def register():
global faces_db
upload_file = request.files['image']
user_name = request.values.get("name")
if upload_file:
try:
image = cv2.imdecode(np.frombuffer(upload_file.read(), np.uint8), cv2.IMREAD_UNCHANGED)
faces, landmarks = mtcnn_detector.detect(image)
if faces.shape[0] is not 0:
faces_sum = 0
bbox = []
points = []
for i, face in enumerate(faces):
if round(faces[i, 4], 6) > 0.95:
bbox = faces[i, 0:4]
points = landmarks[i, :].reshape((5, 2))
faces_sum += 1
if faces_sum == 1:
nimg = face_preprocess.preprocess(image, bbox, points, image_size='112,112')
cv2.imencode('.png', nimg)[1].tofile('face_db/%s.png' % user_name)
# 更新人脸库
faces_db = load_faces(face_sess, inputs_placeholder, embeddings)
return str({"code": 0, "msg": "success"})
return str({"code": 3, "msg": "image not or much face"})
except:
return str({"code": 2, "msg": "this file is not image or not face"})
else:
return str({"code": 1, "msg": "file is None"})
def load_faces(faces_dir, mtcnn_detector):
face_db = []
with tf.Graph().as_default():
with tf.Session() as sess:
load_mobilefacenet(
"./models/mobilefacenet_model/MobileFaceNet_9925_9680.pb")
inputs_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
for root, dirs, files in os.walk(faces_dir):
for file in files:
input_image = cv2.imread(os.path.join(root, file))
faces, landmarks = mtcnn_detector.detect(input_image)
bbox = faces[0, :4]
points = landmarks[0, :].reshape((5, 2))
nimg = face_preprocess.preprocess(input_image,
bbox,
points,
image_size='112,112')
nimg = nimg - 127.5
nimg = nimg * 0.0078125
name = file.split(".")[0]
input_image = np.expand_dims(nimg, axis=0)
feed_dict = {inputs_placeholder: input_image}
emb_array = sess.run(embeddings, feed_dict=feed_dict)
embedding = sklearn.preprocessing.normalize(
emb_array).flatten()
face_db.append({"name": name, "feature": embedding})
return face_db
def face_register(ifile, IMAGE_SIZE):
frame = cv2.imread(ifile)
#cv2.imshow('image', frame)
faces, landmarks = mtcnn_detector.detect(frame)
if faces.shape[0] is not 0:
faces_sum = 0
bbox = []
points = []
for i, face in enumerate(faces):
if round(faces[i, 4], 6) > 0.95:
bbox = faces[i, 0:4]
points = landmarks[i, :].reshape((5, 2))
faces_sum += 1
if faces_sum == 1:
nimg = face_preprocess.preprocess(frame,
bbox,
points,
image_size=IMAGE_SIZE)
#user_name = input("请输入注册名：")
user_name = os.path.splitext(os.path.basename(ifile))[0]
cv2.imencode('.png', nimg)[1].tofile('face_db/%s.png' % user_name)
print("注册成功！")
else:
print('注册图片有错，图片中有且只有一个人脸')
else:
print('注册图片有错，图片中有且只有一个人脸')
def get_faces(self, face_img):
ret = self.detector.detect_face(face_img)
if ret is None:
return None
bbox, points = ret
if bbox.shape[0] == 0:
return [], [], []
bboxes = []
