2021-1-capstone-design2 / 2017103972

Go to a project
Toggle navigation Toggle navigation pinning
김성연
342999ff 1 parent 5310db64

Delete video test

Inline Side-by-side
Showing 4 changed files with 0 additions and 317 deletions
This diff could not be displayed because it is too large.
import dlib, cv2
import numpy as np
detector = dlib.get_frontal_face_detector()
sp = dlib.shape_predictor('models/shape_predictor_68_face_landmarks.dat')
facerec = dlib.face_recognition_model_v1('models/dlib_face_recognition_resnet_model_v1.dat')
descs = np.load('img/descs.npy', allow_pickle=True)[()]
def encode_face(img):
dets = detector(img, 1)
if len(dets) == 0:
return np.empty(0)
for k, d in enumerate(dets):
shape = sp(img, d)
face_descriptor = facerec.compute_face_descriptor(img, shape)
return np.array(face_descriptor)
video_path = './data/record0.mp4'
cap = cv2.VideoCapture(video_path)
if not cap.isOpened():
exit()
_, img_bgr = cap.read() # (800, 1920, 3)
padding_size = 0
resized_width = 1920
video_size = (resized_width, int(img_bgr.shape[0] * resized_width // img_bgr.shape[1]))
output_size = (resized_width, int(img_bgr.shape[0] * resized_width // img_bgr.shape[1] + padding_size * 2))
fourcc = cv2.VideoWriter_fourcc('m', 'p', '4', 'v')
writer = cv2.VideoWriter('%s_output.mp4' % (video_path.split('.')[0]), fourcc, cap.get(cv2.CAP_PROP_FPS), output_size)
while True:
ret, img_bgr = cap.read()
if not ret:
break
img_bgr = cv2.resize(img_bgr, video_size)
img_rgb = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2RGB)
# img_bgr = cv2.copyMakeBorder(img_bgr, top=padding_size, bottom=padding_size, left=0, right=0, borderType=cv2.BORDER_CONSTANT, value=(0,0,0))
dets = detector(img_bgr, 1)
for k, d in enumerate(dets):
shape = sp(img_rgb, d)
face_descriptor = facerec.compute_face_descriptor(img_rgb, shape)
last_found = {'name': 'unknown', 'dist': 0.6, 'color': (0,0,255)}
for name, saved_desc in descs.items():
dist = np.linalg.norm([face_descriptor] - saved_desc, axis=1)
if dist < last_found['dist']:
last_found = {'name': name, 'dist': dist, 'color': (255,255,255)}
cv2.rectangle(img_bgr, pt1=(d.left(), d.top()), pt2=(d.right(), d.bottom()), color=last_found['color'], thickness=2)
cv2.putText(img_bgr, last_found['name'], org=(d.left(), d.top()), fontFace=cv2.FONT_HERSHEY_SIMPLEX, fontScale=1, color=last_found['color'], thickness=2)
writer.write(img_bgr)
cv2.imshow('img', img_bgr)
if cv2.waitKey(1) == ord('q'):
break
cap.release()
writer.release()
import dlib
import cv2
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
import math
import os
import pathlib
import time
import pandas as pd
import tensorflow as tf
from tensorflow.keras.preprocessing.image import ImageDataGenerator,load_img
from tensorflow.keras.models import load_model
from tensorflow.keras import regularizers
from tensorflow import keras
from imutils import face_utils
import time
start = time.time()
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor("./models/shape_predictor_68_face_landmarks.dat")
facerec = dlib.face_recognition_model_v1('models/dlib_face_recognition_resnet_model_v1.dat')
model = load_model('../checkpoint/er-best-mobilenet1-bt32-model-classweight-adam.h5')
# model = load_model('../checkpoint/er-best-mobilenet2-bt32-model-adam.h5')
# model = load_model('../checkpoint/er-best-efficientNet1-bt32-model-SGD.h5')
descs = np.load('img/descs2.npy', allow_pickle=True)[()]
video_path = './data/zoom_1.mp4'
cap=cv2.VideoCapture(video_path)
labels_dict_ = {0 : 'angry', 1 : 'fear' , 2: 'happy', 3: 'neutral', 4: 'sad', 5: 'surprise'}
