def __init__(self, fname_path):
assert os.path.exists(fname_path), f'file {fname_path} does not exists'
self.fname_path = fname_path
self.datetime = self.extract_datetime(fname_path)
self.fie = flir_image_extractor.FlirImageExtractor(
image_suffix="v.jpg", thermal_suffix="t.png")
self.fie.process_image(fname_path)
self.visual_np = self.fie.get_rgb_np()
self.thermal_np = self.fie.get_thermal_np()
self.marks_list = qr_read.QrMarkList(self.visual_np)
# self.meters = [Meter(mark,self.thermal_np) for mark in self.marks_list.marks] # init meters:
self.vis_therm_ratio = (self.visual_np.shape[0] /
self.thermal_np.shape[0],
self.visual_np.shape[1] /
self.thermal_np.shape[1])
def getCsvData(self, jpgfile, csvfile, plot=False):
start = time.time()
fie = flir_image_extractor.FlirImageExtractor()
fie.process_image(jpgfile)
fie.export_thermal_to_csv(csvfile)
end = time.time()
print("Thermal data in picture " + jpgfile + " written to " + csvfile +
" in " + str(end - start) + " s.")
if (plot):
fie.plot()
def main():
fir = flir_image_extractor.FlirImageExtractor(image_suffix="v.jpg",
thermal_suffix="t.png")
for dir in next(os.walk(input_folder))[1]:
dir_start_time = time.perf_counter()
dir_file_counter = 0
dir_path = os.path.join(input_folder, dir)
log = get_all_logs(dir_path)
print(f"folder:{dir_path} len(log)={len(log)}")
for jpg_file in glob.glob(dir_path + '/' + '*.jpg'):
fname_timestamp = flirfname_2_dt(jpg_file)
log_entry = get_log_entry(log, fname_timestamp)
if log_entry is not None:
new_fname = get_new_fname(log_entry, fname_timestamp)
new_folder = get_new_folder(log_entry, result_folder)
new_fname_path = os.path.join(new_folder, new_fname)
shutil.copyfile(jpg_file, new_fname_path)
print(f"{jpg_file} ---> {new_folder}/{new_fname})")
if need_fir:
fir.process_image(new_fname_path)
fir.save_images()
else: # log entry isn't found
folder = os.path.join(result_folder, not_logged_folder)
os.makedirs(folder, exist_ok=True)
os.rename(jpg_file,
os.path.join(folder, os.path.basename(jpg_file)))
print(
f"{jpg_file} moved to {folder} since related log entry is not found"
)
dir_file_counter += 1
copy_to_archive(dir_path)
shutil.rmtree(dir_path, ignore_errors=True)
os.rmdir(dir_path)
dt = time.perf_counter() - dir_start_time
print(
f"{dir_path}: processed {dir_file_counter} files in {dt/60.:.0f} minutes",
f" avg speed = {dt/dir_file_counter:.0f} sec/file")
def __init__(self, fname_path, skip_thermal=False):
assert os.path.exists(fname_path), f'file {fname_path} does not exists'
self.fname_path = fname_path
self.datetime = self.extract_datetime()
self.fie = flir_image_extractor.FlirImageExtractor(
image_suffix="v.jpg", thermal_suffix="t.png")
cached_thermal = ImageFiles.get_cached_thermal(
fname_path) if Cfg.cache_thermal_allowed else None
self.fie.process_image(fname_path, cached_thermal, skip_thermal)
self.flir_img = self.get_flir_image(fname_path)
self.visual_img = self.fie.get_rgb_np()
self.thermal_np = self.fie.get_thermal_np()
thermal_normalized = (self.thermal_np - np.amin(self.thermal_np)) \
/ (np.amax(self.thermal_np) - np.amin(self.thermal_np))
self.thermal_img = np.array(
np.uint8(cm.inferno(thermal_normalized) * 255)) # inferno,gray
self.thermal_img = cv.cvtColor(self.thermal_img, cv.COLOR_RGBA2BGR)
self.vis_therm_ratio = (self.visual_img.shape[0] /
self.thermal_np.shape[0],
self.visual_img.shape[1] /
self.thermal_np.shape[1])
if self.flir_img.shape[0] > self.flir_img.shape[1]: # vertical
# transpose
# self.flir_img = cv.transpose(self.flir_img)
# self.visual_img = cv.transpose(self.visual_img)
# self.thermal_np = cv.transpose(self.thermal_np)
# self.thermal_img = cv.transpose(self.thermal_img)
# rotate
self.flir_img = np.rot90(self.flir_img)
self.visual_img = np.rot90(self.visual_img)
self.thermal_np = np.rot90(self.thermal_np)
self.thermal_img = np.rot90(self.thermal_img)
self.image_id = ImageFiles.save(self.datetime, self.flir_img,
self.visual_img, self.thermal_np)
self.skip_thermal = skip_thermal
# 구글 API 설정
os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = r'ServiceAccountToken.json'
client = vision.ImageAnnotatorClient()
facenet = cv2.dnn.readNet(
'../training custom dataset/face_detector/deploy.prototxt',
'../training custom dataset/face_detector/res10_300x300_ssd_iter_140000.caffemodel'
)
# FaceDetector 모델 > OpenCv의 DNN
model = load_model('../training custom dataset/mask_detector.model')
# MaskDetector 모델 > Keras 모델
# cv2.VideoWriter(outputFile, fourcc, frame, size) : fourcc는 코덱 정보, frame은 초당 저장될 프레임, size는 저장될 사이즈를 뜻합니다 cv2.VideoWriter_fourcc('D','I','V','X') 이런식으로 사용
# 현재 테스트 동영상의 프레임은 25
thermal_camera = Lepton()
fir = flir_image_extractor.FlirImageExtractor()
cap = cv2.VideoCapture(0)
# 동영상 로드
ret, img = cap.read()
# ret이 True이면 영상이 있다는 뜻
fourcc = cv2.VideoWriter_fourcc('m', 'p', '4', 'v')
out = cv2.VideoWriter('output.mp4', fourcc, 1, (img.shape[1], img.shape[0]))
# cv2.VideoWriter(outputFile, fourcc, frame, size) : fourcc는 코덱 정보, frame은 초당 저장될 프레임, size는 저장될 사이즈를 뜻합니다 cv2.VideoWriter_fourcc('D','I','V','X') 이런식으로 사용
# 현재 테스트 동영상의 프레임은 25
number = 0 # 마스크 안 쓴 사람 사진 저장할 때 사용
def get_max_temperature(thermal_np, x1, y1, x2, y2):
# 온도 데이터에서 얼굴 영역만 잘라서 검사함
crop = thermal_np[y1:y2, x1:x2]