pointses = []
faces = []
for i in range(len(bbox)):
b = bbox[i, 0:4]
bboxes.append(b)
p = points[i, :].reshape((2, 5)).T
pointses.append(p)
nimg = face_preprocess.preprocess(face_img,
b,
p,
image_size='112,112')
nimg = cv2.cvtColor(nimg, cv2.COLOR_BGR2RGB)
aligned = np.transpose(nimg, (2, 0, 1))
input_blob = np.expand_dims(aligned, axis=0)
data = mx.nd.array(input_blob)
db = mx.io.DataBatch(data=(data, ))
faces.append(db)
return faces, bboxes, pointses
def face_register():
print("点击y确认拍照！")
cap = cv2.VideoCapture(0)
while True:
ret, frame = cap.read()
if ret:
cv2.imshow('image', frame)
if cv2.waitKey(1) & 0xFF == ord('y'):
faces, landmarks = mtcnn_detector.detect(frame)
if faces.shape[0] is not 0:
faces_sum = 0
bbox = []
points = []
for i, face in enumerate(faces):
if round(faces[i, 4], 6) > 0.95:
bbox = faces[i, 0:4]
points = landmarks[i, :].reshape((5, 2))
faces_sum += 1
if faces_sum == 1:
nimg = face_preprocess.preprocess(frame,
bbox,
points,
image_size='112,112')
user_name = input("请输入注册名：")
cv2.imencode('.png', nimg)[1].tofile('face_db/%s.png' %
user_name)
print("注册成功！")
else:
print('注册图片有错，图片中有且只有一个人脸')
else:
print('注册图片有错，图片中有且只有一个人脸')
break
def recognition_face(frame):
try:
faces, landmarks = mtcnn_detector.detect(frame)
if faces.shape[0] is not 0:
faces_sum = 0
for i, face in enumerate(faces):
if round(faces[i, 4], 6) > 0.95:
faces_sum += 1
if faces_sum == 0:
return
# 人脸信息
info_bbox = np.zeros((faces_sum, 4))
info_landmarks = np.zeros((faces_sum, 10))
info_name = []
probs = []
img_i = 0
# 提取图像中的人脸
input_images = np.zeros((faces.shape[0], 112, 112, 3))
for i, face in enumerate(faces):
if round(faces[i, 4], 6) > 0.95:
bbox = faces[i, 0:4]
points = landmarks[i, :].reshape((5, 2))
nimg = face_preprocess.preprocess(frame, bbox, points, image_size='112,112')
# 图像预处理
nimg = nimg - 127.5
nimg = nimg * 0.0078125
input_images[i, :] = nimg
# 关键点和人脸框
info_bbox[img_i] = bbox
info_landmarks[img_i] = landmarks[i, :]
img_i += 1
# 进行人脸识别
feed_dict = {inputs_placeholder: input_images}
emb_arrays = face_sess.run(embeddings, feed_dict=feed_dict)
emb_arrays = sklearn.preprocessing.normalize(emb_arrays)
for i, embedding in enumerate(emb_arrays):
embedding = embedding.flatten()
temp_dict = {}
# 比较已经存在的人脸数据库
for com_face in faces_db:
ret, sim = feature_compare(embedding, com_face["feature"], 0.70)
temp_dict[com_face["name"]] = sim
dict = sorted(temp_dict.items(), key=lambda d: d[1], reverse=True)
if dict[0][1] > VERIFICATION_THRESHOLD:
name = dict[0][0]
probs.append(dict[0][1])
info_name.append(name)
else:
probs.append(dict[0][1])
info_name.append("unknown")
# 如果识别就跳出检测
return info_name, probs, info_bbox, info_landmarks
else:
raise Exception("infer result is None!")