# labels_dict_ = {'angry' : 0,'fear' : 1 ,'happy' : 2, 'neutral' : 3, 'sad' : 4, 'surprise' : 5}
time_dict = {'angry': [], 'fear': [], 'happy': [], 'neutral': [], 'sad': [], 'surprise': []}
def get_key(val):
for key, value in labels_dict_.items():
if(value == val):
return key
def convertMillis(millis):
seconds=(millis/1000)%60
minutes=(millis/(1000*60))%60
hours=(millis/(1000*60*60))%24
return seconds, int(minutes), int(hours)
#cap = cv2.VideoCapture(0) # 0번 카메라
# 동영상 크기(frame정보)를 읽어옴
frameWidth = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
frameHeight = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
frame_size = (frameWidth, frameHeight)
fps = cap.get((cv2.CAP_PROP_FPS))
_, img_bgr = cap.read() # (800, 1920, 3)
padding_size = 0
resized_width = 1920
video_size = (resized_width, int(img_bgr.shape[0] * resized_width // img_bgr.shape[1]))
timestamps = [cap.get(cv2.CAP_PROP_POS_MSEC)]
prev_time = 0
fourcc = cv2.VideoWriter_fourcc('m', 'p', '4', 'v')
# out1 = cv2.VideoWriter('./data/record0.mp4',fourcc, fps, frame_size)
while True:
retval, frameBGR = cap.read() # 영상을 한 frame씩 읽어오기
current_time = time.time() - prev_time
if(type(frameBGR) == type(None)):
pass
else:
frameBGR = cv2.resize(frameBGR, video_size)
frame = cv2.cvtColor(frameBGR, cv2.COLOR_BGR2RGB)
if (retval is True) and (current_time > 1.5) :
prev_time = time.time()
faces = detector(frame, 1)
for (i, face) in enumerate(faces):
shape = predictor(frame, face)
face_descriptor = facerec.compute_face_descriptor(frame, shape)
img = cv2.resize(frame[face.top():face.bottom(), face.left():face.right()], dsize=(224, 224), interpolation = cv2.INTER_CUBIC)
imgarr = np.array(img).reshape(1, 224, 224, 3) /255
emotion = labels_dict_[model.predict(imgarr).argmax(axis=-1)[0]]
# emotion = get_key(model.predict_classes(imgarr))
last_found = {'name': 'unknown', 'dist': 0.6, 'color': (0,0,255)}
for name, saved_desc in descs.items():
dist = np.linalg.norm([face_descriptor] - saved_desc, axis=1)
if dist < last_found['dist']:
last_found = {'name': name, 'dist': dist, 'color': (255,255,255)}
cv2.rectangle(frameBGR, pt1=(face.left(), face.top()), pt2=(face.right(), face.bottom()), color=last_found['color'], thickness=2)
cv2.putText(frameBGR, last_found['name'] + ',' + emotion , org=(face.left(), face.top()), fontFace=cv2.FONT_HERSHEY_SIMPLEX, fontScale=1, color=last_found['color'], thickness=2)
# cv2.putText(frameBGR, last_found['name'] + ',' , org=(face.left(), face.top()), fontFace=cv2.FONT_HERSHEY_SIMPLEX, fontScale=1, color=last_found['color'], thickness=2)
con_sec, con_min, con_hour = convertMillis(cap.get(cv2.CAP_PROP_POS_MSEC))
time_dict[emotion].append("{0}:{1}:{2}".format(con_hour, con_min, round(con_sec, 3)))
print("{0}:{1}:{2} {3}".format(con_hour, con_min, round(con_sec, 3), emotion))
# print("{0}:{1}:{2} {3}".format(con_hour, con_min, con_sec))
cv2.imshow('frame', frameBGR)
key = cv2.waitKey(25)
if key == 27 :
break
print(time_dict)
print("총 시간 : ", time.time() - start)
if cap.isOpened():
cap.release()
for i in range(1,5):
cv2.destroyAllWindows()
cv2.waitKey(1)
import dlib
import cv2
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
import math
import os
import pathlib
import time
import pandas as pd
import tensorflow as tf
from tensorflow.keras.preprocessing.image import ImageDataGenerator,load_img
from tensorflow.keras.models import load_model
from tensorflow.keras import regularizers
from tensorflow import keras
from imutils import face_utils
import time
start = time.time()
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor("./models/shape_predictor_68_face_landmarks.dat")
