcessing

* Update and rename scaling2IK.py to kinematics.py

* Add files via upload

* Add files via upload

* Update Config.toml

* Update Config.toml

* Update Config.toml

* Update Config.toml

* Update Config.toml

* Update Config.toml

* implementing opensim processing

* OpenSim part addition

* OpenSim Processing function signature adjustment

* code logic and layout adjustments

* opensimProcessing test enabled

* Update Pose2Sim.py

* Update Pose2Sim.py

* docstring for opensimProcessing updated

* saved folder name changed to opensim

* opensim processing tests enabled

* Deleted a repetitive line at opensim kinematics section
2024-09-18 01:04:52 +02:00
davidpagnon
07afe0b0fb removed tracking option in pose estimation + fixed tests so that synchonization is not done in multiperson Demo + fixed multitab plots crashing 2024-09-17 23:35:40 +02:00
davidpagnon
56d2565f37 only keep right-left alternating and full contact pairs 2024-09-09 17:38:58 +02:00
davidpagnon
2160d47648 new gait event methods 2024-09-09 15:54:22 +02:00
davidpagnon
28e06edd58 no torch dependency if running on CPU 2024-08-06 13:13:31 +02:00
David PAGNON
676c6825fb
fixed when camera not moving 2024-07-31 15:53:31 +02:00
davidpagnon
fa81ecd0ba replace by nan if out of image 2024-07-31 10:47:02 +02:00
davidpagnon
16c8a73bbf Merge branch 'main' of https://github.com/perfanalytics/pose2sim 2024-07-26 16:51:00 +02:00
davidpagnon
7b58454712 Moving cameras supported (to be added to the Pose2Sim main pipeline) 2024-07-26 16:50:51 +02:00
David PAGNON
90d0ccc14a
start at frame 1 instead of 0 2024-07-23 00:14:15 +02:00
David PAGNON
1a8253aa24
optional argument for specifying marker list to export 2024-07-22 22:44:31 +02:00
davidpagnon
2bc68d4d59 fixed batch processing 2024-07-17 16:50:14 +02:00
davidpagnon
b31215c8c0 integration of pose estimation 2024-07-10 10:12:57 +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
cab870efe8 much faster analysis 2024-06-07 14:11:19 +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
davidpagnon
14a4c15fb5 Merge branch 'main' of https://github.com/perfanalytics/pose2sim 2024-04-23 22:46:20 +02:00
davidpagnon
fb191d8a59 added screen axis for c3d so that import possible in blender 2024-04-23 22:46:10 +02:00
David PAGNON
e1cfc22b13
better sorting of json files 2024-04-20 23:12:50 +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
bd9bbb68ab works both for single trial and batch 2024-04-13 18:42:30 +02:00
davidpagnon
88d9ffbfc1 should finish tomorrow 2024-04-12 01:59:32 +02:00
davidpagnon
e858dfd2cd choose ids of persons to display 2024-04-04 23:28:43 +02:00
davidpagnon
2bb5bbbc4b a 2024-03-20 14:16:38 +01:00
davidpagnon
c4773faa68 draft synchro 2024-03-19 10:33:07 +01:00
davidpagnon
f4c764f3cb tests synchro 2024-03-16 15:49:40 +01:00
David PAGNON
ce0abe1929
Faster computation 2024-03-15 10:49:32 +01:00
David PAGNON
864f89c433
Merge pull request #77 from rlagnsals/patch-1
sort by frame number.
2024-03-06 22:32:18 +01:00
davidpagnon
5347f22d49 alternative to multi-person if not satisfying 2024-03-06 22:26:10 +01:00
HunMinKim
23cc2119f1
sort by frame number.
Robust performance on long length frames.
2024-03-06 15:36:22 +09:00
davidpagnon
66df6bbd7c small improvements on multi-person detection 2024-03-04 18:46:56 +01:00
davidpagnon
f7021be051 save images with right ratio 2024-03-01 03:56:10 +01:00
davidpagnon
a948c205cf multi-person analysis almost there 2024-02-28 16:28:09 +01:00
davidpagnon
e9fc09bc2f output type needs to be specified 2024-02-27 21:43:02 +01:00
davidpagnon
05ffe7f36f multi-person frame of work works with single person 2024-02-26 18:13:39 +01:00
davidpagnon
6220c1baa1 fixed only one frame reprojected 2024-02-26 14:57:52 +01:00
davidpagnon
1c2fc6d9d1 minor script changes 2024-02-20 17:21:47 +01:00
David PAGNON
02d2c5c56f
Update reproj_from_trc_calib.py 2024-02-09 00:47:39 +01:00
davidpagnon
6eeaef6445 change version 2024-02-05 17:49:10 +01:00
davidpagnon
bd453fcb58 replace .dot by @ 2024-01-25 11:02:58 +01:00
davidpagnon
070692afaf change RT2qca function -> world_to_camera_persp 2024-01-25 10:53:28 +01:00
davidpagnon
c4de3d03a6 fullproof until limb swapping solved 2024-01-15 11:51:02 +01:00
davidpagnon
57eef5f0c4 undistort to false by default 2024-01-08 13:01:39 +01:00
davidpagnon
76c39fcafd should work on cameras with distortions; still needs to be fully tested 2024-01-02 20:15:43 +01:00