except Exception as e:
print(e)
return None, None, None, None, None, None
def add_faces(mtcnn_detector):
face_db_path = config.FACE_DB_PATH
faces_name = os.listdir(face_db_path)
temp_face_path = config.TEMP_FACE_PATH
for root, dirs, files in os.walk(temp_face_path):
for file in files:
if file not in faces_name:
input_image = cv2.imdecode(np.fromfile(os.path.join(root, file), dtype=np.uint8), 1)
faces, landmarks = mtcnn_detector.detect(input_image)
bbox = faces[0, :4]
points = landmarks[0, :].reshape((5, 2))
nimg = face_preprocess.preprocess(input_image, bbox, points, image_size='112,112')
cv2.imwrite(os.path.join(face_db_path, os.path.basename(file)), nimg)
def get_input(self, face_img):
# ret = self.detector.detect_face(face_img, det_type = self.args.det)
# if ret is None:
# return None
# bbox, points = ret
# if bbox.shape[0]==0:
# return None
# bbox = bbox[0,0:4]
# points = points[0,:].reshape((2,5)).T
# #print(bbox)
# #print(points)
# nimg = face_preprocess.preprocess(face_img, bbox, points, image_size='112,112')
nimg = preprocess(face_img, image_size='112,112')
nimg = cv2.cvtColor(nimg, cv2.COLOR_BGR2RGB)
aligned = np.transpose(nimg, (2, 0, 1))
return aligned
def get_align(self, face_img):
ret = self.detector.detect_face(face_img, det_type=self.args.det)
if ret is None:
return None
bbox, points = ret
if bbox.shape[0] == 0:
return None
box = bbox[0, 0:4]
point = points[0, :].reshape((2, 5)).T
nimg = face_preprocess.preprocess(face_img,
box,
point,
image_size='112,112')
nimg = cv2.cvtColor(nimg, cv2.COLOR_BGR2RGB)
aligned = np.transpose(nimg, (2, 0, 1))
return aligned
def get_face(self, face_img, random_bg=False):
ret = self.detector.detect_face(face_img)
if ret is None:
return None
bbox, points = ret
if bbox.shape[0] == 0:
return None
bbox = bbox[0, 0:4]
points = points[0, :].reshape((2, 5)).T
if random_bg:
b = random.randint(0, 255)
g = random.randint(0, 255)
r = random.randint(0, 255)
borderValue = (b, g, r)
else:
borderValue = 0.0
nimg = face_preprocess.preprocess(face_img, bbox, points, image_size='112,112', borderValue=borderValue)
return nimg
def get_input(self, face_img):
ret = self.detector.detect_face(face_img, det_type=self.args.det)
if ret is None:
return None
bbox, points = ret
if bbox.shape[0] == 0:
return None
bbox_total = []
aliged_total = []
for i in range(min(self.args.FaceMaxNum, len(bbox))):
box = bbox[i, 0:4]
point = points[i, :].reshape((2, 5)).T
nimg = face_preprocess.preprocess(face_img,
box,
point,
image_size='112,112')
nimg = cv2.cvtColor(nimg, cv2.COLOR_BGR2RGB)
aligned = np.transpose(nimg, (2, 0, 1))
bbox_total.append(box)
aliged_total.append(aligned)
return aliged_total, bbox_total
def face_register(img_path, name):
image = cv2.imdecode(np.fromfile(img_path, dtype=np.uint8), 1)
faces, landmarks = mtcnn_detector.detect(image)
if faces.shape[0] is not 0:
faces_sum = 0
bbox = []
points = []
for i, face in enumerate(faces):
if round(faces[i, 4], 6) > 0.95:
bbox = faces[i, 0:4]
points = landmarks[i, :].reshape((5, 2))
faces_sum += 1
if faces_sum == 1:
nimg = face_preprocess.preprocess(image,
bbox,
points,
image_size='112,112')
