Commit Graph

45 Commits

Author SHA1 Message Date
Tadas Baltrusaitis
937e2de488 Integrating OpenFace 1.0.0 changes into CE-CLM branch 2018-04-04 17:48:44 +01:00
Tadas Baltrusaitis
d26107b219 Making sure correct rgb and grayscale images are passed. 2018-04-02 08:15:26 +01:00
Tadas Baltrusaitis
aa2b0c9def Adapting eye gaze script, moving to new multi-face interface, a bug fix in rotation conversion 2018-02-27 08:08:02 +00:00
Tadas Baltrusaitis
4fe4fa0b24 Removing redundant functions (rotation conversions) that have been defined in utilities now. 2018-02-15 08:24:24 +00:00
Tadas Baltrusaitis
608d925364 Adapting matlab demo runners. 2018-02-13 17:51:24 +00:00
Tadas Baltrusaitis
75c0a54d60 More changes to floats, and removing limiting of pose as that leads to an odd bug with the way rotations are currently represented internally. 2017-10-17 21:42:35 +01:00
Tadas Baltrusaitis
71dc98faa0 Some more removal of doubles. 2017-10-04 18:48:14 +01:00
Tadas Baltrusaitis
71174dc32b Moving more stuff over to floats (landmark locations and piece-wise affine warps) 2017-10-02 21:26:56 +01:00
Tadas Baltrusaitis
22d09a5193 Converting some more doubles to floats. 2017-10-01 13:22:03 +01:00
Tadas Baltrusaitis
156cf2e2dd Moving params_local to floats, preparing more things to move to floats. 2017-10-01 09:21:39 +01:00
Tadas Baltrusaitis
15e18028f5 Optimizing CalcParams further. 2017-09-24 16:59:20 +01:00
Tadas Baltrusaitis
c96aa6391b Dealing with unusual image formats (16 bit and 4 channel). 2017-09-02 09:01:24 +01:00
Tadas Baltrusaitis
e8e93c3f96 Incorporating MTCNN face detection with CE-CLM.
Merge remote-tracking branch 'origin/feature/mtcnn_face_det' into feature/CE-CLM

