def feature_extraction_video_traj(file_traj):
print 'old dataset'
##visulaization apathy over week 19_4-29_4
# motion_week = [12.038,9.022,7.974,9.9650,2.113,4.4285,5.7845]
# slight_motion_week = [27.856,22.571,27.846,31.002,13.4013,10.6954,28.1096]
# sedentary_week = [29.236,36.7410,35.1045,53.6780,35.505,43.7546,57.1622]
#
# vis.bar_plot_motion_in_region_over_long_time(motion_week)
##divide image into patches(polygons) and get the positions of each one
my_room = np.zeros((480, 640), dtype=np.uint8)
list_poly = my_img_proc.divide_image(my_room)
##--------------Pre-Processing----------------##
content, skeleton_data_in_time_slices = org_OLDdata_timeIntervals(
file_traj)
#occupancy_histograms = occupancy_histograms_in_time_interval(my_room, list_poly, skeleton_data_in_time_slices)
occupancy_histograms = 1
## create Histograms of Oriented Tracks
HOT_data = histograms_of_oriented_trajectories(
list_poly, skeleton_data_in_time_slices)
#HOT_data = 1
vis.bar_plot_motion_over_time(HOT_data)
def main_pecs_data():
##get raw data for displaying
task_skeleton_data = data_organizer.load_matrix_pickle(
'C:/Users/dario.dotti/Documents/pecs_data_review/skeletons_repetitive_behavior_08082017.txt'
)
##if data contains multiple skeletons here I sort them cronologically
sort_skeletons(task_skeleton_data)
my_room = np.zeros((424, 512, 3), dtype=np.uint8)
my_room += 255
list_poly = img_processing.divide_image(my_room)
#draw_joints_and_tracks(task_skeleton_data,my_room)
#return 0
skeleton_data_in_time_slices = org_data_in_timeIntervals(
task_skeleton_data, [0, 0, 2])
HOT_data, patient_ID = histograms_of_oriented_trajectories(
list_poly, skeleton_data_in_time_slices)
data_organizer.save_matrix_pickle(
HOT_data,
'C:/Users/dario.dotti/Documents/pecs_data_review/HOT_repetitive_behavior_08082017.txt'
)
return frames_where_joint_displacement_over_threshold
def feature_extraction_video_traj(file_traj):
##divide image into patches(polygons) and get the positions of each one
<<<<<<< HEAD
global scene
=======
#global scene
>>>>>>> 9348384985d2847c272133ff77ce6181ca1fa082
#scene = np.zeros((414,512),dtype=np.uint8)
#scene = cv2.imread('C:/Users/dario.dotti/Documents/Datasets/my_dataset/wandering_dataset_um/subject4_1834.jpg')
#scene = cv2.imread('D:/experiment_data/subject_20/388.jpg')
list_poly = my_img_proc.divide_image(scene)
##check patches are correct
# for rect in list_poly:
# cv2.rectangle(scene, (int(rect.vertices[1][0]), int(rect.vertices[1][1])),
# (int(rect.vertices[3][0]), int(rect.vertices[3][1])), (0, 0, 0))
# #
# cv2.imshow('ciao',scene)
# cv2.waitKey(0)
##--------------Pre-Processing----------------##
skeleton_data = xml_parser(file_traj)
##reliability method
#measure_joints_accuracy(skeleton_data)
>>>>>>> 9348384985d2847c272133ff77ce6181ca1fa082
import data_organizer
import img_processing
import AE_rec
feature_p_1 = data_organizer.load_matrix_pickle('C:/Users/dario.dotti/Desktop/Hier_AE_deliverable/head_joint_id1/feature_matrix_participant_task_l2_new_realCoordinates.txt')
<<<<<<< HEAD
feature_p_2 =data_organizer.load_matrix_pickle('C:/Users/dario.dotti/Desktop/Hier_AE_deliverable/head_joint_id1/feature_matrix_participant_master_task_l2_new_realCoordinates.txt')
feature_p = feature_p_1[:19]+feature_p_2[:27]
real_coord = feature_p_1[19:]+feature_p_2[27:]
list_poly = img_processing.divide_image(np.zeros((414,512),dtype=np.uint8))
space_features = []
for i_p in xrange(0,len(real_coord)):
for i_task in xrange(0,len(real_coord[i_p])):
for i_slice in xrange(0,len(real_coord[i_p][i_task])):
votes = np.zeros((16, 3))
for p in xrange(0,len(real_coord[i_p][i_task][i_slice])):
size_per_frame = int(len(real_coord[i_p][i_task][i_slice][p])/3)
x = real_coord[i_p][i_task][i_slice][p][:size_per_frame]
y = real_coord[i_p][i_task][i_slice][p][size_per_frame:(size_per_frame*2)]
z = real_coord[i_p][i_task][i_slice][p][(size_per_frame*2):]
# data_organizer.save_matrix_pickle(training_bayes_vector,
# 'C:/Users/dario.dotti/Documents/data_for_personality_exp/computed_matrix/bayes_vector.txt')
def extract_traj_word_temporal_window(participant_data, n_layer):
<<<<<<< HEAD
scene = cv2.imread('C:/Users/dario.dotti/Documents/Datasets/my_dataset/wandering_dataset_um/exp_scene_depth.jpg')
#scene = np.zeros((414, 512, 3), dtype=np.uint8)
#scene += 255
=======
#scene = cv2.imread('C:/Users/dario.dotti/Documents/Datasets/my_dataset/wandering_dataset_um/exp_scene_depth.jpg')
scene = np.zeros((414, 512, 3), dtype=np.uint8)
scene += 255
>>>>>>> 9348384985d2847c272133ff77ce6181ca1fa082
list_poly = img_processing.divide_image(scene)
size_mask = 20
#max_step = np.sqrt(np.power(((size_mask - 3) - 0), 2) + np.power(((size_mask - 3) - 0), 2)) * 1.3
max_step = 23
matrix_features_participant = []
matrix_original_points_participants = []
matrix_real_coord_participants = []
for i_task, task in enumerate(participant_data):
print 'task: ', i_task
if len(task) == 0: continue