cv2.imencode('.png', nimg)[1].tofile('face_db/%s.png' % name)
print("注册成功！")
else:
print('注册图片有错，图片中有且只有一个人脸')
else:
print('注册图片有错，图片中有且只有一个人脸')
def face_recognition(img_path):
image = cv2.imdecode(np.fromfile(img_path, dtype=np.uint8), 1)
faces, landmarks = mtcnn_detector.detect(image)
if faces.shape[0] is not 0:
faces_sum = 0
for i, face in enumerate(faces):
if round(faces[i, 4], 6) > 0.95:
faces_sum += 1
if faces_sum > 0:
# 人脸信息
info_location = np.zeros(faces_sum)
info_location[0] = 1
info_name = []
probs = []
# 提取图像中的人脸
input_images = np.zeros((faces.shape[0], 112, 112, 3))
for i, face in enumerate(faces):
if round(faces[i, 4], 6) > 0.95:
bbox = faces[i, 0:4]
points = landmarks[i, :].reshape((5, 2))
nimg = face_preprocess.preprocess(image,
bbox,
points,
image_size='112,112')
nimg = nimg - 127.5
nimg = nimg * 0.0078125
input_images[i, :] = nimg
# 进行人脸识别
feed_dict = {inputs_placeholder: input_images}
emb_arrays = face_sess.run(embeddings, feed_dict=feed_dict)
print(emb_arrays.shape)
emb_arrays = sklearn.preprocessing.normalize(emb_arrays)
print(emb_arrays.shape)
for i, embedding in enumerate(emb_arrays):
embedding = embedding.flatten()
temp_dict = {}
# 比较已经存在的人脸数据库
for com_face in faces_db:
ret, sim = feature_compare(embedding, com_face["feature"],
0.70)
temp_dict[com_face["name"]] = sim
dict = sorted(temp_dict.items(),
key=lambda d: d[1],
reverse=True)
if dict[0][1] > VERIFICATION_THRESHOLD:
name = dict[0][0]
probs.append(dict[0][1])
info_name.append(name)
else:
probs.append(dict[0][1])
info_name.append("unknown")
for k in range(faces_sum):
# 写上人脸信息
x1, y1, x2, y2 = faces[k][0], faces[k][1], faces[k][2], faces[
k][3]
x1 = max(int(x1), 0)
y1 = max(int(y1), 0)
x2 = min(int(x2), image.shape[1])
y2 = min(int(y2), image.shape[0])
prob = '%.2f' % probs[k]
label = "{}, {}".format(info_name[k], prob)
cv2img = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
pilimg = Image.fromarray(cv2img)
draw = ImageDraw.Draw(pilimg)
font = ImageFont.truetype('font/simfang.ttf',
18,
encoding="utf-8")
draw.text((x1, y1 - 18), label, (255, 0, 0), font=font)
image = cv2.cvtColor(np.array(pilimg), cv2.COLOR_RGB2BGR)
cv2.rectangle(image, (x1, y1), (x2, y2), (255, 0, 0), 2)
cv2.imshow('image', image)
cv2.waitKey(0)
cv2.destroyAllWindows()
def main():
cap = cv2.VideoCapture(0)
conf = configparser.ConfigParser()
conf.read("config/main.cfg")
mtcnn_detector = load_mtcnn(conf)
MODEL_PATH = conf.get("MOBILEFACENET", "MODEL_PATH")
VERIFICATION_THRESHOLD = float(
conf.get("MOBILEFACENET", "VERIFICATION_THRESHOLD"))
FACE_DB_PATH = conf.get("MOBILEFACENET", "FACE_DB_PATH")
faces_db = load_faces(FACE_DB_PATH, mtcnn_detector)
with tf.Graph().as_default():
with tf.Session() as sess:
load_mobilefacenet(MODEL_PATH)
inputs_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
while True:
ret, frame = cap.read()
if ret:
faces, landmarks = mtcnn_detector.detect(frame)
if faces.shape[0] is not 0:
input_images = np.zeros((faces.shape[0], 112, 112, 3))
for i, face in enumerate(faces):
if round(faces[i, 4], 6) > 0.95:
bbox = faces[i, 0:4]
points = landmarks[i, :].reshape((5, 2))
nimg = face_preprocess.preprocess(
