def __init__(self):
QMainWindow.__init__(self)
Ui_MainWindow.__init__(self)
self.setupUi(self)
# 初始变量
self.video_path = None
self.video_type = None # 0: offline 1: webcamera
self.status = opt.STATUS_INIT # 0: init 1:playing 2: pause
self.video_label_size = None
self.video_size = None
self.video_show_size = None
self.video_center_box = None
self.fr_ready = False
self.fr_input_img = None
opt.display_mw_view = self.viewList # 更新输出控件
opt.display_mw_sys = self.infoList # 更新输出控件
# 线程设置
self.timer = None
self.fr_worker = None
self.load_worker = None
self.dot_worker = None
# 视频初始参数设置
self.playCapture = VideoCapture()
# self.videoWriter = VideoWriter('*.mp4', VideoWriter_fourcc('M', 'J', 'P', 'G'), self.fps, size)
# 欢迎信息
opt.print_system_gui('欢迎进入系统！')
def login_main(self):
string = '数据加载中，请稍后...'
print(string)
opt.print_system_gui(string)
# 强制处理其他事物，防止GUI卡死
QApplication.processEvents()
string = '正在加载人员数据'
print(string)
opt.print_system_gui(string)
self.load_database()
# 强制处理其他事物，防止GUI卡死
QApplication.processEvents()
string = '正在加载深度神经网络'
print(string)
opt.print_system_gui(string)
self.load_model()
# 强制处理其他事物，防止GUI卡死
QApplication.processEvents()
string = '正在编码人员数据'
print(string)
opt.print_system_gui(string)
self.create_person_data()
# 强制处理其他事物，防止GUI卡死
QApplication.processEvents()
string = '数据加载成功，可以开始监测。'
print(string)
opt.print_system_gui(string)
opt.is_net_load_done = True
def pause(self):
if self.playCapture.isOpened():
# 停止线程
self.timer.stop()
self.fr_worker.stop()
# 改为暂停状态
self.status = opt.STATUS_PAUSE
self.playButton.setIcon(self.style().standardIcon(
QStyle.SP_MediaPlay))
print('暂停显示')
opt.print_system_gui('暂停监测')
def re_play(self):
if self.playCapture.isOpened():
# 启动线程
self.timer.start()
# 改为播放状态
self.status = opt.STATUS_PLAYING
self.playButton.setIcon(self.style().standardIcon(
QStyle.SP_MediaPause))
print('恢复显示')
opt.print_system_gui('恢复监测')
# 延后启动线程
time.sleep(0.01)
self.fr_worker.start()
def stop(self):
if self.playCapture.isOpened():
# 注意先后暂停线程
if self.fr_worker is not None:
self.fr_worker.stop()
if self.timer is not None:
self.timer.stop()
self.playCapture.release()
# 改为停止状态
self.status = opt.STATUS_STOP
self.playButton.setIcon(self.style().standardIcon(
QStyle.SP_MediaPlay))
print('停止显示')
opt.print_system_gui('停止监测')
def chk_video_type(self):
if self.fr_ready:
if self.offlineButton.isChecked(
) and self.video_type != opt.VIDEO_TYPE_OFFLINE:
self.switch_offline()
if self.webcamButton.isChecked(
) and self.video_type != opt.VIDEO_TYPE_WEBCAMERA:
self.switch_webcam()
if self.onlineButton.isChecked(
) and self.video_type != opt.VIDEO_TYPE_ONLINE:
self.switch_online()
else:
print('未加载网络数据')
opt.print_system_gui('未加载网络数据！请先加载网络数据')
def play(self):
if not self.playCapture.isOpened():
if self.video_type is opt.VIDEO_TYPE_WEBCAMERA:
self.playCapture = VideoCapture(0)
else:
print('获取在线流媒体中...')
self.playCapture.open(self.video_path)
# 启动线程
self.timer.start()
# 改为播放状态
self.status = opt.STATUS_PLAYING
self.playButton.setIcon(self.style().standardIcon(
QStyle.SP_MediaPause))
print('开始显示')
opt.print_system_gui('开始监测')
# 延后启动线程
time.sleep(0.01)
self.fr_worker.start()
def who_is_it(self, test_img):
"""
Implements face recognition for the happy house by finding who is the person on the image_path image.
Arguments:
image_path -- path to an image
database -- database containing image encodings along with the name of the person on the image
model -- your Inception model instance in Keras
Returns:
min_dist -- the minimum distance between image_path encoding and the encodings from the database
identity -- string, the name prediction for the person on image_path
"""
# START CODE HERE #
# 适应网络输入尺寸, 预处理变换
test_img = self.img_preprocessing(test_img)
# print(np.shape(test_img))
test_img = torch.unsqueeze(test_img, 0)
# print(np.shape(test_img))
# Step 1: Compute the target "encoding" for the image.
if opt.cuda:
images = Variable(test_img).cuda()
else:
images = Variable(test_img)
self.net.eval()
# Step 1: Compute the encoding for the image.
with torch.no_grad():
encodings = self.net(images)
encoding = torch.squeeze(encodings)
# print(np.shape(encoding))
if opt.cuda:
encoding = encoding.data.cpu().numpy()
else:
encoding = encoding.data.numpy()
# Step 2: Find the closest encoding #
# Initialize "min_dist" to a large value, say 100 (≈1 line)
min_dist = 100
identity = 'None'
# Loop over the database dictionary's names and encodings.
for (name, db_enc) in self.database.items():
# Compute L2 distance between the target "encoding" and the current "emb" from the database. (≈ 1 line)
dist = np.linalg.norm(encoding - db_enc)
print('监测与 %s 距离为： %f ' % (name, dist))
# If this distance is less than the min_dist, then set min_dist to dist, and identity to name. (≈ 3 lines)
if dist < min_dist:
min_dist = dist
identity = name
# END CODE HERE #
time_str = time.strftime('%m月%d日-%H时%M分%S秒')
if min_dist > self.net_best_margin:
string = time_str + ' : ' + '非数据库中人员'
sys_string = '检测事件（监测到人员不在数据库当中，检测距离%0.2f）' % min_dist
else:
string = time_str + ' : ' + identity + '到访'
sys_string = '检测事件（监测到人员%s，检测距离%0.2f）' % (identity, min_dist)
print(opt.WARNING + string + opt.ENDC)
opt.print_view_gui(string)
opt.print_system_gui(sys_string)
def switch_online(self):
self.set_video(video_path='rtmp://58.200.131.2:1935/livetv/hunantv',
video_type=opt.VIDEO_TYPE_ONLINE)
opt.print_system_gui('视频模式：online')
def switch_webcam(self):
self.set_video(video_path='', video_type=opt.VIDEO_TYPE_WEBCAMERA)
opt.print_system_gui('视频模式：webcam')
def switch_offline(self):
self.set_video(video_path='./video/f40.mp4',
video_type=opt.VIDEO_TYPE_OFFLINE)
opt.print_system_gui('视频模式：offline')
def login_finish(self):
self.main_window.show()
opt.print_system_gui('登录系统')
self.close()
def login_fun(self):
fr.login_main()
self.main_window.show()
opt.print_system_gui('登录系统')
self.close()