facerec = dlib.face_recognition_model_v1('models/dlib_face_recognition_resnet_model_v1.dat')
# model = load_model('../checkpoint/er-best-mobilenet1-bt32-model-adam.h5')
model = load_model('../checkpoint/er-best-efficientNet1-bt32-model-SGD.h5')
descs = np.load('img/descs2.npy', allow_pickle=True)[()]
video_path = './data/zoom_1.mp4'
cap=cv2.VideoCapture(video_path)
# labels_dict_ = {0 : 'angry', 1 : 'fear' , 2: 'happy', 3: 'neutral', 4: 'sad', 5: 'surprise'}
labels_dict_ = {'angry' : 0,'fear' : 1 ,'happy' : 2, 'neutral' : 3, 'sad' : 4, 'surprise' : 5}
time_dict = {'angry': [], 'fear': [], 'happy': [], 'neutral': [], 'sad': [], 'surprise': []}
def get_key(val):
for key, value in labels_dict_.items():
if(value == val):
return key
def convertMillis(millis):
seconds=(millis/1000)%60
minutes=(millis/(1000*60))%60
hours=(millis/(1000*60*60))%24
return seconds, int(minutes), int(hours)
#cap = cv2.VideoCapture(0) # 0번 카메라
# 동영상 크기(frame정보)를 읽어옴
frameWidth = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
frameHeight = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
frame_size = (frameWidth, frameHeight)
fps = cap.get((cv2.CAP_PROP_FPS))
_, img_bgr = cap.read() # (800, 1920, 3)
padding_size = 0
resized_width = 1920
video_size = (resized_width, int(img_bgr.shape[0] * resized_width // img_bgr.shape[1]))
timestamps = [cap.get(cv2.CAP_PROP_POS_MSEC)]
prev_time = 0
fourcc = cv2.VideoWriter_fourcc('m', 'p', '4', 'v')
# out1 = cv2.VideoWriter('./data/record0.mp4',fourcc, fps, frame_size)
while True:
retval, frameBGR = cap.read() # 영상을 한 frame씩 읽어오기
current_time = time.time() - prev_time
if(type(frameBGR) == type(None)):
pass
else:
frameBGR = cv2.resize(frameBGR, video_size)
frame = cv2.cvtColor(frameBGR, cv2.COLOR_BGR2RGB)
if (retval is True) and (current_time > 1.5) :
prev_time = time.time()
faces = detector(frame, 1)
for (i, face) in enumerate(faces):
shape = predictor(frame, face)
face_descriptor = facerec.compute_face_descriptor(frame, shape)
img = cv2.resize(frame[face.top():face.bottom(), face.left():face.right()], dsize=(224, 224), interpolation = cv2.INTER_CUBIC)
imgarr = np.array(img).reshape(1, 224, 224, 3) /255
# emotion = labels_dict_[model.predict(imgarr).argmax(axis=-1)[0]]
emotion = get_key(model.predict_classes(imgarr))
last_found = {'name': 'unknown', 'dist': 0.6, 'color': (0,0,255)}
for name, saved_desc in descs.items():
dist = np.linalg.norm([face_descriptor] - saved_desc, axis=1)
if dist < last_found['dist']:
last_found = {'name': name, 'dist': dist, 'color': (255,255,255)}
cv2.rectangle(frameBGR, pt1=(face.left(), face.top()), pt2=(face.right(), face.bottom()), color=last_found['color'], thickness=2)
cv2.putText(frameBGR, last_found['name'] + ',' + emotion , org=(face.left(), face.top()), fontFace=cv2.FONT_HERSHEY_SIMPLEX, fontScale=1, color=last_found['color'], thickness=2)
# cv2.putText(frameBGR, last_found['name'] + ',' , org=(face.left(), face.top()), fontFace=cv2.FONT_HERSHEY_SIMPLEX, fontScale=1, color=last_found['color'], thickness=2)
con_sec, con_min, con_hour = convertMillis(cap.get(cv2.CAP_PROP_POS_MSEC))
time_dict[emotion].append("{0}:{1}:{2}".format(con_hour, con_min, round(con_sec, 3)))
print("{0}:{1}:{2} {3}".format(con_hour, con_min, round(con_sec, 3), emotion))
# print("{0}:{1}:{2} {3}".format(con_hour, con_min, con_sec))
cv2.imshow('frame', frameBGR)
key = cv2.waitKey(25)
if key == 27 :
break
print(time_dict)
print("총 시간 : ", time.time() - start)
if cap.isOpened():
cap.release()
for i in range(1,5):
cv2.destroyAllWindows()
cv2.waitKey(1)