frame, bbox, points, image_size='112,112')
cv2.imshow("face", nimg)
nimg = nimg - 127.5
nimg = nimg * 0.0078125
# input_image = np.expand_dims(nimg, axis=0)
input_images[i, :] = nimg
feed_dict = {inputs_placeholder: input_images}
emb_arrays = sess.run(embeddings, feed_dict=feed_dict)
emb_arrays = sklearn.preprocessing.normalize(
emb_arrays)
names = []
sims = []
for i, embedding in enumerate(emb_arrays):
embedding = embedding.flatten()
temp_dict = {}
for com_face in faces_db:
ret, sim = feature_compare(
embedding, com_face["feature"], 0.65)
temp_dict[com_face["name"]] = sim
dict = sorted(temp_dict.items(),
key=lambda d: d[1],
reverse=True)
if dict[0][1] > VERIFICATION_THRESHOLD:
name = dict[0][0]
sim = dict[0][1]
else:
name = "unknown"
sim = 0
names.append(name)
sims.append(sim)
x1, y1, x2, y2 = faces[i][0], faces[i][1], faces[
i][2], faces[i][3]
x1 = max(int(x1), 0)
y1 = max(int(y1), 0)
x2 = min(int(x2), frame.shape[1])
y2 = min(int(y2), frame.shape[0])
cv2.rectangle(frame, (x1, y1), (x2, y2),
(255, 0, 0), 2)
draw_rect(faces, names, sims, frame)
cv2.imshow("frame", frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
def main(strargument):
shutil.rmtree("./test")
os.mkdir("./test")
os.remove("result.txt")
f = open("result.txt", "a")
cap = cv2.VideoCapture(strargument)
# cap.set(cv2.CAP_PROP_FRAME_WIDTH, 640)
#cap = cv2.VideoCapture("NTQ.mkv")
#cap = cv2.VideoCapture("/home/fitmta/Real-Time-Face-Detection-OpenCV-GPU/videos/video/out1.1.avi")
#cap = cv2.VideoCapture("http://*****:*****@#[email protected]:8932/mjpg/video.mjpg")
# cap = cv2.VideoCapture("http://*****:*****@[email protected]:8933/Streaming/channels/102/preview")
success, frame = cap.read()
startId = countIdFolder("./face_db/")
# quit if unable to read the video file
if not success:
print('Failed to read video')
sys.exit(1)
#The color of the rectangle we draw around the face
rectangleColor = (0, 165, 255)
#variables holding the current frame number and the current faceid
frameCounter = 0
currentFaceID = 0
#Variables holding the correlation trackers and the name per faceid
conf = configparser.ConfigParser()
conf.read("config/main.cfg")
mtcnn_detector = load_mtcnn(conf)
MODEL_PATH = conf.get("MOBILEFACENET", "MODEL_PATH")
VERIFICATION_THRESHOLD = float(
conf.get("MOBILEFACENET", "VERIFICATION_THRESHOLD"))
FACE_DB_PATH = conf.get("MOBILEFACENET", "FACE_DB_PATH")
BLUR_THRESH = int(conf.get("CUSTOM", "BLUR_THRESH"))
MIN_FACE_SIZE = int(conf.get("MTCNN", "MIN_FACE_SIZE"))
MAX_BLACK_PIXEL = int(conf.get("CUSTOM", "MAX_BLACK_PIXEL"))
YAWL = int(conf.get("CUSTOM", "YAWL"))
YAWR = int(conf.get("CUSTOM", "YAWR"))
PITCHL = int(conf.get("CUSTOM", "PITCHL"))
PITCHR = int(conf.get("CUSTOM", "PITCHR"))
ROLLL = int(conf.get("CUSTOM", "ROLLL"))
ROLLR = int(conf.get("CUSTOM", "ROLLR"))
MAXDISAPPEARED = int(conf.get("CUSTOM", "MAXDISAPPEARED"))
IS_FACE_THRESH = float(conf.get("CUSTOM", "IS_FACE_THRESH"))
EXTEND_Y = int(conf.get("CUSTOM", "EXTEND_Y"))
EXTEND_X = int(conf.get("CUSTOM", "EXTEND_X"))
SIMILAR_THRESH = float(conf.get("CUSTOM", "SIMILAR_THRESH"))
MAX_LIST_LEN = int(conf.get("CUSTOM", "MAX_LIST_LEN"))
