def run_vfs(video_uri, out_dir, r_config):
"""
Processing all participants for fetching voice frame score
---------------
---------------
Args:
video_uri: video path; r_config: raw variable config object
out_dir: (str) Output directory for processed output
"""
try:
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter) > 0:
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(
audio_file))
empty_vfs(video_uri, out_loc, fl_name, r_config)
return
calc_vfs(video_uri, audio_file, out_loc, fl_name, r_config)
except Exception as e:
logger.error('Failed to process audio file')
def run_eye_gaze(video_uri, out_dir, r_config):
"""
Processing all patient's for getting eye movement artifacts
--------------------------------
--------------------------------
Args:
video_uri: video path; input_dir : input directory for video's
out_dir: (str) Output directory for processed output; r_config: raw variable config object
"""
try:
#filtering path to generate input & output path
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
of_csv_path = glob.glob(join(out_loc, fl_name + '_OF_features/*.csv'))
if len(of_csv_path) > 0:
of_csv = of_csv_path[0]
df_of = pd.read_csv(of_csv, error_bad_lines=False)
logger.info('Processing Output file {} '.format(
os.path.join(out_loc, fl_name)))
calc_eye_mov(video_uri, df_of, out_loc, fl_name, r_config)
except Exception as e:
logger.error('Failed to process video file')
def batch_open_face(filepaths,video_url, input_dir, out_dir, of_path):
""" Computes open_face features for the files in filepaths
Args:
-----
filepaths: (itreable[str])
video_tracking: To specify whether openface's video tracking module (FaceLandmarkVid)
is being used or the default (FeatureExtract)
video_url: Raw video location on S3 bucket
input_dir: Path to the input videos
out_dir: Path to the processed output
of_path: OpenFace source code path
Returns:
--------
(itreable[str]) list of .csv files
"""
suffix = '_OF_features'
csv_files = []
for fp in filepaths:
try:
_, out_loc, fl_name = ut.filter_path(video_url, out_dir)
full_f_name = fl_name + suffix
output_directory = os.path.join(out_loc, full_f_name)
csv_files.append(ut.compute_open_face_features(fp,output_directory,of_path))
except Exception as e:
logger.error('Failed to run OpenFace on {}\n{}'.format(fp, e))
return csv_files
def run_face_expressivity(video_uri, out_dir, f_cfg):
"""
Processing all patient's for fetching facial landmarks
---------------
---------------
Args:
video_uri: video path; f_cfg: raw variable config object
out_dir: (str) Output directory for processed output
"""
try:
#Baseline logic
cfr = ConfigFaceReader()
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
of_csv_path = glob.glob(join(out_loc, fl_name + '_OF_features/*.csv'))
if len(of_csv_path) > 0:
df_of = pd.read_csv(of_csv_path[0], error_bad_lines=False)
df_of = df_of[cfr.AU_fl]
expr_df_list = of_feature(df_of, cfr, f_cfg)
exp_final_df = pd.concat(expr_df_list, ignore_index=True)
exp_final_df['dbm_master_url'] = video_uri
logger.info('Processing Output file {} '.format(
os.path.join(out_loc, fl_name)))
ut.save_output(exp_final_df, out_loc, fl_name, face_expr_dir,
csv_ext)
except Exception as e:
logger.error('Failed to process video file')
def run_transcribe(video_uri, out_dir, r_config, deep_path):
"""
Processing all patient's for fetching Formant freq
---------------
---------------
Args:
video_uri: video path; r_config: raw variable config object
out_dir: (str) Output directory for processed output; deep_path: deepspeech build path
"""
try:
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter) > 0:
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
if float(aud_dur) < 0.1:
logger.info('Output file {} size is less than 0.1 sec'.format(
audio_file))
empty_transcribe(video_uri, out_loc, fl_name, r_config)
return
calc_transcribe(video_uri, audio_file, out_loc, fl_name, r_config,
deep_path, aud_dur)
except Exception as e:
logger.error('Failed to process audio file')
def run_face_asymmetry(video_uri, out_dir, f_cfg):
"""
Processing all patient's for calculating facial asymmetry
---------------
---------------
Args:
video_uri: video path; f_cfg: face config object
out_dir: (str) Output directory for processed output
"""
try:
#Baseline logic
cfr = ConfigFaceReader()
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
of_csv_path = glob.glob(join(out_loc, fl_name + '_OF_features/*.csv'))
if len(of_csv_path) > 0:
of_csv = of_csv_path[0]
