# get a new pair of eye images if available
eyes_consumed, eye_boxes = eyeDetector.consume_output(wait_needed)
if eyes_consumed:
frame, face_box, _, _ = q[
eyes_produced] # the corresponding frame and the face bounding box for this detection
eyes = eyeDetector.preprocess_output(eye_boxes,
face_image=helpers.crop(
frame, face_box))
q[eyes_produced][2] = eyes
eyes_produced += 1
# get a new face and the bounding box if available
face_consumed, face_box = faceDetector.consume_output(
confidence=args.confidence, wait=wait_needed)
if face_consumed:
face_img, face_box = faceDetector.preprocess_output(
face_box, frame=q[faces_produced][0])
q[faces_produced][1] = face_box
faces_produced += 1
eyeDetector.feed_input(face_img)
headPoseEstimator.feed_input(face_img)
frame = feed.read_next() # get the next frame from the input feed
if frame is not None:
# [original frame, face box, eyes, head pose]
q.append([frame, None, None, None])
faceDetector.feed_input(frame)
else:
# When we reached the end of the input stream we have to wait for all frames to finish processing.
# To avoid idle running the loop, blocking wait is used when no output is available from any model.
wait_needed = not gaze_vector_consumed and not head_pose_consumed and not eyes_consumed and not face_consumed
done = len(q) < 1
def main(args):
fd_infer_time, ld_infer_time, hpe_infer_time, ge_infer_time = 0 ,0 ,0 ,0
start = time.time()
face_detector = FaceDetector(args.model_fd, args.device_fd, args.ext_fd)
fd_load_time = time.time() - start
start = time.time()
landmarks_detector = LandmarksDetector(args.model_ld, args.device_ld, args.ext_ld)
ld_load_time = time.time() - start
start = time.time()
head_pose_estimator = HeadPoseEstimator(args.model_hpe, args.device_hpe, args.ext_hpe)
hpe_load_time = time.time() - start
start = time.time()
gaze_estimator = GazeEstimator(args.model_ge, args.device_ge, args.ext_ge)
ge_load_time = time.time() - start
log.info("Models Loading...")
log.info("Face detection load time :{:.4f}ms".format(fd_load_time))
log.info("Landmarks estimation load time :{:.4f}ms".format(ld_load_time))
log.info("Head pose estimation load time :{:.4f}ms".format(hpe_load_time))
log.info("Gaze estimation load time :{:.4f}ms".format(ge_load_time))
log.info('All Models loaded')
mouse_controller = MouseController('high', 'fast')
if args.input == 0:
input_feeder = InputFeeder('cam', args.input)
elif args.input.endswith('.jpg') or args.input.endswith('.bmp'):
input_feeder = InputFeeder('image', args.input)
else:
input_feeder = InputFeeder('video', args.input)
input_feeder.load_data()
init_w = input_feeder.init_w
init_h = input_feeder.init_h
counter = 0
for flag, frame in input_feeder.next_batch():
if not flag:
break
counter +=1
key = cv2.waitKey(60)
try:
start = time.time()
outputs = face_detector.predict(frame)
face = face_detector.preprocess_output(frame, outputs, init_w, init_h)
fd_infer_time += time.time() - start
start = time.time()
outputs = landmarks_detector.predict(face)
left_eye, right_eye, real_landmraks = landmarks_detector.preprocess_output(face, outputs)
ld_infer_time += time.time() - start
start = time.time()
outputs = head_pose_estimator.predict(face)
head_pose_angles = head_pose_estimator.preprocess_output(outputs)
hpe_infer_time += time.time() - start
start = time.time()
outputs = gaze_estimator.predict(left_eye, right_eye, head_pose_angles)
gaze = gaze_estimator.preprocess_output(outputs)
ge_infer_time += time.time() - start
log.info("Face detection time :{:.4f}ms".format(fd_infer_time/counter))
log.info("Landmarks estimation time :{:.4f}ms".format(ld_infer_time/counter))
log.info("Head pose estimation time :{:.4f}ms".format(hpe_infer_time/counter))
log.info("Gaze estimation time :{:.4f}ms".format(ge_infer_time/counter))
if args.input != 0:
drawer = Drawer(face, real_landmraks, head_pose_angles, gaze)
drawer.draw_landmarks(20)
drawer.draw_head_pose()
drawer.draw_gazes()
drawer.show()
roll_cos = math.cos(head_pose_angles[2] * math.pi/180)
roll_sin = math.sin(head_pose_angles[2] * math.pi/180)
mouse_x = gaze[0] * roll_cos + gaze[0] * roll_sin
mouse_y = gaze[1] * roll_cos + gaze[1] * roll_sin
mouse_controller.move(mouse_x, mouse_y)
except Exception as e:
log.error(e)
finally:
if key == 27:
break
input_feeder.close()