MIN_FACE_FOR_SAVE = int(conf.get("CUSTOM", "MIN_FACE_FOR_SAVE"))
LIVE_TIME = int(conf.get("CUSTOM", "LIVE_TIME"))
ROIXL = int(conf.get("CUSTOM", "ROIXL"))
ROIXR = int(conf.get("CUSTOM", "ROIXR"))
ROIYB = int(conf.get("CUSTOM", "ROIYB"))
ROIYA = int(conf.get("CUSTOM", "ROIYA"))
maxDisappeared = MAXDISAPPEARED ## khong xuat hien toi da 100 frame
faces_db = load_faces(FACE_DB_PATH, mtcnn_detector)
# load_face_db = ThreadingUpdatefacedb(FACE_DB_PATH,mtcnn_detector)
time.sleep(10)
for item in faces_db:
print(item["name"])
listTrackedFace = []
mark_detector = MarkDetector()
tm = cv2.TickMeter()
_, sample_frame = cap.read()
height, width = sample_frame.shape[:2]
pose_estimator = PoseEstimator(img_size=(height, width))
with tf.Graph().as_default():
with tf.Session() as sess:
load_mobilefacenet(MODEL_PATH)
inputs_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
try:
start = time.time()
while True:
start1 = time.time()
retval, frame = cap.read()
#Increase the framecounter
frameCounter += 1
if retval:
_frame = frame[ROIYA:ROIYB, ROIXL:ROIXR]
cv2.rectangle(frame, (ROIXL, ROIYA), (ROIXR, ROIYB),
(0, 0, 255), 2)
good_face_index = []
# faces_db = load_face_db.face_db
if (frameCounter % 1) == 0:
### embed and compare name
for i, face_db in enumerate(faces_db):
if not os.path.isdir(
"./face_db/" +
face_db["name"].split("_")[0]):
faces_db.pop(i)
faces, landmarks = mtcnn_detector.detect(_frame)
if faces.shape[0] is not 0:
input_images = np.zeros(
(faces.shape[0], 112, 112, 3))
save_images = np.zeros(
(faces.shape[0], 112, 112, 3))
(yaw, pitch, roll) = (0, 0, 0)
for i, face in enumerate(faces):
if round(faces[i, 4], 6) > IS_FACE_THRESH:
bbox = faces[i, 0:4]
points = landmarks[i, :].reshape(
(5, 2))
nimg = face_preprocess.preprocess(
_frame,
bbox,
points,
image_size='112,112')
save_images[i, :] = nimg
nimg = nimg - 127.5
nimg = nimg * 0.0078125
input_images[i, :] = nimg
(x1, y1, x2, y2) = bbox.astype("int")
if x1 < 0 or y1 < 0 or x2 < 0 or y2 < 0 or x1 >= x2 or y1 >= y2:
continue
temp = int((y2 - y1) / EXTEND_Y)
y1 = y1 + temp
y2 = y2 + temp
temp = int((x2 - x1) / EXTEND_X)
if x1 > temp:
x1 = x1 - temp
x2 = x2 + temp
# cv2.imshow("mainframe",frame)
# cv2.imwrite("temp2.jpg",frame[y1:y2,x1:x2])
face_img = cv2.resize(
_frame[y1:y2, x1:x2], (128, 128))
# cv2.imshow("ok",face_img)
face_img = cv2.cvtColor(
face_img, cv2.COLOR_BGR2RGB)
tm.start()
marks = mark_detector.detect_marks(
[face_img])
tm.stop()
marks *= (x2 - x1)
marks[:, 0] += x1
marks[:, 1] += y1
# mark_detector.draw_marks(
# frame, marks, color=(0, 255, 0))
pose, (
yaw, pitch, roll
) = pose_estimator.solve_pose_by_68_points(
marks)
# temp = frame
# cv2.putText(temp,"yaw: "+str(yaw),(x2,y1),cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 255), thickness=2)
# cv2.putText(temp,"pitch: "+str(pitch),(x2,y1+25),cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 255), thickness=2)
# cv2.putText(temp,"roll: "+str(roll),(x2,y1+50),cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 255), thickness=2)
# cv2.imshow("frame",temp)
# if measureGoodFace(MIN_FACE_SIZE,MAX_BLACK_PIXEL,frame[y1:y2,x1:x2],yaw,pitch,roll,BLUR_THRESH,YAWL,YAWR,PITCHL,PITCHR,ROLLL,ROLLR):
# good_face_index.append(i)
# cv2.waitKey(0)
# print(good_face_index)
feed_dict = {inputs_placeholder: input_images}