asym_df_list = calc_asym_feature(of_csv, f_cfg)
asym_final_df = pd.concat(asym_df_list, ignore_index=True)
asym_final_df['dbm_master_url'] = video_uri
logger.info('Processing Output file {} '.format(
os.path.join(out_loc, fl_name)))
ut.save_output(asym_final_df, out_loc, fl_name, face_asym_dir,
csv_ext)
except Exception as e:
logger.error('Failed to process video file')
def run_pause_segment(video_uri, out_dir, r_config):
"""
Processing all patient's for getting Pause Segment
---------------
---------------
Args:
video_uri: video path; r_config: raw variable config object
out_dir: (str) Output directory for processed output
"""
try:
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
aud_filter = glob.glob(join(input_loc, fl_name + '.wav'))
if len(aud_filter) > 0:
audio_file = aud_filter[0]
aud_dur = librosa.get_duration(filename=audio_file)
if float(aud_dur) < 0.064:
logger.info('Output file {} size is less than 0.064sec'.format(
audio_file))
error_txt = 'error: length less than 0.064'
empty_pause_segment(video_uri, out_loc, fl_name, r_config,
error_txt)
return
logger.info('Converting stereo sound to mono-lD')
sound_mono = AudioSegment.from_wav(audio_file)
sound_mono = sound_mono.set_channels(1)
sound_mono = sound_mono.set_frame_rate(48000)
mono_wav = os.path.join(input_loc, fl_name + '_mono.wav')
sound_mono.export(mono_wav, format="wav")
df_pause_seg = process_silence(mono_wav, r_config)
os.remove(mono_wav) #removing mono wav file
if isinstance(df_pause_seg,
pd.DataFrame) and len(df_pause_seg) > 0:
logger.info('Processing Output file {} '.format(out_loc))
df_pause_seg['dbm_master_url'] = video_uri
ut.save_output(df_pause_seg, out_loc, fl_name, pause_seg_dir,
csv_ext)
else:
error_txt = 'error: webrtcvad returns no segment'
empty_pause_segment(video_uri, out_loc, fl_name, r_config,
error_txt)
except Exception as e:
logger.error('Failed to process audio file')
def run_face_landmark(video_uri, out_dir, f_cfg):
"""
Processing all patient's for fetching facial landmarks
---------------
---------------
Args:
video_uri: video path; f_cfg: raw variable config object
out_dir: (str) Output directory for processed output
"""
try:
#Baseline logic
cfr = ConfigFaceReader()
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
of_csv_path = glob.glob(join(out_loc, fl_name + '_OF_features/*.csv'))
if len(of_csv_path) > 0:
df_of = pd.read_csv(of_csv_path[0], error_bad_lines=False)
df_lmk = df_of[extract_col_nm_lmk(df_of)]
df_lmk = df_lmk.copy()
df_lmk['frame'] = df_of['frame']
df_lmk['face_id'] = df_of[' face_id']
df_lmk['timestamp'] = df_of[' timestamp']
df_lmk['confidence'] = df_of[' confidence']
df_lmk['success'] = df_of[' success']
df_lmk = lmk_col_nm_map(df_lmk)
df_lmk = add_disp_3D(df_lmk)
df_lmk['dbm_master_url'] = video_uri
logger.info('Processing Output file {} '.format(
join(out_loc, fl_name)))
ut.save_output(df_lmk, out_loc, fl_name, face_lmk_dir, csv_ext)
except Exception as e:
logger.error('Failed to process video file')
def run_eye_blink(video_uri, out_dir, r_config, facial_landmarks):
"""
Processing all patient's for getting eye blink artifacts
---------------
---------------
Args:
video_uri: video path; input_dir : input directory for video's
out_dir: (str) Output directory for processed output; r_config: raw variable config object;
facial_landmarks: landmark model path
"""
try:
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
vid_file_path = os.path.exists(video_uri)
if vid_file_path == True:
logger.info('Processing Output file {} '.format(
os.path.join(out_loc, fl_name)))
df_blink = blink_detection(video_uri, facial_landmarks, r_config)
ut.save_output(df_blink, out_loc, fl_name, movement_expr_dir,
csv_ext)
except Exception as e:
logger.error('Failed to process video file')
def run_speech_feature(video_uri, out_dir, r_config):
"""
Processing all patient's for fetching nlp features
-------------------
-------------------
Args:
video_uri: video path; r_config: raw variable config object
out_dir: (str) Output directory for processed output
"""
try:
input_loc, out_loc, fl_name = ut.filter_path(video_uri, out_dir)
transcribe_path = glob.glob(join(out_loc, transcribe_ext))
if len(transcribe_path)>0:
transcribe_df = pd.read_csv(transcribe_path[0])
df_speech= n_util.process_speech(transcribe_df, r_config)
logger.info('Saving Output file {} '.format(out_loc))
ut.save_output(df_speech, out_loc, fl_name, speech_dir, speech_ext)
except Exception as e:
logger.error('Failed to process video file')