# Conflicts:
#	exe/FaceLandmarkImg/FaceLandmarkImg.cpp
#	exe/FaceLandmarkVid/FaceLandmarkVid.cpp
#	exe/FaceLandmarkVidMulti/FaceLandmarkVidMulti.cpp
#	exe/FeatureExtraction/FeatureExtraction.cpp
#	lib/local/LandmarkDetector/LandmarkDetector.vcxproj
#	lib/local/LandmarkDetector/LandmarkDetector.vcxproj.filters
#	lib/local/LandmarkDetector/src/LandmarkDetectorFunc.cpp
#	lib/local/LandmarkDetector/src/LandmarkDetectorParameters.cpp
#	lib/local/LandmarkDetector/src/LandmarkDetectorUtils.cpp
2017-08-26 13:23:16 +01:00
Tadas Baltrusaitis
452d1b8008 Integrating MTCNN in all of the demos. 2017-08-18 20:57:19 +01:00
Tadas Baltrusaitis
f19fab7ff7 Bringing CE-CLM up to speed with master. 2017-08-03 11:14:49 -04:00
Tadas Baltrusaitis
5959176921 Some big changes:
- face validator is a retrained CNN now
- starting retiring CLM-Z from OpenFace
2017-08-01 17:11:02 -04:00
Tadas Baltrusaitis
39d0dac347 Bug fix with writing video file out when -fdir is used for loading video in. 2017-07-25 14:18:45 -04:00
Tadas Baltrusaitis
165a708796 Decoupling C++ code so that AU detection works properly with a new PDM. 2017-06-20 14:55:59 -04:00
Tadas Baltrusaitis
85c603a85c OpenBLAS fix attempt. 2017-06-12 20:32:59 -04:00
Tadas Baltrusaitis
8de395d4ef Blas fixes for C++ code. 2017-06-12 15:58:19 -04:00
Tadas Baltrusaitis
305af01326 Auto stash before merge of "develop" and "origin/develop"
- Adding new license files
- Replacing images with more suitable CC ones
2017-05-08 21:36:23 -04:00
Tadas Baltrusaitis
1c546298b8 A small fix for linux compilation. 2017-03-08 14:25:13 -05:00
Tadas Baltrusaitis
52c50b4ff3 - Fixing the issue with gaze not tracking properly in video and landmark modes.
- Fixing the simscale/simalign bug
2017-03-08 11:46:50 -05:00
somacoder
764337e2a1 Disable Key Presses if Quiet Mode Enabled
Enables running without OpenCV calling on GTK, which you do not installed if running in a non-interactive manner. Perhaps better solution exist if "interactive" command line was added.
2017-03-05 15:49:01 -05:00
Tadas Baltrusaitis
51f442a3e2 Merge pull request #107 from CJxD/develop
Fix CMake install process for Unix make install
2017-01-03 14:20:34 -05:00
Chris Watts
4260f6a20e Fix AU and triangulation loading for FaceLandmarkImg and FeatureExtraction 2016-12-29 23:40:03 +00:00
Guillaume Chanel
11031f5a36 Bug correction: FeatureExtraction file header corrected. 2016-09-16 10:49:18 +02:00
Guillaume Chanel
358cd6f9e2 Added the possibility to change the output videos codec by specifying the -oc option
A warning is now issued in the case the VideoWriter could not be instantiated, advising to change the codec
This change applies to FaceLandmarkVid* and FeatureExtraction executables
The option is used as "-oc CODEC_FOURCC" and defaults to DIVX. If the user inputs a FOURCC with a size different than 4, than the default codec is used
The option is handled by the function get_video_input_output_params in the LandMarkDetector namespace
2016-09-14 09:00:57 +02:00
Tadas Baltrusaitis
ef15d5c2cd Getting rid of compiler warnings. 2016-08-14 10:20:07 -04:00
Tadas Baltrusaitis
4c2e0bd9a0 Getting rid of some warnings. 2016-08-13 17:56:17 -04:00
Tadas Baltrusaitis
5416048697 Corrections for output, faster compilation in VS2015, retuning experiments. 2016-08-01 13:39:52 -04:00
Tadas Baltrusaitis
2f667bf23d Ubuntu case sensitivity fix in travis test, making sure a check is made to see if image output is successful. 2016-08-01 10:14:58 -04:00
Tadas Baltrusaitis
3fc388cdeb Fixes with -inroot and -outroot 2016-07-31 20:55:29 -04:00
Tadas Baltrusaitis
51ae195124 A number of small fixes, renamings and corrections. 2016-07-31 16:31:17 -04:00
Tadas Baltrusaitis
ee15ecbc46 More testing and prettier drawing on images (with anti-aliasing) 2016-07-31 13:11:14 -04:00
Tadas Baltrusaitis
bb7ba5ba60 A fix to a previous fix - OpenCV does not handle Debug/Release mixing with writing out ,jpeg and .png files, so use .bmp instead 2016-07-31 10:09:35 -04:00
Tadas Baltrusaitis
a62de100e4 A fix to deal with OpenCV not liking to output png in Debug mode. Feature extraction now saves jpg instead of png for aligned face images. 2016-07-31 09:31:47 -04:00
Tadas Baltrusaitis
242ce8d130 Making sure failure returns 1 and success 0, adding an initial attempt at AppVeyor CI for Windows. 2016-07-29 13:04:25 -04:00
Tadas Baltrusaitis
2128589309 A lot of changes:
- New AU recognition models trained on extra datasets - Bosphorus, UNBC, FERA2011
- Cleaner and clearer separation of static and dynamic AU models
- AU training code cleaned up and instructions added
- bug fixes with median feature computation
- AU prediction correction (smoothing and shifting) with post processing
2016-07-22 09:35:50 -04:00
Tadas Baltrusaitis
146dcd5e5b More work on AU - WIP 2016-06-14 17:55:16 -04:00
Tadas Baltrusaitis
65e91da3a6 Full face model. 2016-06-03 16:53:27 -04:00
Tadas Baltrusaitis
27641add77 Cleaning up and adding AU training - WIP 2016-06-03 09:33:04 -04:00
Tadas Baltrusaitis
803575d5b7 More work at establishing AU baselines on SEMAINE and BP4D datasets. 2016-05-24 16:51:18 -04:00
Tadas Baltrusaitis
fc27b5bbb6 Moving things around for clarity. 2016-05-19 11:51:32 -04:00
unknown
57e58a6949 Master commit of OpenFace. 2016-04-28 15:40:36 -04:00