emb_arrays = sess.run(embeddings,
feed_dict=feed_dict)
emb_arrays = sklearn.preprocessing.normalize(
emb_arrays)
names = []
sims = []
for i, embedding in enumerate(emb_arrays):
# if len(listTrackedFace)>i and RepresentsInt(listTrackedFace[i].name)==False:
# names.append(listTrackedFace[i].name)
# continue
embedding = embedding.flatten()
temp_dict = {}
for com_face in faces_db:
ret, sim = feature_compare(
embedding, com_face["feature"],
0.65)
temp_dict[com_face["name"]] = sim
# print(temp_dict)
dictResult = sorted(temp_dict.items(),
key=lambda d: d[1],
reverse=True)
# print(dictResult[:5])
name = ""
if len(dictResult) > 0 and dictResult[0][
1] > VERIFICATION_THRESHOLD:
name = dictResult[0][
0] #.split("_")[0]
sim = dictResult[0][1]
## wite log
t = time.time()
f.write(name + "___" +
str((t - start) // 60) + ":" +
str(int(t - start) % 60) +
"\n")
else:
name = "unknown"
sim = 0
names.append(name)
sims.append(sim)
# cv2.imwrite("./test/"+name+"_"+str(frameCounter//60)+":"+str(frameCounter%60)+".jpg",save_images[i,:])
# if len(dictResult)>0 :
# cv2.imwrite("./test/"+names[i]+"_"+str(frameCounter//60)+":"+str(frameCounter%60)+"_"+str(dictResult[0][1])+".jpg",save_images[i,:])
################################ tracker
for i, embedding in enumerate(emb_arrays):
embedding = embedding.flatten()
ResultDict = {}
for objectTrackFace in listTrackedFace:
tempList = []
(x1, y1, x2,
y2) = objectTrackFace.latestBox
for com_face in objectTrackFace.listEmbedding:
ret, sim = feature_compare(
embedding, com_face, 0.65)
tempList.append(sim)
tempList.sort(reverse=True)
if len(tempList) > 0:
if tempList[0] > 0.9 or (
similarIOU(
faces[i, :4].astype(
"int"),
objectTrackFace.
latestBox) and
(frameCounter - objectTrackFace
.latestFrameCounter) < 3):
ResultDict[objectTrackFace.
name] = tempList[0]
dictResult = sorted(ResultDict.items(),
key=lambda d: d[1],
reverse=True)
if True:
if len(
ResultDict
) > 0 and dictResult[0][
1] > SIMILAR_THRESH: ## neu khop -- 0.5
# for ik in range(len(dict)):
# if dict[ik][1]>SIMILAR_THRESH:
nameTrackCurrent = dictResult[0][0]
for index, tempFaceTrack in enumerate(
listTrackedFace):
if tempFaceTrack.name == nameTrackCurrent:
if len(tempFaceTrack.
listImage
) > MAX_LIST_LEN:
tempFaceTrack.listImage.pop(
0)
tempFaceTrack.listEmbedding.pop(
0)
if measureGoodFace(
MIN_FACE_SIZE,
MAX_BLACK_PIXEL,
save_images[
i, :], yaw,
pitch, roll,
BLUR_THRESH,
YAWL, YAWR,
PITCHL, PITCHR,
ROLLL, ROLLR):
tempFaceTrack.listImage.append(
save_images[
i, :])
tempFaceTrack.listEmbedding.append(
emb_arrays[i])
else:
if measureGoodFace(
MIN_FACE_SIZE,
MAX_BLACK_PIXEL,
save_images[
i, :], yaw,
pitch, roll,
BLUR_THRESH,
YAWL, YAWR,
PITCHL, PITCHR,
ROLLL, ROLLR):
tempFaceTrack.listImage.append(
save_images[
i, :])
tempFaceTrack.listEmbedding.append(
emb_arrays[i])
if names[i] != "unknown":
if RepresentsInt(
nameTrackCurrent
):
tempFaceTrack.name = names[
i]
# else: #################
# names[i] = nameTrackCurrent
else:
if not RepresentsInt(
nameTrackCurrent
):
names[
i] = nameTrackCurrent
tempFaceTrack.countDisappeared = 0
tempFaceTrack.latestBox = faces[
i, 0:4].astype("int")
tempFaceTrack.latestFrameCounter = frameCounter
tempFaceTrack.liveTime = 0
tempFaceTrack.justAdded = True ## but we still action with it
break
else: ## neu khong khop thi tao moi nhung chi them anh khi mat du tot
if len(ResultDict) > 0:
print(dictResult[0][1])
if names[i] != "unknown":
newTrackFace = trackedFace(
names[i])
else:
newTrackFace = trackedFace(
str(currentFaceID))
currentFaceID = currentFaceID + 1
if measureGoodFace(
MIN_FACE_SIZE,
MAX_BLACK_PIXEL,
save_images[i, :], yaw,
pitch, roll, BLUR_THRESH,
YAWL, YAWR, PITCHL, PITCHR,
ROLLL, ROLLR):
newTrackFace.listImage.append(
save_images[i, :])
newTrackFace.listEmbedding.append(
emb_arrays[i])
newTrackFace.latestBox = faces[
i, 0:4].astype("int")
newTrackFace.latestFrameCounter = frameCounter
# print(newTrackFace.latestBox)
newTrackFace.justAdded = True
listTrackedFace.append(
newTrackFace) ## add list
### disappeared
for index, trackFace in enumerate(
listTrackedFace):
if trackFace.justAdded == False:
trackFace.countDisappeared = trackFace.countDisappeared + 1
trackFace.liveTime = trackFace.liveTime + 1
else:
trackFace.justAdded = False
if trackFace.liveTime > LIVE_TIME:
t = listTrackedFace.pop(index)
del t
if trackFace.countDisappeared > maxDisappeared:
if len(
trackFace.listImage
) < MIN_FACE_FOR_SAVE: ## neu chua duoc it nhat 5 mat thi xoa luon
trackedFace.countDisappeared = 0
continue
if trackFace.saveTrackedFace(
"./temp/", startId):
startId = startId + 1
t = listTrackedFace.pop(index)
del t
for i, face in enumerate(faces):
x1, y1, x2, y2 = faces[i][0], faces[i][
1], faces[i][2], faces[i][3]
x1 = max(int(x1), 0)
y1 = max(int(y1), 0)
x2 = min(int(x2), _frame.shape[1])
y2 = min(int(y2), _frame.shape[0])
cv2.rectangle(frame,
(x1 + ROIXL, y1 + ROIYA),
(x2 + ROIXL, y2 + ROIYA),
(0, 255, 0), 2)
# if i in good_face_index:
# if not RepresentsInt(names[i]):
cv2.putText(frame, names[i].split("_")[0],
(int(x1 / 2 + x2 / 2 + ROIXL),
int(y1 + ROIYA)),
cv2.FONT_HERSHEY_SIMPLEX, 0.5,
(255, 255, 255), 2)
else:
for index, trackFace in enumerate(
listTrackedFace):
trackFace.countDisappeared = trackFace.countDisappeared + 1
trackFace.liveTime = trackFace.liveTime + 1
if trackFace.liveTime > LIVE_TIME:
t = listTrackedFace.pop(index)
del t
continue
if trackFace.countDisappeared > maxDisappeared:
if len(
trackFace.listImage
) < MIN_FACE_FOR_SAVE: ## neu chua duoc it nhat 5 mat thi xoa luon
trackedFace.countDisappeared = 0
continue
if trackFace.saveTrackedFace(
"./temp/", startId):
startId = startId + 1
t = listTrackedFace.pop(index)
del t
end = time.time()
cv2.putText(frame,
"FPS: " + str(1 // (end - start1)),
(400, 30), cv2.FONT_HERSHEY_SIMPLEX, 1,
(0, 0, 0), 3)
cv2.putText(
frame, "Time: " + str((end - start) // 60) +
":" + str(int(end - start) % 60), (200, 30),
cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 0), 3)
cv2.imshow("frame", frame)
key = cv2.waitKey(30)
if key & 0xFF == ord('q'):
break
if key == 32:
cv2.waitKey(0)
else:
break
except KeyboardInterrupt as e:
pass
gc.collect()
cv2.destroyAllWindows()
exit(0)